@article {pmid42655093,
year = {2026},
author = {Pu, J and Cheng, P and Guo, Y and Xiao, D and Zhang, H and Jin, D},
title = {Vagococcus changpingensis sp. nov., a Fly-Associated Bacterium with Human Gut Metagenomic Representatives: Genomic and Metagenomic Insights into Its Ecological Distribution.},
journal = {Microorganisms},
volume = {14},
number = {8},
pages = {},
pmid = {42655093},
issn = {2076-2607},
support = {2025ZD01901104 and 2025ZD01900110//National Science and Technology Major Project of China for the Prevention and Control of Emerging and Major Infectious Diseases/ ; },
abstract = {The genus Vagococcus comprises Gram-positive bacteria with a broad ecological distribution, yet its diversity and potential links between animal and human habitats remain underexplored. Here, we report two novel fly-associated strains, CY52-2[T] and CY62-2, isolated from a retail market in Beijing, China. Polyphasic taxonomic analyses demonstrated that they represent a novel species, for which we propose the name Vagococcus changpingensis sp. nov. Large-scale mining of 805 public metagenomes identified two human gut-derived genomes that share > 99.3% ANI with V. changpingensis, extending the known distribution of this species from insects to the human gastrointestinal tract at the genomic level. Pangenome analysis revealed an open pangenome and uncovered niche-specific gene sets. These findings highlight the power of targeted metagenomics to reveal the potential ecological breadth of newly described species and provide a genomic framework for future investigations of the genus Vagococcus.},
}

@article {pmid42656273,
year = {2026},
author = {Liu, M and Wu, Z and Mao, J and Zhang, S and Xu, S and Min, J and Yu, W and Liu, H and Hu, Y and Wu, X},
title = {Integrative genomic and clinical analysis of carbapenem-resistant and susceptible Klebsiella pneumoniae isolates from a tertiary hospital in Wuhan.},
journal = {Frontiers in cellular and infection microbiology},
volume = {16},
number = {},
pages = {1881548},
pmid = {42656273},
issn = {2235-2988},
mesh = {*Klebsiella pneumoniae/genetics/drug effects/isolation & purification/classification ; Tertiary Care Centers ; Humans ; China/epidemiology ; Phylogeny ; *Klebsiella Infections/microbiology/epidemiology ; Genome, Bacterial ; *Carbapenems/pharmacology ; Anti-Bacterial Agents/pharmacology ; Virulence Factors/genetics ; Genomics ; Polymorphism, Single Nucleotide ; beta-Lactamases/genetics ; Microbial Sensitivity Tests ; Plasmids/genetics ; *Carbapenem-Resistant Enterobacteriaceae/genetics/isolation & purification ; Risk Factors ; Virulence/genetics ; },
abstract = {OBJECTIVES: Carbapenem-resistant Klebsiella pneumoniae (CRKP) has emerged as a major global health threat due to its resistance to carbapenems. As the mechanisms underlying carbapenem resistance in CRKP remain incompletely understood, we seek to provide important insights into the clinical and genomic characteristics of CRKP.

METHODS: A total of 40 CRKP and 42 carbapenem-susceptible Klebsiella pneumoniae (CSKP) isolates were collected from a tertiary hospital in Wuhan, China. Integrating 2,460 publicly available Klebsiella pneumoniae genomes, we conducted a comprehensive analysis of clinical risk factors, resistance and virulence gene profiles, plasmid replicon composition, core genome SNP-based phylogeny, pan-genome structure, and genome-wide single-nucleotide variants and insertions/deletions (SNVs/InDels) variation.

RESULTS: Clinical analysis identified a Charlson comorbidity index > 3 and respiratory tract infections as independent risk factors for CRKP infection. Genomic comparisons revealed that CRKP strains harbored more resistance and virulence genes than CSKP strains, with ST11 being the dominant CRKP clone that frequently carried the blaKPC-2 gene. Phylogenetic analysis incorporating public genomes revealed regional differences in sequence type and carbapenemase genotype distributions. Pan-genome analysis demonstrated open pan-genome characteristics in both groups, with cloud genes representing the largest gene category. Comparative genomic analyses revealed distinct SNV and InDel distribution patterns between CRKP and CSKP isolates, while GO annotation of the prioritized variant-associated genes showed broad functional representation across cellular and metabolic processes, transport and responses to stimuli, membrane-associated components, and binding and catalytic functions.

CONCLUSIONS: CCI >3 and respiratory tract infection were independently associated with CRKP infection. ST11-blaKPC-2 was the predominant epidemic lineage and CRKP isolates carried a greater burden of resistance and virulence determinants than CSKP isolates. Phylogenetic, pan-genomic, and comparative genomic analyses revealed substantial genomic diversity and distinct genomic variation patterns between CRKP and CSKP. These findings provide insights into the clinical risk profile, clonal dynamics, and genomic evolution of CRKP, informing future surveillance and infection control strategies.},
}

*Klebsiella pneumoniae/genetics/drug effects/isolation & purification/classification
Tertiary Care Centers
Humans
China/epidemiology
Phylogeny
*Klebsiella Infections/microbiology/epidemiology
Genome, Bacterial
*Carbapenems/pharmacology
Anti-Bacterial Agents/pharmacology
Virulence Factors/genetics
Genomics
Polymorphism, Single Nucleotide
beta-Lactamases/genetics
Microbial Sensitivity Tests
Plasmids/genetics
*Carbapenem-Resistant Enterobacteriaceae/genetics/isolation & purification
Risk Factors
Virulence/genetics

@article {pmid42656412,
year = {2026},
author = {Pearl, S and Anbarasu, A},
title = {Comparative genomics of carbapenem resistant and susceptible clinical Acinetobacter baumannii reveals lineage-associated mobilization of acquired carbapenemase determinants: an integrative in silico genomics approach.},
journal = {Frontiers in cellular and infection microbiology},
volume = {16},
number = {},
pages = {1886564},
pmid = {42656412},
issn = {2235-2988},
mesh = {*Acinetobacter baumannii/genetics/drug effects/classification/enzymology/isolation & purification ; *Carbapenems/pharmacology ; *beta-Lactamases/genetics ; *Genomics/methods ; *Bacterial Proteins/genetics ; Humans ; *Anti-Bacterial Agents/pharmacology ; Genome, Bacterial ; Acinetobacter Infections/microbiology ; Interspersed Repetitive Sequences ; Genotype ; Microbial Sensitivity Tests ; Gene Transfer, Horizontal ; Virulence Factors/genetics ; Computer Simulation ; Plasmids/genetics ; Phylogeny ; },
abstract = {BACKGROUND: Carbapenem resistant Acinetobacter baumannii (CRAB) is recognized as one of the most critical priority pathogens by the World Health Organization due to its persistence in nosocomial settings, extensive antimicrobial resistance, and increasing dissemination at the global level. Despite the escalating availability of genomic data, genotype-phenotype integrated studies exploring the genetic determinants associated with carbapenem resistance remain limited.

METHODS: In this study, a comprehensive comparative genomics was performed using publicly available 395 clinical A. baumannii genomes, comprising of 267 CRAB and 128 carbapenem susceptible A. baumannii (CSAB). Comparative genomic analyses included sequence types (STs), virulence factors (VFs), antimicrobial resistance genes (ARGs), and mobile genetic elements (MGEs) characterization. Pangenome-wide association study (PanGWAS) was performed to test the associations between genotypes and carbapenem resistance phenotype.

RESULTS: CRAB genome subset demonstrated higher abundance of ARGs (acquired carbapenemases in particular), plasmids, carbapenem resistance-associated insertion sequences, and integrons than CSAB genomes. PanGWAS identified six positively associated genes (relE, umuC, hphA, hsmA, hphR, and fecI) significantly enriched in CRAB population. Core SNP phylogeny integrated with STs and acquired carbapenemase genes exhibited heterogeneous distribution of resistance genes across lineages, indicating potential role of both clonal dissemination and horizontal gene transfer.

CONCLUSION: This study provides an overall genomic architecture of CRAB integrating comparative genomics, PanGWAS, and phylogenomics approaches. The findings underscore the complex interplay between ARGs, VFs, and MGEs in the genomic evolution of CRAB, expanding current understanding of CRAB adaptation and may contribute toward enhanced surveillance, antimicrobial stewardship, and exploration of alternative therapeutic targets.},
}

*Acinetobacter baumannii/genetics/drug effects/classification/enzymology/isolation & purification
*Carbapenems/pharmacology
*beta-Lactamases/genetics
*Genomics/methods
*Bacterial Proteins/genetics
Humans
*Anti-Bacterial Agents/pharmacology
Genome, Bacterial
Acinetobacter Infections/microbiology
Interspersed Repetitive Sequences
Genotype
Microbial Sensitivity Tests
Gene Transfer, Horizontal
Virulence Factors/genetics
Computer Simulation
Plasmids/genetics
Phylogeny

@article {pmid42658326,
year = {2026},
author = {Anandan, N and Venkatachalam, R and Sundar, S},
title = {Pan-genomic analysis of the multi-drug resistant strains of Mycobacterium tuberculosis.},
journal = {World journal of microbiology & biotechnology},
volume = {42},
number = {9},
pages = {},
pmid = {42658326},
issn = {1573-0972},
mesh = {*Mycobacterium tuberculosis/genetics/drug effects/isolation & purification/classification ; *Genome, Bacterial/genetics ; India ; *Drug Resistance, Multiple, Bacterial/genetics ; *Tuberculosis, Multidrug-Resistant/microbiology ; Antitubercular Agents/pharmacology ; Whole Genome Sequencing ; Humans ; Genomics ; Genetic Variation ; Computational Biology ; Phylogeny ; Genes, Bacterial/genetics ; Microbial Sensitivity Tests ; },
abstract = {Tuberculosis (TB) caused by Mycobacterium tuberculosis (Mtb) remains one of the most critical infectious diseases worldwide. The emergence of multi-drug resistant tuberculosis (MDR-TB) continues to pose a significant challenge to effective treatment and disease control. This study aims to perform a pan-genome analysis of MDR-TB isolates from three eastern Indian states namely Arunachal Pradesh, Odisha and Sikkim to analyze the regional genomic diversity, identify the antibiotic resistance genes prevalent within these populations and functionally characterize the accessory genes present.Whole-genome sequencing (WGS) datasets retrieved from public repositories were processed and analyzed using a bioinformatics pipeline comprising FastQC, Trimmomatic, Unicycler, Prokka, Roary, PanGP, RAxML, Phandango, TB-Profiler and eggNOG mapper. The analysis classified genes into core and accessory genomes and evaluated the openness of the pan-genome isolates from the three regions using Heaps' and power law model. The results indicated that MDR-TB pan-genome remains open across all three states suggesting ongoing gene diversity. The investigation of resistance genes enabled the identification of prevalent resistance patterns among the eastern Indian isolates. Functional annotation and KEGG pathway mapping of accessory genes and hypothetical proteins were carried out to understand their biological roles and identify potential targets for drug development.},
}

*Mycobacterium tuberculosis/genetics/drug effects/isolation & purification/classification
*Genome, Bacterial/genetics
India
*Drug Resistance, Multiple, Bacterial/genetics
*Tuberculosis, Multidrug-Resistant/microbiology
Antitubercular Agents/pharmacology
Whole Genome Sequencing
Humans
Genomics
Genetic Variation
Computational Biology
Phylogeny
Genes, Bacterial/genetics
Microbial Sensitivity Tests

@article {pmid42658440,
year = {2026},
author = {Chen, Y and Shi, H and Zhang, H and Chen, M and Cao, Z and Ma, C and Xu, J},
title = {Complete Genome Sequence Analysis, Probiotic Properties, and Safety Assessment of Healthy Human-Derived Pediococcus pentosaceus.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {42658440},
issn = {1867-1314},
support = {2023YFC0871200//the National Key R and D Program of China/ ; },
abstract = {The probiotic potential of microorganisms is generally strain-specific and requires comprehensive evaluation at the strain level. In this study, two human-derived Pediococcus pentosaceus strains, MIANGUAN and MIANGUAN2, which have previously demonstrated beneficial effects in animal models, were subjected to integrated genomic and phenotypic characterization. Complete genome sequencing revealed that both strains possessed one chromosome and four plasmids, together with genetic features associated with carbohydrate metabolism, stress adaptation, adhesion-related functions, and biosynthesis of secondary metabolites. Pan-genome analysis further identified strain-specific genetic characteristics and provided insights into their potential ecological adaptation. In vitro assays conducted according to FAO/WHO recommendations demonstrated tolerance to simulated gastrointestinal conditions, aggregation capacity, adhesion ability, and antimicrobial activity. Additional safety assessments showed absence of hemolytic activity, gelatinase activity, cytotoxicity, and transferable antibiotic resistance determinants. A Penocin_A-associated gene cluster was identified in MIANGUAN2; however, neutralized cell-free supernatant assays indicated that organic acids were the major contributors to antibacterial activity under the tested conditions. Collectively, this study provides a comprehensive genomic and experimental characterization of two human-derived P. pentosaceus strains and supports their further investigation as potential probiotic candidates.},
}

@article {pmid42643404,
year = {2026},
author = {Cuccato, M and Chiesa, F and Mazzone, E and Divari, S and Cannizzo, FT},
title = {Characterization of Actinobacillus pleuropneumoniae isolates from pigs in Piedmont, Italy, by whole-genome sequencing: insights into antimicrobial resistance.},
journal = {Frontiers in veterinary science},
volume = {13},
number = {},
pages = {1861912},
pmid = {42643404},
issn = {2297-1769},
abstract = {BACKGROUND: Actinobacillus pleuropneumoniae (APP) remains a major respiratory pathogen in swine production worldwide. The limited cross-protection of available vaccines and the increasing occurrence of antimicrobial resistance (AMR) highlight the need for integrated phenotypic and genomic surveillance to support effective local control strategies.

METHODS: Twelve APP isolates previously collected in Piedmont (Italy) were investigated. Antimicrobial susceptibility was assessed by minimum inhibitory concentration (MIC) testing against a panel of antimicrobials commonly used in swine medicine. Whole-genome sequencing was performed using Illumina technology, followed by resistome profiling and comparative genomic analyses. Virulence-associated genes, including apx toxin genes and capsular polysaccharide loci, were also characterized.

RESULTS: Phenotypic testing revealed resistance to tetracycline, macrolides, β-lactams, tiamulin, and sulfamethoxazole/trimethoprim in a subset of strains. Genomic analysis identified tetracycline- and phenicol-resistance genes (tet, flor) in one isolate, while genes associated with macrolide and elfamycin resistance were widespread across the dataset. All isolates carried major apx toxin genes, with variable distribution of apxII and apxIII operons. A serovar 9/11 isolate showed a partial deletion within the capsular polysaccharide biosynthesis locus, confirmed by PCR and sequencing. Comparative genomics also suggested distinct genomic lineages among serovar 6 isolates.

CONCLUSION: The combined phenotypic and genomic approach provides valuable insights for evidence-based antimicrobial use and provides additional genomic information on clinically relevant APP field isolates and supports future studies on AMR and genomic diversity.},
}

@article {pmid42643698,
year = {2026},
author = {Su, X and Du, R and Xing, Z and Yang, Q and Liu, Y and Wang, Y and Zhu, Y and Ye, J and Lin, T},
title = {Graph-based pangenomics reveals the genetic basis of agronomic traits in tomato fruits.},
journal = {Horticulture research},
volume = {13},
number = {9},
pages = {uhag147},
pmid = {42643698},
issn = {2662-6810},
abstract = {Tomato serves as a globally important vegetable crop and a genetic model organism, and the improvement of its agronomic traits represents a central objective in breeding. While graph-based pangenomes comprehensively capture species-wide genetic diversity, those built from large cohorts of individuals frequently present considerable computational challenges. To address this, we constructed a graph-based pangenome that integrated only the spectrum of genetic variants between wild (Solanum pimpinellifolium) and cultivated tomato (Solanum lycopersicum). By balancing reduced resource demands with reliable variant calling accuracy, this resource establishes a practical foundation for high-throughput genetic analysis. Using the graph-based pangenome and an F7 recombinant inbred line (RIL) population, genome-wide association studies (GWAS) pinpointed known loci for trichome, vegetative form, and weight traits, as well as a novel fruit-weight locus, fw6.4. The candidate gene SlILL6 within this region likely affects fruit weight (FW) by modulating cell expansion. Metabolite profiling revealed micro-scale quality variation and identified 128 differentially accumulated metabolites. Among these, a GDSL lipase-like caffeoyltransferase (SlCGT) was found to function as a negative regulator of chlorogenic acid content, thereby affecting fruit resistance to pathogenic fungi. Integrating a graph-based pangenome with multi-omics data, this research deciphered the genetic basis of complex traits and supplies new genomic resources, analytical tools, and candidate genes for tomato improvement.},
}

@article {pmid42643750,
year = {2026},
author = {Wang, Y and Zhang, Y and Zhang, Y and Tan, H and Liu, L and Xu, S and Qu, J and Shu, Y and Wu, X and Xu, R and Zhang, S},
title = {Pan-species genome-wide evolution of the RGF peptide gene family and its impact on adventitious root regeneration in apple.},
journal = {Horticulture research},
volume = {13},
number = {9},
pages = {uhag151},
pmid = {42643750},
issn = {2662-6810},
abstract = {Root meristem growth factors (RGFs) are pivotal regulators of root growth in plants and are critically involved in the regulation of root development in fruit trees. In this study, we constructed a comprehensive small secreted peptide library from 64 plant species. Using a structure-based screening strategy, we identified a total of 495 RGF genes. Phylogenetic analysis revealed that the modern RGF gene family originated in ferns and exhibited an evolutionary pattern of initial contraction and subsequent expansion, consistent with the evolutionary emergence and diversification of plant root systems. Analysis of the Malus pan-genome indicated that RGF genes within the genus were classified into 12 clades, with some clades present exclusively in wild Malus species. Notably, the repertoire and copy number of RGF peptides vary significantly among Malus species with different ploidy levels, suggesting a potential association between RGF gene expansion and polyploidization. Functional analysis of a gene encoding the canonical RGF mature peptide 'DYTPARKKPPIHN' in Malus demonstrated a dose-dependent effect on primary root elongation in apple seedlings following exogenous application. Subsequent experiments confirmed that overexpression of MdglRGF1 negatively regulates adventitious root growth during regeneration-associated and hormone-induced adventitious rooting, a phenotype sustained throughout adventitious root development in soil-grown seedlings. Collectively, our research provides novel insights into the identification and functional characterization of small peptides and establishes a foundation for their potential application in apple rootstock breeding and the development of ideal root system architecture.},
}

@article {pmid42645566,
year = {2026},
author = {Chen, H and Wu, Z and Yang, Q and Yu, W and Zhou, H},
title = {A Strain of Mycoplasma hominis Causing Pleuropneumonia Infection in an Immunocompetent Patient and Recent Epidemiological Trends: Implications for Clinical Management.},
journal = {Current microbiology},
volume = {83},
number = {10},
pages = {},
pmid = {42645566},
issn = {1432-0991},
support = {2022YFC2504502//he Key R&D Plan of the Ministry of Science and Technology of China/ ; 2023C03068//the Research and Development Program of Zhejiang Province/ ; 82272338//the National Natural Science Foundation of China/ ; },
mesh = {Humans ; *Mycoplasma hominis/genetics/drug effects/isolation & purification/classification ; Phylogeny ; Anti-Bacterial Agents/pharmacology ; China/epidemiology ; *Pleuropneumonia/microbiology/epidemiology/drug therapy ; Drug Resistance, Bacterial ; Genome, Bacterial ; Microbial Sensitivity Tests ; Whole Genome Sequencing ; *Mycoplasma Infections/microbiology/epidemiology ; Polymorphism, Single Nucleotide ; Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization ; Fluoroquinolones/pharmacology ; },
abstract = {Mycoplasma hominis (M. hominis) is an opportunistic pathogen linked to urogenital and neonatal infections; however, limited genetic and epidemiological data are available. Extragenital infections in healthy adults are rare, and effective antibiotics are species-specific, complicating diagnosis and treatment. Hence, this study aimed to elucidate the clinical process, update the epidemiological characteristics, and investigate the genomic features of a fluoroquinolone-resistant M. hominis isolate from an immunocompetent patient with pleuropneumonia in China. The M. hominis isolate ZY_MH01 was recovered from pleural fluid and was identified by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and Whole Genome Sequencing (WGS). The completed genome was annotated using the NCBI Prokaryotic Genome Annotation Pipeline (PGAP). Snippy v4.4.5 was utilized to conduct a core genome single nucleotide polymorphism (cgSNP) analysis between ZY_MH01 and 144 M. hominis strains from the NCBI GenBank database. Subsequently, phylogenies were constructed using IQ-TREE v3.1.2 and visualized by iTOL. Antimicrobial resistance determinants were identified using strict criteria of Comprehensive Antibiotic Resistance Database (CARD) RGI 6.0.5 (Web portal) and broth microdilution test. Virulence genes were screened using Abricate v1.0.1 against the Virulence Factor Database (VFDB). A total of 42 strains (including ZY_MH01) from Genbank with an assembly level of Complete or Chromosome were re-annotated using Prokka v1.2.0 and pangenome analysis was performed using the Roary. The core genome constitutes only 17.1%, which may contribute to the unusually high level of polymorphism observed among M. hominis strains. No antibiotic resistance genes or virulence genes were detected in the genome of ZY_MH01. However, some resistance-associated mutations of gene parC and gyrA in the Quinolone Resistance Determining Region (QRDR) were identified. Phylogenetic analysis indicates that strains originating from the same geographic region typically exhibit reduced genetic distances; this trend is especially pronounced in regions with a higher number of publicly available strain sequences. In specific circumstances, when conventional broad-spectrum antibiotics are ineffective, even immunocompetent patients should consider the possibility of M. hominis infection. This study presents a detailed account of the diagnostic and therapeutic course of a pleuropneumonia infection caused by M. hominis in an immunocompetent patient, and performs an epidemiological analysis of all M. hominis sequences that have been recently made publicly available.},
}

Humans
*Mycoplasma hominis/genetics/drug effects/isolation & purification/classification
Phylogeny
Anti-Bacterial Agents/pharmacology
China/epidemiology
*Pleuropneumonia/microbiology/epidemiology/drug therapy
Drug Resistance, Bacterial
Genome, Bacterial
Microbial Sensitivity Tests
Whole Genome Sequencing
*Mycoplasma Infections/microbiology/epidemiology
Polymorphism, Single Nucleotide
Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization
Fluoroquinolones/pharmacology

@article {pmid42647157,
year = {2026},
author = {Flores-Lopez, LF and Callejas, DM and Vidaver, AK and Khokhani, D and Morales-Galvan, O and Roman-Reyna, V},
title = {Ecogenomic Diversity of Clavibacter nebraskensis in North America.},
journal = {Phytopathology},
volume = {},
number = {},
pages = {},
doi = {10.1094/PHYTO-02-26-0042-FI},
pmid = {42647157},
issn = {0031-949X},
abstract = {Goss's wilt and leaf blight of maize is caused by Clavibacter nebraskensis and has reemerged as an important disease in North America. Despite its epidemiological relevance, this species remains poorly characterized in terms of population structure, functional diversity, and ecological differentiation, particularly among strains reported from Mexico. In this study, long-read whole-genome sequencing and phenotypic assays were used to characterize genomic diversity, virulence, and fitness-associated traits in C. nebraskensis. We generated 24 long-read genomes, including 20 contemporary Mexican isolates and four historical United States strains collected between 1969 and 1996, and compared them with publicly available genomes from North America and South Africa. Phylogenomic analyses confirmed that all strains cluster within the C. nebraskensis clade, and gene accumulation curves supported a closed pangenome with accessory gene variation linked to geographic origin and isolation period. Functional assays showed strain-level variation in virulence, enzymatic activity, bacteriocin antagonism, polysaccharide production, biofilm formation, and pigmentation. Cellulolytic activity was associated with disease severity, whereas pigment-related traits were linked to thiamine metabolism. Overall, these results indicate that C. nebraskensis populations are ecologically diverse, potentially reflecting the use of alternative strategies for survival and competition. Integrating genome-wide comparisons with functional characterization of fitness-related traits provides a framework for understanding the biological factors underlying Goss's wilt dynamics.},
}

@article {pmid42649226,
year = {2026},
author = {Pike, B and Gonçalves da Silva, A and Terán, W},
title = {Four haplotype-resolved genome assemblies and a reference-free 66-haplotype pangenome graph for Cannabis sativa.},
journal = {Scientific data},
volume = {13},
number = {1},
pages = {},
pmid = {42649226},
issn = {2052-4463},
support = {20969//Vice-Rectorate of Research of the Pontificia Universidad Javeriana/ ; },
mesh = {*Cannabis/genetics ; *Haplotypes ; *Genome, Plant ; Polymorphism, Single Nucleotide ; },
abstract = {We present 4 haplotype-resolved, chromosome scale diploid assemblies of cannabis, assembled from ONT R9.4.1 reads via a novel pipeline based on Hi-C phasing. These assemblies, while low in QV, offer contiguity and genic content comparable to recent HiFi assemblies. Along with a trio-binned assembly previously produced by us and 56 haplotypes selected from the Salk Institute Cannabis Pangenome project, we use these assemblies to create a reference-free pangenome graph. Within a total length of 6.48 Gb, it contains 162.14 M nodes, 228.27 M edges, 14.87 M SNPs, and 6.40 M indels. By optimizing parameters within the Pangenome Graph Builder (PGGB), we avoid many spurious connections among repeat elements, reduce processing time, and arrive at a data structure that visibly recapitulates the linear nature of plant chromosomes. Via k-mer analysis, we corroborate that more genotypes are needed to close the cannabis pangenome, and that, in particular, the region of origin likely remains undersampled.},
}

*Cannabis/genetics
*Haplotypes
*Genome, Plant
Polymorphism, Single Nucleotide

@article {pmid42650066,
year = {2026},
author = {Duan, Y and Zeng, R and Cai, Y and Liu, X and Sun, F},
title = {Pan-Genome Analysis of the Tubulin Gene Family Reveals Candidates for Fiber Strength in Gossypium barbadense.},
journal = {Genes},
volume = {17},
number = {8},
pages = {},
doi = {10.3390/genes17080873},
pmid = {42650066},
issn = {2073-4425},
support = {2023D01B42//Natural Science Foundation of Xinjiang Uygur Autonomous Region/ ; },
mesh = {*Tubulin/genetics/metabolism ; *Gossypium/genetics/metabolism ; Phylogeny ; *Cotton Fiber ; *Genome, Plant ; Multigene Family ; *Plant Proteins/genetics/metabolism ; Gene Expression Regulation, Plant ; },
abstract = {Background/Objectives: Tubulins (Tub) are central components of microtubules, but intraspecific variation and developmental expression of the Tub family in Gossypium barbadense remain poorly characterized. This study aimed to characterize the GbTub family using a pan-genome framework and identify candidates associated with fiber development and strength. Methods: A total of 50 GbTub genes were identified in the G. barbadense 3-79 reference genome, and their orthologous presence-absence patterns were subsequently assessed across 12 additional G. barbadense accessions. Phylogenetic, presence-absence variation (PAV), Ka/Ks, structural variation (SV), RNA-seq, RT-qPCR, co-expression, and GO enrichment analyses were integrated. Results: Among the 50 reference-defined GbTub genes, 43 were classified as core genes, 6 as near-core genes, and 1 as an accessory gene, and the encoded proteins were classified into α-, β-, and γ-tubulin clades. All genes showed Ka/Ks < 1. Twenty-three GbTub genes differed between the fiber-strength-contrasting accessions 5917 and PimaS-7, and representative expression trends were supported by RT-qPCR. Network analysis prioritized 10 GbTub candidates based on degree centrality. GbTub21 was the sole SV-associated GbTub gene displaying significant differential expression between accessions harboring versus lacking the corresponding SV. Non-Tub neighbors of the candidate hub genes were enriched for cytoskeletal, intracellular-transport, and plasma-membrane functions. Conclusions: The pan-genome analysis reveals strong conservation with limited intraspecific variation in the GbTub family. Co-expression profiles nominate candidates associated with fiber secondary-wall development, and their causal contribution to fiber strength awaits functional dissection.},
}

*Tubulin/genetics/metabolism
*Gossypium/genetics/metabolism
Phylogeny
*Cotton Fiber
*Genome, Plant
Multigene Family
*Plant Proteins/genetics/metabolism
Gene Expression Regulation, Plant

@article {pmid42650086,
year = {2026},
author = {Yao, M and Chu, Y and Dai, X},
title = {Pan-Family Analysis of HAK/KUP/KT Potassium Transporters in Brassica napus Prioritizes a Candidate Locus Associated with Salt-Related Variation.},
journal = {Genes},
volume = {17},
number = {8},
pages = {},
doi = {10.3390/genes17080893},
pmid = {42650086},
issn = {2073-4425},
support = {2025-KYYWF-ZR0448//the Fundamental Research Funds for the Provincial Universities in Heilongjiang Province/ ; 2025-KYYWF-ZR0446//the Fundamental Research Funds for the Provincial Universities in Heilongjiang Province/ ; },
mesh = {*Brassica napus/genetics/metabolism ; *Plant Proteins/genetics/metabolism ; Phylogeny ; *Cation Transport Proteins/genetics/metabolism ; Potassium/metabolism ; Gene Expression Regulation, Plant ; Multigene Family ; Arabidopsis/genetics ; *Salt Tolerance/genetics ; },
abstract = {The HAK/KUP/KT family represents a major group of plant potassium transporters involved in K[+] uptake, ion homeostasis and stress responses. However, the accession-level diversity of HAK/KUP/KT genes in Brassica napus remains insufficiently characterized. In this study, we performed a pan-family analysis of HAK/KUP/KT genes across eight B. napus accessions. A total of 269 annotated HAK/KUP/KT family members were identified and classified into core, soft-core, dispensable and private orthogroups based on their representation across the analyzed genome annotations. Phylogenetic analysis grouped these proteins into four major clades together with reference HAK/KUP/KT members from Arabidopsis thaliana and rice. Ka/Ks analysis indicated that HAK/KUP/KT orthogroups were predominantly under purifying selection, while accession-variable orthogroups showed greater variation in sequence conservation. Gene structure, conserved domain, motif and predicted promoter cis-element analyses revealed conserved transporter-related protein features together with orthogroup-level structural and sequence variation. Expression profiling using the ZS11 BnIR dataset further revealed tissue-, hormone- and stress-responsive expression patterns among ZS11 HAK/KUP/KT genes. By integrating expression features, predicted promoter information, evolutionary characteristics, published salt GWAS context and BnVIR haplotype-phenotype information, BnaA08T0085800ZS was prioritized as a candidate locus located near salt-associated variation. This study provides a pan-genome perspective on HAK/KUP/KT family diversity in B. napus and establishes a framework for prioritizing candidate genes for future functional investigation.},
}

*Brassica napus/genetics/metabolism
*Plant Proteins/genetics/metabolism
Phylogeny
*Cation Transport Proteins/genetics/metabolism
Potassium/metabolism
Gene Expression Regulation, Plant
Multigene Family
Arabidopsis/genetics
*Salt Tolerance/genetics

@article {pmid42651850,
year = {2026},
author = {Mussayeva, A and Samarina, L},
title = {Resolving Cattle GWAS Loci: Current Progress, Persistent Challenges and Future Directions.},
journal = {Current issues in molecular biology},
volume = {48},
number = {8},
pages = {},
pmid = {42651850},
issn = {1467-3045},
support = {BR24993004//Ministry of Science and Higher Education of the Republic of Kazakhstan/ ; },
abstract = {Genome-wide association studies (GWASs) have mapped many regions affecting cattle production, health and fertility, yet the lead variant is usually a marker for a linkage-disequilibrium block rather than the molecular lesion. This state-of-the-field review examines how those loci are interpreted at different levels. The literature shows both progress and persistent limits. Colocalization may identify a likely effector transcript without establishing mediation, whereas structural variants missing from SNP-based analyses can account for expression, splicing, or complex-trait signals. Earlier reviews have audited proposed causative variants across cattle and pigs, surveyed causal variants across livestock species, or concentrated on structural variation. Here, these lines of evidence are brought together around a narrower question: Why do cattle complex-trait loci remain resolved at such different biological depths? Coding, regulatory, splicing, and structural examples show where inference is persuasive and where alternatives remain. The evidence is organized as a conceptual landscape, not a validated hierarchy or prescriptive pipeline. The available mechanistic evidence is nevertheless concentrated in commercial taurine, particularly dairy populations, which limits the direct transferability of locus-level conclusions to indicine, African taurine, composite and locally adapted cattle. Priorities include clearer causal terminology, multi-signal and multi-breed analyses, better representation of structural variation, tissue- and cell-state-matched molecular data, native bovine experimental systems and transparent reporting of unresolved explanations.},
}

@article {pmid42654758,
year = {2026},
author = {Kim, D and Ryu, S and Kim, Y and Choi, J and Lee, MJ and Kim, Y and Joo, I and Lee, W},
title = {Insights into the Genetic Diversity of Yersinia enterocolitica Isolated from Poultry and Red Meat in South Korea in 2024.},
journal = {Pathogens (Basel, Switzerland)},
volume = {15},
number = {8},
pages = {},
doi = {10.3390/pathogens15080821},
pmid = {42654758},
issn = {2076-0817},
support = {25191MFDS002//Ministry of Food and Drug Safety/ ; },
mesh = {Animals ; *Yersinia enterocolitica/genetics/isolation & purification/classification ; Republic of Korea ; *Genetic Variation ; Phylogeny ; *Red Meat/microbiology ; *Poultry/microbiology ; Whole Genome Sequencing ; Food Microbiology ; Genome, Bacterial ; Chickens/microbiology ; *Yersinia Infections/microbiology/veterinary ; Virulence Factors/genetics ; Virulence/genetics ; },
abstract = {Yersinia enterocolitica is a psychrotrophic foodborne bacterium that can proliferate at refrigeration temperatures and is frequently associated with animal-source foods, raising concerns about food safety and public health. However, genomic data on Y. enterocolitica isolates from South Korea are limited, despite the increasing use of whole-genome sequencing (WGS) in bacterial surveillance. Herein, 91 Y. enterocolitica isolates recovered from chicken, pork, beef, and duck samples collected nationwide in 2024 were analyzed using WGS to elucidate their genomic diversity and genomic features. Phylogenomic analysis predicted all isolates as biotype 1A (sub-biotype 1Aa) and revealed substantial genetic diversity, comprising 27 sequence types and 43 core-genome types. Pan-genome analysis identified 11,230 gene clusters, revealing an open pan-genome in which accessory and unique gene clusters were assigned to predicted functional categories associated with metabolism, defense mechanisms, and stress responses. Although the canonical virulence plasmid pYV was absent, conserved chromosomal virulence-associated genes involved in adhesion (yapE), invasion (inv), secretion, and enterotoxicity (ystB) were detected. Antimicrobial resistance genes were predominantly intrinsic, particularly blaA and vat(F), whereas acquired resistance genes were identified sporadically. These findings provide a genomic baseline for biotype 1A Y. enterocolitica isolates recovered from animal-source foods in South Korea. The functional and public health significance of the detected virulence-associated loci requires further phenotypic investigation.},
}

Animals
*Yersinia enterocolitica/genetics/isolation & purification/classification
Republic of Korea
*Genetic Variation
Phylogeny
*Red Meat/microbiology
*Poultry/microbiology
Whole Genome Sequencing
Food Microbiology
Genome, Bacterial
Chickens/microbiology
*Yersinia Infections/microbiology/veterinary
Virulence Factors/genetics
Virulence/genetics

@article {pmid42654900,
year = {2026},
author = {Liu, R and Huang, L and Mu, J and Lu, T and Zhang, Y and Deng, K and Xu, D},
title = {Structural Variation and Its Roles in Plant Genomes.},
journal = {Plants (Basel, Switzerland)},
volume = {15},
number = {16},
pages = {},
doi = {10.3390/plants15162498},
pmid = {42654900},
issn = {2223-7747},
support = {32260089//National Natural Science Foundation of China/ ; },
abstract = {Plant genomes exhibit extensive structural diversity generated by large-scale genomic alterations, collectively known as structural variations (SVs). Unlike single nucleotide polymorphisms (SNPs) and small insertions/deletions (indels), SVs can reshape genome architecture through changes in sequence content, gene dosage, regulatory landscapes, and chromosome organization. Recent advances in long-read sequencing (LRS), pan-genome construction, and multi-omics technologies have greatly expanded our ability to identify and interpret SVs across plant species. In this review, we summarize recent progress in understanding the formation mechanisms, classification, and functional consequences of plant SVs. We discuss major sources of SV generation, including transposable element activity, non-allelic homologous recombination (NAHR), horizontal gene transfer (HGT), and genome restructuring following polyploidization. We further highlight how LRS and graph-based pan-genomes overcome limitations of traditional linear reference genomes and enable more comprehensive characterization of genetic diversity. Beyond variant discovery, we emphasize the importance of integrating genomic, transcriptomic, epigenomic, proteomic, metabolomic, and spatial omics datasets to decipher how SVs influence gene regulation and complex agronomic traits. We also discuss current challenges, including repetitive genomes, polyploidy, computational complexity, and translation of SV knowledge into practical breeding applications. Together, these advances establish SV-centered genomics as a critical framework for understanding plant genome evolution and accelerating precision crop improvement.},
}

@article {pmid42654999,
year = {2026},
author = {Akinyemi, MO and Coulibaly, WH and Sakia Mian, TM and Popescu, PA and Ebenso, B and Razafindralambo, H},
title = {Genome Sequences of Three Enterococcus faecalis Strains (LAB1, LAB10, and LAB11) with Probiotic, Plant Growth-Promoting, and Nitrifying Properties.},
journal = {Microorganisms},
volume = {14},
number = {8},
pages = {},
doi = {10.3390/microorganisms14081653},
pmid = {42654999},
issn = {2076-2607},
support = {BOU/PaD/CC/PVB/sd-eab/LD 2024-2025/WBI.IN//Wallonie-Bruxelles International/ ; },
abstract = {Here we report the draft genome sequences of three Enterococcus faecalis strains, LAB1, LAB10, and LAB11, isolated from the pond water of a tilapia (Oreochromis niloticus) aquaculture farm at the University Nangui Abrogoua, Abidjan, Ivory Coast. These strains were previously characterised for their probiotic, plant growth-promoting (PGP), and nitrifying properties. All three strains were assigned to sequence type ST19 by multilocus sequence typing (MLST). The draft genomes of LAB1, LAB10, and LAB11 consist of 34, 35, and 34 contigs, totalling 2.94 Mb each (GC content 37.40%). Prokka annotation predicted 2872, 2873, and 2875 protein-coding sequences (CDS) for LAB1, LAB10, and LAB11, respectively. Genomic screening revealed no vancomycin resistance genes; however, tet(M) and lsa(A) resistance determinants were identified in all three strains, located on a repUS43-type plasmid replicon. Fourteen virulence factor homologs conserved in the E. faecalis reference strain V583 were detected, including Ebp pili, gelatinase (gelE), Fsr quorum-sensing system, and capsule biosynthesis genes, but no cytolysin operon was identified. Genes associated with stress tolerance (katA, sodA), bile salt hydrolysis (cbh), siderophore transport (fepC, fhuD), and ethanolamine nitrogen metabolism (eutB/eutC) were identified in all three genomes. Pan-genome analysis with the E. faecalis reference strain revealed 551 core gene clusters and 279 gene clusters exclusive to the three aquaculture isolates. Despite their high genomic similarity, we report the three genomes as distinct isolates due to observed differences in their expressed phenotypic properties. These sequences provide a genomic resource supporting the development of multifunctional probiotic consortia for integrated aquaponic systems.},
}

@article {pmid42655014,
year = {2026},
author = {Ge, X and Gong, R and Ma, J and Fu, Y and Chen, J and Li, M and Guo, Q and Liu, X and Li, W},
title = {Isolation, Identification, and Biological Characterization of Proteus mirabilis Isolated from Beef Cattle in China.},
journal = {Microorganisms},
volume = {14},
number = {8},
pages = {},
doi = {10.3390/microorganisms14081668},
pmid = {42655014},
issn = {2076-2607},
abstract = {Proteus mirabilis, a member of the family Enterobacteriaceae, is widely distributed in the environment and commonly colonizes the gastrointestinal tract of animals. Although traditionally regarded as an opportunistic zoonotic pathogen, increasing evidence suggests that it may also contribute to bovine diseases. However, information regarding the antimicrobial resistance, virulence determinants, and genomic characteristics of bovine-associated P. mirabilis in China remains limited. In this study, a P. mirabilis strain, designated A3, was isolated from one of 19 diarrheic adult beef cattle sampled in Anhui Province, China, and comprehensively characterized through phenotypic, genomic, and pathogenicity analyses. Strain A3 exhibited typical swarming motility and a multidrug-resistant phenotype. PCR screening identified the resistance genes aac(6')-Ib and qnrA, together with seven virulence genes (pmfA, atfA, ureC, mrpA, ucaA, zapA, and atfC) involved in adhesion and colonization. Whole-genome sequencing generated a 3,965,086 bp draft genome with a GC content of 38.37% and identified 85 resistance-associated genes and 147 virulence-associated genes, including multidrug efflux pumps and virulence factors related to adhesion, motility, iron acquisition, secretion systems, and host interaction. Comparative genomic analysis demonstrated high genomic similarity to other bovine-derived P. mirabilis isolates, with average nucleotide identity (ANI) values ranging from 99.06% to 99.32%, while pangenome analysis identified 5680 orthologous gene clusters, including 2959 core genes, indicating an open pangenome structure. Multiple insertion sequences, prophages, and genomic islands were identified, highlighting substantial genomic plasticity and adaptive potential. In a mouse infection model, strain A3 exhibited clear dose-dependent pathogenicity. All eight mice challenged with 2.22 × 10[9] CFU/mL died within 12 h post-infection and developed severe pathological lesions in multiple organs, whereas only one of eight mice in the low-dose group died during the same period. Collectively, these findings indicate that bovine-derived P. mirabilis A3 combines multidrug resistance, genomic plasticity, and opportunistic pathogenic potential. This study expands current knowledge of bovine-associated P. mirabilis and provides a genomic and experimental basis for surveillance, risk assessment, and prevention strategies in cattle production systems.},
}

@article {pmid42655020,
year = {2026},
author = {Wang, Z and Wang, ZX and Lu, GJ and Xia, LL and Lu, GH and Guo, XJ and Hao, WC and Zhang, YJ and Jiang, RH and Xu, SJ and Li, YF and Shi, ZT and Xu, ZZ and Qi, JF and Shao, ZY and Li, J and Zhu, LW and Zheng, L},
title = {Distinct Host and Bacterial Profiles in Murine Single Versus Co-Infection with Foal-Isolated Streptococcus equi and Streptococcus dysgalactiae.},
journal = {Microorganisms},
volume = {14},
number = {8},
pages = {},
doi = {10.3390/microorganisms14081674},
pmid = {42655020},
issn = {2076-2607},
support = {262102321126//Henan Science and Technology Department/ ; 262102310423//Henan Science and Technology Department/ ; XKPY-2025013//Huanghuai University/ ; 2025-NK-112//Science and Technology Department of Qinghai Province/ ; },
abstract = {This study investigated the interactive pathogenic characteristics of co-infection with Streptococcus equi (S. equi) and Streptococcus dysgalactiae (S. dysgalactiae) isolated from diseased foals. Integrating genomic analysis, in vitro phenotypic assays, and a murine intranasal infection model, we comparatively analyzed the biological traits and pathogenic differences between single and dual infections. Comparative genomic analysis revealed divergent virulence profiles between the two isolates, and both species harbored open pan-genomes. In vitro, the biofilm biomass of strain F1 was higher than that of all other groups. No synergistic hemolytic activity was observed in co-cultures of the two isolates. In vivo infection results indicated that streptococcal infection significantly altered the structure and abundance of pulmonary microbiota in mice. Furthermore, single and dual infections displayed strain-specific and time-dependent microbial disparities at early and late infection stages, which were associated with differential enrichment of multiple immune- and metabolism-related Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways, including the Tumor Necrosis Factor (TNF) and Mitogen-Activated Protein Kinase (MAPK) signaling pathways. Notably, co-infection triggered the most severe pulmonary microbiota dysbiosis and aberrant functional pathway regulation. This study preliminarily characterized the distinct phenotypic and pathological alterations induced by dual streptococcal infection, providing experimental evidence and novel insights for further exploring the interactive features of equine streptococcal mixed infections.},
}

@article {pmid42637401,
year = {2026},
author = {Tenzin, K and Balyatanda, SB and Prakash, SD and Siliveru, K and Platt, TG},
title = {Lineage-aware comparative genomics shows no consistent reservoir-specific plasmidome in low-moisture food associated Salmonella Enteritidis.},
journal = {Food research international (Ottawa, Ont.)},
volume = {242},
number = {Pt 4},
pages = {120003},
doi = {10.1016/j.foodres.2026.120003},
pmid = {42637401},
issn = {1873-7145},
mesh = {*Salmonella enteritidis/genetics/isolation & purification ; *Plasmids/genetics ; *Food Microbiology ; *Genomics/methods ; Animals ; Polymorphism, Single Nucleotide ; *Genome, Bacterial ; Poultry/microbiology ; },
abstract = {Foodborne outbreaks of Salmonella Enteritidis have been historically linked to poultry, but outbreaks associated with low-moisture foods (LMFs) are increasingly reported. Since plasmids encode stress-response and tolerance traits that support persistence in dry environments, this study evaluated whether LMF-associated (nuts, spices, grains, etc.) S. enteritidis isolates carry lineage-specific plasmidomes distinct from non-LMF (poultry/egg-associated and production-environment). A total of 2824 non-clinical records were curated from the NCBI Pathogen Detection database and organized into 51 SNP clusters (30 non-LMF, 11 LMF, 10 mixed). Reservoir comparisons were restricted to mixed clusters (319 non-LMF, 24 LMF at the metadata level) using 64 assemblies (24 LMF, 40 non-LMF). PlasmidFinder identified that most genomes contained IncF plasmid (IncFIB(S) 90.6%, IncFII(S) 89.1%), though global Fisher's exact tests and lineage-stratified CMH tests (FDR-adjusted) identified no replicon family enriched in LMF. MOB-suite reconstructed 88 plasmids from 63/64 genomes and assigned 11 backbone clusters dominated by AB461 (58/64 genomes). Plasmid counts, mobility profiles, and functional annotations were similar across reservoirs, with variations attributable to SNP clusters rather than isolation source. In the largest mixed lineage (PDS000218745.3; 9 LMF, 15 controls), no LMF-enriched plasmid gene products were detected. Shared accessory plasmids occurred in both reservoirs, including AB233 carrying mer operon genes and emrE, while rare LMF-only backbones (AB947; AA149; AA372 encoding TEM β-lactamase, toxN, mbeA, proQ) were isolate-specific. Pangenome analysis of 4899 gene clusters likewise found no accessory genes significantly enriched in LMF after lineage-stratified testing. Plasmid architecture was largely lineage-structured with limited evidence for association with LMF environments.},
}

*Salmonella enteritidis/genetics/isolation & purification
*Plasmids/genetics
*Food Microbiology
*Genomics/methods
Animals
Polymorphism, Single Nucleotide
*Genome, Bacterial
Poultry/microbiology

@article {pmid42638878,
year = {2026},
author = {Liu, R and Wang, L and Wang, S and Wang, Y and Liu, L},
title = {Nitrogen use efficiency in crops under salt stress: from molecular networks to intelligent breeding.},
journal = {Frontiers in plant science},
volume = {17},
number = {},
pages = {1922452},
pmid = {42638878},
issn = {1664-462X},
abstract = {Soil salinization threatens global arable land and agricultural sustainability, severely reducing crop nitrogen use efficiency (NUE) by disrupting root ammonium and nitrate fluxes, impairing nitrogen-assimilation enzymes, and disrupting carbon-nitrogen (C-N) balance. This review synthesizes recent advances in the coordination of salt-stress signaling and nitrogen homeostasis in plants. Two mechanistically distinct regulatory axes have recently been proposed. In one, a nitrate transporter acts as a dual sensor for nitrate and abscisic acid (ABA); in the other, SOS kinase-mediated phosphorylation of an ammonium transporter maintains ammonium uptake under Na[+] stress. In addition, rapid post-translational regulatory mechanisms, including reversible protein phosphorylation and S-nitrosylation of nitrate reductase, can fine-tune nitrogen fluxes shortly after salt exposure. These findings inform a four-tier closed-loop conceptual framework comprising signal perception, transport reprogramming, metabolic redistribution, and genetic redesign. The framework yields three testable predictions: the sequential activation of regulatory tiers; a quantitative relationship between Ca[2+] signal amplitude and the extent of C-N metabolic redistribution; and salt-concentration thresholds that distinguish basal homeostatic buffering from full adaptive reprogramming. Translation of this framework to field crops requires an integrated breeding pipeline that combines multi-environment quantitative trait locus (QTL) mapping, pan-genome-enabled genome-wide association studies, genomic selection for minor-effect alleles, and multiplex CRISPR editing coupled with stress-inducible synthetic promoters to pyramid favorable traits while minimizing yield penalties. A major unresolved challenge is to resolve the dynamic protein-metabolite networks that govern growth-defense trade-offs under combined salinity and nitrogen limitation. The integration of single-cell transcriptomics, isotope-based metabolic flux analysis, and machine-learning-assisted phenomics may help link genotypic variation to agronomic performance in salinized agroecosystems.},
}

@article {pmid42638926,
year = {2026},
author = {Zeng, J and Wu, Y and Li, Y and Lv, W and Lin, J and Nie, Q and Lin, Q and Wen, X and Lin, K and Zhang, L and Wu, S and Su, R},
title = {Global distribution and genomic characteristics of linezolid resistance gene-positive Enterococcus faecium among humans, animals, and the environment.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1916332},
pmid = {42638926},
issn = {1664-302X},
abstract = {BACKGROUND: Over the past decade, considerable attention has been directed toward the plasmid-mediated dissemination of linezolid resistance determinants among Enterococcus faecium (E. faecium). Despite extensive epidemiological research, a systematic global genomic analysis of linezolid resistance gene-positive E. faecium (LRGPEfm) is lacking.

METHODS: This study conducted a comprehensive genomic analysis of 832 LRGPEfm genomes, with the aim of investigating their antibiotic resistance genes (ARGs), virulence factor genes (VFGs), population structure, and transmission pathways.

RESULTS: The greatest proportion of LRGPEfm originated from China (32.57%), with Germany following at 11.54%. In relation to host origin, humans represented the dominant category (48.08%), followed by pigs (10.58%). LRGPEfm additionally functions as a repository for ARGs, with a total of 47 ARGs identified. Isolates from China and pigs harbored the highest ARG numbers. Furthermore, 35 VFGs were identified, with isolates from hospital environments and Germany harboring the highest VFG numbers. A total of 211 sequence types were delineated through multilocus sequence typing (MLST) analysis, with ST80 being the most common. Minimal SNP differences detected in LRGPEfm originating from various countries and host sources suggest cross-border and cross-species clonal dissemination. Pan-genome-wide association studies (pan-GWAS) demonstrated that the accessory genome of LRGPEfm varies significantly by geography and host, showing a marked enrichment of genes associated with metabolic enzymes, mobile genetic elements (MGEs), and ARGs. Among the genetic contexts of linezolid resistance genes, IS1216E was the predominant carrier.

CONCLUSION: LRGPEfm poses a substantial public health threat, and sustained, comprehensive surveillance is essential.},
}

@article {pmid42635661,
year = {2026},
author = {Ha, PTH and Do-Hyung, K and Luan, NT},
title = {Cooperative Chemical Biosynthesis of Tetrodotoxin: Evidence from Marine Microbial Contributors.},
journal = {Marine biotechnology (New York, N.Y.)},
volume = {28},
number = {5},
pages = {},
pmid = {42635661},
issn = {1436-2236},
mesh = {*Tetrodotoxin/biosynthesis/genetics ; *Genome, Bacterial ; Multigene Family ; Phylogeny ; Animals ; Vibrio/genetics/metabolism ; Pseudoalteromonas/genetics/metabolism ; Aquatic Organisms ; *Bacteria/genetics/metabolism ; },
abstract = {Tetrodotoxin (TTX) is a potent neurotoxin widely distributed in pufferfish and other marine organisms, yet its microbial biosynthetic basis remains unresolved because no definitive bacterial TTX gene cluster has been identified. This study develops a hypothesis-generating comparative-genomic framework to prioritize bacterial genomes for experimental investigation of TTX-related metabolism; it does not demonstrate bacterial TTX biosynthesis. Thirteen genomes representing Pseudoalteromonas, Cytobacillus, Shewanella, and Vibrio were analyzed using whole-genome comparison, average amino acid identity (AAI), and a weighted functional-prioritization score. Candidate homologous gene families were assigned to four mechanistic groups: scaffold formation and nitrogen incorporation (Group A), redox tailoring and polyoxygenation (Group B), structural tailoring and rearrangement (Group C), and transport, regulation, and ecological support (Group D). The AAI structure revealed both closely related Vibrio lineages and deeply divergent genera, enabling interpretation of functional enrichment against contrasting genomic backgrounds. Cytobacillus gottheilii 1839 and Pseudoalteromonas tetraodonis DSM 16,099 had the highest cumulative scores, whereas Vibrio representatives showed moderate or partial enrichment profiles. These rankings reflect the distribution of hypothesized functional markers, rather than validated TTX-production capacity. Groups A and B were more discriminating than the broadly distributed Groups C and D. Accordingly, C. gottheilii 1839 and P. tetraodonis DSM 16,099 are proposed as high-priority targets for integrated metabolomics, transcriptomics, targeted gene disruption, and pathway-mining studies. The results support a dispersed, multi-module working hypothesis for microbial contribution to TTX-associated ecology, while emphasizing that the pathway, its products, and the causal role of individual strains remain to be experimentally resolved.},
}

*Tetrodotoxin/biosynthesis/genetics
*Genome, Bacterial
Multigene Family
Phylogeny
Animals
Vibrio/genetics/metabolism
Pseudoalteromonas/genetics/metabolism
Aquatic Organisms
*Bacteria/genetics/metabolism

@article {pmid42635836,
year = {2026},
author = {Tatta, ER and Kumavath, R},
title = {Pan-genome analysis reveals the triangle mechanisms of antibiotic resistance, pathogenicity, and biofilm formation in Enterococcus faecalis.},
journal = {Molecular genetics and genomics : MGG},
volume = {301},
number = {1},
pages = {},
pmid = {42635836},
issn = {1617-4623},
support = {SERB-EMEQ/051/2014//Science and Engineering Research Board/ ; },
mesh = {*Enterococcus faecalis/genetics/pathogenicity/drug effects ; *Biofilms/growth & development/drug effects ; *Genome, Bacterial/genetics ; Humans ; Anti-Bacterial Agents/pharmacology ; Quorum Sensing/genetics ; *Drug Resistance, Multiple, Bacterial/genetics ; Animals ; Bacterial Proteins/genetics ; Virulence/genetics ; *Drug Resistance, Bacterial/genetics ; },
abstract = {The bacterial genus Enterococcus is typically nonpathogenic and a commensal that lives symbiotically with humans. However, the transition from commensal to opportunistic pathogenic is a complex, multi-step process driven by environmental adaptation. The study focused on 214 Enterococcus faecalis genome sequences, selected from various environments and organisms, including humans and animals, and targeted genes associated with biofilm formation, antibiotic resistance, and quorum sensing. KEGG pathway analysis identified 36 potential drug targets, comprising n = 15 non-enzymatic and n = 21 enzymatic targets, primarily located in the cytoplasm, including four surface proteins and seven pharmacological targets. The study also revealed resistance-conferring genes, including ABC transporters, major facilitator superfamily (MFS) proteins, and antibiotic efflux pumps, which mediate resistance to glycopeptides, quinolones, aminoglycosides, and tetracyclines. In this pangenome study, critical insights into the development of multidrug resistance in nosocomial pathogens are provided. Insights into the outcomes could enlighten novel drug designs and strategies to combat infections in both clinical and environmental settings.},
}

*Enterococcus faecalis/genetics/pathogenicity/drug effects
*Biofilms/growth & development/drug effects
*Genome, Bacterial/genetics
Humans
Anti-Bacterial Agents/pharmacology
Quorum Sensing/genetics
*Drug Resistance, Multiple, Bacterial/genetics
Animals
Bacterial Proteins/genetics
Virulence/genetics
*Drug Resistance, Bacterial/genetics

@article {pmid42632028,
year = {2026},
author = {Bingöl, Z and Şahin, B and Zambaku, K and Roman-Brenes, R and Koliogeorgi, K and Firtina, C and Mutlu, O and Alkan, C},
title = {De Bruijn graphs for pangenomics: in-depth performance benchmarking of de Bruijn graph-based tools for read mapping.},
journal = {Briefings in bioinformatics},
volume = {27},
number = {4},
pages = {},
pmid = {42632028},
issn = {1477-4054},
support = {101047160//European Union's Horizon Programme for Research and Innovation/ ; },
mesh = {*Genomics/methods ; *Software ; Benchmarking ; Algorithms ; Computational Biology/methods ; Humans ; },
abstract = {De Bruijn graphs are widely used in pangenome representation due to their numerous advantages and extensions, such as colored and compacted variants that enhance the representation of genetic variation. Although de Bruijn graphs are becoming increasingly adopted, their performance and energy impact have not been clearly studied. Such an overlooked understanding can lead to suboptimal designs for de Bruijn graph-based tools in addressing the computational challenges posed by pangenome data. To identify workflow bottlenecks and assess the efficiency of hardware utilization, we present an in-depth performance analysis of state-of-the-art de Bruijn graph-based read mapping tools on pangenomic datasets, focusing on scalability of execution time, hardware resource utilization, and energy consumption. We observe that the tools primarily prioritize data parallelism for processing read datasets, disregarding the increasing complexity of the pangenome graph, which hinders scalability. As the pangenome graph grows in size and complexity, cache miss rates also increase, leading to poor overall performance. By extensively analyzing sources of suboptimal performance, we pave the way for optimizing the existing and future tools to fully realize their potential in advancing pangenome research.},
}

*Genomics/methods
*Software
Benchmarking
Algorithms
Computational Biology/methods
Humans

@article {pmid42633411,
year = {2026},
author = {Duan, Y and Du, B and Song, Z and Yuan, M and Qiu, X and Xu, S and Li, Z},
title = {Phylogenetic and Genomic Feature Analysis of Cutaneous Nocardia Isolates.},
journal = {Infection and drug resistance},
volume = {19},
number = {},
pages = {619525},
pmid = {42633411},
issn = {1178-6973},
abstract = {BACKGROUND: Cutaneous nocardiosis differs from pulmonary and disseminated nocardiosis in that it can occur in immunocompetent individuals and is usually localized with a favorable prognosis. However, the phylogenetic relationships, genomic characteristics, and virulence and antimicrobial resistance profiles of human cutaneous Nocardia isolates remain poorly understood.

PURPOSE: This study aimed to characterize the phylogenetic relationships and genomic features of human cutaneous Nocardia isolates and to investigate their virulence-associated and antimicrobial resistance determinants, as well as their phenotypic antimicrobial susceptibility profiles.

MATERIALS AND METHODS: A total of 31 human cutaneous Nocardia genomes were included for comparative genomic analysis, comprising nine clinical isolates sequenced in this study and 22 publicly available genomes retrieved from the NCBI database. Phylogenetic reconstruction, average nucleotide identity (ANI) analysis, and pan-genome analysis were performed to investigate the genomic relationships and diversity of the isolates. Putative virulence-associated and antimicrobial resistance genes were identified through genome-based annotation. In vitro antimicrobial susceptibility testing was performed for 13 isolates against 15 antimicrobial agents.

RESULTS: Phylogenetic analysis demonstrated clear species-level clustering and identified a potentially novel cutaneous pathogen, Nocardia sp. NK_136. Pan-genome analysis revealed an open pan-genome with substantial genomic plasticity. Virulence profiling identified a broadly conserved core framework mainly associated with stress response, immune evasion, iron acquisition, secretion systems, and host interaction, together with variable virulence-associated modules distributed in a species- or strain-specific manner. A total of 40 antimicrobial resistance genes were identified, showing marked species-dependent distribution. Phenotypic antimicrobial susceptibility testing demonstrated that all tested isolates were susceptible to trimethoprim-sulfamethoxazole (TMP-SMX) and linezolid, whereas variable resistance was observed to cefepime, cefoxitin, ciprofloxacin, tobramycin, and clarithromycin.

CONCLUSION: Human cutaneous Nocardia isolates possess a conserved core virulence-associated genomic framework accompanied by variable virulence modules, while their antimicrobial resistance determinants and phenotypic resistance profiles show substantial species-dependent variation. These findings provide genomic insights into the diversity, potential pathogenicity, and antimicrobial resistance of cutaneous Nocardia isolates and provide a basis for further investigation of the pathogenesis and clinical management of cutaneous nocardiosis.},
}

@article {pmid42633847,
year = {2026},
author = {Liu, P and Hu, K and Mughini-Gras, L and Zomer, AL and Brouwer, MSM and Dallman, TJ and Paganini, JA},
title = {Exploring differences across pangenome-graph representations using Escherichia coli O157:H7 as a model.},
journal = {Genomics},
volume = {},
number = {},
pages = {111309},
doi = {10.1016/j.ygeno.2026.111309},
pmid = {42633847},
issn = {1089-8646},
abstract = {Pangenome graphs are increasingly used to represent population-scale bacterial diversity, yet construction methods span fundamentally different representation paradigms whose outputs and sensitivities to assembly quality remain poorly quantified. We systematically reviewed microbial pangenome graph tools and benchmarked seven representative methods spanning gene-cluster, compacted coloured de Bruijn graph, one hybrid approach and one multiple sequence alignment method. Using a repeat-rich Escherichia coli O157:H7 dataset with complete genomes and matched short-read data, we constructed graphs from identical inputs and observed orders-of-magnitude differences in graph size and fragmentation, indicating that global topology is driven by representation strategy. Varying completeness composition revealed that assembly fragmentation is a first-order determinant of graph structure: gene-cluster graphs contracted as draft assemblies replaced complete genomes, whereas compacted coloured de Bruijn graphs expanded, with distinct degree-prevalence fingerprints across tools. In contrast, the multiple sequence alignment method could not be evaluated across fragmented inputs because it did not run reliably on draft-assembly datasets. Computational cost mirrored these shifts and depended strongly on completeness composition, including a pronounced runtime penalty for one compacted coloured de Bruijn graph implementation on all-draft inputs. Finally, analysis of Shiga toxin loci showed that pangenome-level reconciliation by gene-cluster-based tools does not reliably correct assembly artefacts at challenging multi-copy genes and that performance varies by locus. Together, these findings show that pangenome graphs are representation-dependent models of bacterial diversity, and that, in this repeat-rich O157:H7 benchmark dataset, assembly completeness is a primary determinant of their topology, scalability, and locus-level accuracy.},
}

@article {pmid42629026,
year = {2026},
author = {In Ko, H and Kim, SR and Lee, M and Jeong, CR and Na, N and Eun, JB and Kim, TW},
title = {Transcriptomic and proteomic analyses of Weissella koreensis isolated from kimchi with different growth-limiting temperatures.},
journal = {Food research international (Ottawa, Ont.)},
volume = {242},
number = {Pt 1},
pages = {119781},
doi = {10.1016/j.foodres.2026.119781},
pmid = {42629026},
issn = {1873-7145},
mesh = {*Weissella/genetics/growth & development/isolation & purification/metabolism ; *Proteomics ; *Temperature ; *Transcriptome ; Gene Expression Profiling ; *Fermented Foods/microbiology ; *Food Microbiology ; *Proteome ; Phylogeny ; Genome, Bacterial ; },
abstract = {Weissella koreensis, a dominant species in kimchi, is typically isolated and cultured at 30 °C. However, some strains do not grow well at this temperature. This study aimed to investigate the molecular basis underlying differences in growth-limiting temperatures between two psychrotrophic and one mesophilic W. koreensis strains isolated from kimchi using pan-genome, transcriptome, and proteome analyses. The three W. koreensis genomes showed slight differences in genome size, GC content, and gene number. Pan-genome analysis of the six W. koreensis strains identified 1224 core pan-genome orthologous groups (POGs), 201 accessory POGs, and 213 unique POGs. A phylogenetic analysis revealed low genetic distances among the strains, with no significant differences between the psychrotrophic and mesophilic strains. Using the criteria of |FC| ≥ 2 and raw p-value <0.05, transcriptomic analysis identified 138-335 up-regulated genes and 157-337 down-regulated genes across all tested temperature conditions compared with 20 °C. A transcriptomic analysis under various growth-limiting temperatures and functional annotation using Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed distinct gene expression patterns and functional profiles between mesophilic and psychrotrophic strains of W. koreensis depending on the temperature conditions. At the growth-limiting temperature, various genes showing consistent trends in the transcriptome and proteome datasets differed between psychrotrophic and mesophilic strains; these genes may be involved in the ability of W. koreensis to grow at its thermal limit. In particular, arcC, rnj, glmM, xseB, nadE, and araA were upregulated at the growth-limiting temperature in the mesophilic strain W. koreensis KCKM 0130 and may contribute to growth at moderate temperatures. These findings provide exploratory insights into the strain-specific and temperature-dependent molecular responses of W. koreensis. Furthermore, the results provide foundational data for the development of starter cultures suitable for fermentation processes conducted at varying temperatures.},
}

*Weissella/genetics/growth & development/isolation & purification/metabolism
*Proteomics
*Temperature
*Transcriptome
Gene Expression Profiling
*Fermented Foods/microbiology
*Food Microbiology
*Proteome
Phylogeny
Genome, Bacterial

@article {pmid42630188,
year = {2026},
author = {Hou, T and Gao, QH and Zhang, QL and Zhou, SJ and Zhang, L and He, QL and Cheng, LP and Zhang, N and Guan, T and Yang, YY and Li, XR and He, J},
title = {Whole-genome and pan-genome analyses reveal genomic differences among nontypeable Haemophilus influenzae isolates from bronchiectasis, community-acquired pneumonia, and chronic obstructive pulmonary disease.},
journal = {Frontiers in cellular and infection microbiology},
volume = {16},
number = {},
pages = {1827485},
pmid = {42630188},
issn = {2235-2988},
mesh = {*Haemophilus influenzae/genetics/isolation & purification/classification ; Humans ; *Bronchiectasis/microbiology ; *Genome, Bacterial ; Phylogeny ; *Pulmonary Disease, Chronic Obstructive/microbiology ; Multilocus Sequence Typing ; Community-Acquired Pneumonia/microbiology ; Whole Genome Sequencing ; Genetic Variation ; *Haemophilus Infections/microbiology ; Genome-Wide Association Study ; Genomics ; },
abstract = {BACKGROUND: Nontypeable Haemophilus influenzae (NTHi) is a major bacterial pathogen in both acute and chronic respiratory diseases, yet the genomic basis underlying its association with different clinical phenotypes remains incompletely understood.

METHODS: We performed whole-genome sequencing and comparative genomic analysis of 27 NTHi isolates, including strains derived from patients with bronchiectasis (n = 10), community-acquired pneumonia (CAP; n = 6), and chronic obstructive pulmonary disease (COPD; n = 11). Among these, three isolates (one from each disease group) were newly sequenced using a hybrid Oxford Nanopore-Illumina approach, while the remaining 24 genomes were retrieved from public databases. Pan-genome analysis, multilocus sequence typing (MLST), core genome phylogenetic analysis, accessory genome based discriminant analysis, and pan-genome-wide association analysis (pan-GWAS) were performed to characterize genomic diversity and variation in gene content across isolates.

RESULTS: MLST and core genome phylogenetic analyses revealed substantial genetic diversity, with isolates from bronchiectasis, CAP, and COPD distributed across multiple lineages without clear disease-specific clustering. Accessory genome-based analyses indicated heterogeneous differences in gene content among isolates from different clinical backgrounds, although overlap between groups remained evident. Pan-genome-wide association analysis did not identify any accessory genes that remained statistically significant after Benjamini-Hochberg false discovery rate (FDR) correction. Under a relaxed exploratory threshold (empirical P-value < 0.35 and odds ratio > 1), a subset of accessory genes showing differential distribution patterns among disease groups was identified and reported as exploratory candidates. Comparatively greater accessory genome divergence was observed between bronchiectasis and COPD isolates. Functional annotation indicated that these candidate genes spanned multiple categories, including recombination, membrane-associated processes, transport, and nutrient utilization.

CONCLUSIONS: Clinical heterogeneity among NTHi isolates was not reflected in core genome phylogeny. Differences in accessory gene content were observed across isolates from different clinical sources; however, these patterns were not supported by statistically robust associations after multiple testing correction. The identified candidate genes should therefore be regarded as exploratory, and the findings interpreted as descriptive of genomic diversity rather than evidence of disease-associated functional differentiation.},
}

*Haemophilus influenzae/genetics/isolation & purification/classification
Humans
*Bronchiectasis/microbiology
*Genome, Bacterial
Phylogeny
*Pulmonary Disease, Chronic Obstructive/microbiology
Multilocus Sequence Typing
Community-Acquired Pneumonia/microbiology
Whole Genome Sequencing
Genetic Variation
*Haemophilus Infections/microbiology
Genome-Wide Association Study
Genomics

@article {pmid42627592,
year = {2026},
author = {Chen, Y and Rizwan, M and Nawaz, A and Waheed, MI and Waqas, M and Ullah, M},
title = {Lactiplantibacillus plantarum: Systems Biology of a Versatile Microbe.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {42627592},
issn = {1867-1314},
support = {202409FE01//Open Project Funding of the Key Laboratory of Fermentation Engineering Ministry of Education/ ; 5501330015//High-level Talent Fund of Jiangsu University/ ; },
abstract = {Lactiplantibacillus plantarum is a metabolically versatile lactic acid bacterium found in fermented foods and the human gastrointestinal tract. Its relatively large genome (3.0-3.6 Mb) features an open pan-genome with 1,436-2,100 core genes and over 13,000 cloud genes, enabling remarkable adaptation to diverse environments. This species encodes a diverse repertoire of CAZymes that degrade plant polysaccharides and host glycans, yielding short-chain fatty acids that modulate epithelial barrier integrity, host metabolism, and immune signaling. Pattern-recognition receptors (PRRs, including TLR2, TLR9, and NOD2) detect L. plantarum at the host interface, primarily through cell-surface molecules such as lipoteichoic acids, peptidoglycan, and exopolysaccharides. These interactions can influence NF-κB signaling, leading to either inflammatory or regulatory responses, depending on the specific strain. Certain strains also possess the glutamate decarboxylase system (GadB/GadC), which transforms dietary glutamate into gamma-aminobutyric acid (GABA), linking L. plantarum to the biology of the gut-brain axis. Despite substantial mechanistic evidence, clinical outcomes are inconsistent due to the significant variability among strains, marked differences in host microbiomes, and the absence of predictive multiomic markers for colonization and efficacy. This review consolidates current insights on genome organization, metabolic characteristics, and mechanisms of host interaction, with a specific focus on the challenges that continue to hinder the advancement of L. plantarum as a precision biotherapeutic.},
}

@article {pmid42627916,
year = {2026},
author = {Ruggieri, AA and Cicconardi, F and Bellin, N and Montgomery, SH and Mallet, J and Van Belleghem, SM and McMillan, OW and Counterman, BA and Papa, R},
title = {Multilocus basis of incipient reproductive isolation in hybridizing populations is revealed by pangenomic and epigenetic divergence.},
journal = {Science advances},
volume = {12},
number = {34},
pages = {eadz6665},
pmid = {42627916},
issn = {2375-2548},
mesh = {*Reproductive Isolation ; Gene Flow ; *Epigenesis, Genetic ; Genetic Variation ; *Genomics/methods ; *Hybridization, Genetic ; Genetics, Population ; Mutation ; Selection, Genetic ; Animals ; },
abstract = {Incipient reproductive isolation in the presence of gene flow has traditionally been attributed to a small number of major-effect loci under strong selection. Here, using the Heliconius erato adaptive radiation, we apply a pangenome framework to examine how mutational divergence, regulatory variation, and structural variants contribute to genome-wide divergence. In contrast to earlier studies, our high-resolution analyses reveal widespread divergence across the genome, consistent with a multilocus barrier to gene flow. Our findings support a model in which selection acts on regulatory phenotypes under migration-selection balance, with genetic differentiation becoming more pronounced as gene flow declines. By integrating population-level sampling, we show that apparent population-specific structural and regulatory variation inferred from single-reference genomes is overestimated, reflecting pervasive reference bias. While structural variants contribute to genomic variation, in our system, most are shared or polymorphic rather than fixed differences between populations. Together, our results show that the genomic landscape of H. erato divergence reflects the combined contributions of regulatory variation and mutational change, while highlighting the importance of accounting for reference bias when interpreting structural and regulatory divergence. This multilocus framework provides a more accurate view of how reproductive barriers emerge and strengthen under ongoing gene flow.},
}

*Reproductive Isolation
Gene Flow
*Epigenesis, Genetic
Genetic Variation
*Genomics/methods
*Hybridization, Genetic
Genetics, Population
Mutation
Selection, Genetic
Animals

@article {pmid42620293,
year = {2026},
author = {Matrishin, CB and Haase, EM and Miles, AK and Steimer, S and Soh, D and Smardz, M and Diaz, PI and Kauffman, KM},
title = {Pervasive integrative and conjugative elements shape Porphyromonas gingivalis gene repertoires.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.08.04.741601},
pmid = {42620293},
issn = {2692-8205},
abstract = {BACKGROUND: Porphyromonas gingivalis (Pg) is an oral pathobiont that contributes to periodontal disease and has been associated with systemic health conditions. Although Pg is recognized as exhibiting extensive strain-level genomic diversity and recombination, the extent to which mobile elements contribute to this variation, and their relevance to its fitness and virulence, remain incompletely understood. Our recent study of the Pg pangenome revealed diverse accessory defense-associated genes, raising the question of whether these are carried by unrecognized mobile genetic elements (MGEs). Integrative and conjugative elements (ICEs) are large autonomous mobile elements that often encode genes for proteins beneficial to their bacterial hosts, including defense systems that protect against phage infection. To date, only one ICE, CTnPg1, has been described in Pg .

RESULTS: Here, we developed a bioinformatic approach integrating ICE prediction and curation, hallmark-gene detection, and genomic-context analysis, to investigate ICEs in Pg . We discovered that ICEs are pervasive in Pg genomes, with >90% of genomes harboring at least one ICE. We found that these elements comprise at least five distinct groups, two of which dominate and frequently co-occur in Pg genomes, inserting into distinct characteristic insertion sites. Using marker-gene analysis of enrichment-culture mini-metagenomes from subjects with periodontal disease we detected representatives of these dominant Pg ICE groups, as well as others, in recent clinical samples. We found that anti-defense and defense genes are common in Pg ICEs, and that these elements commonly encode biosynthetic gene clusters, including for menaquinone synthesis and predicted ribosomally synthesized and post-translationally modified peptides (RiPPs). In contrast to the extensive CRISPR-Cas defense targeting we observed for Pg phages, we detected no exact matches between ICE sequences and Pg CRISPR spacers.

CONCLUSION: This work establishes that ICEs are pervasive contributors to Pg 's pangenome and unique strain-level gene repertoires. Their distinct cargo profiles suggest that ICEs likely impact the virulence and ecology of Pg through the introduction and spread of advantageous traits, including expansion of Pg 's biosynthetic capacity and resistance to phage infection. This work provides a curated framework for investigating ICE diversity in Pg and establishes a foundation for expanded experimental studies of their host ranges and roles in shaping Pg 's interactions with phages, other microbes, and the human host.},
}

@article {pmid42621231,
year = {2026},
author = {Bari, MA and Pal, DC and Khan, MAM and Momen, M and Khan, M and Karim, MM and Hoq, MM and Khan, SN},
title = {Genomic Insights Into Bacillus thuringiensis Strain JSd1 From Bangladesh: A Whole Genome Sequencing Approach.},
journal = {Bioinformatics and biology insights},
volume = {20},
number = {},
pages = {11779322261475762},
pmid = {42621231},
issn = {1177-9322},
abstract = {Bacillus thuringiensis (Bt) is a well-known entomopathogenic bacterium widely used in biopesticide formulations due to its diverse arsenal of insecticidal toxins and environmental adaptability. However, the genetic diversity and virulence potential of native Bt strains from South Asia remain underexplored. In this study, we performed whole-genome sequencing and comparative genomic analysis of B. thuringiensis strain JSd1, isolated from Bangladeshi soil. The high-quality draft genome, assembled at 75x coverage, comprises 5.39 Mb in 64 contigs with a GC content of 35.28% and 99.26% completeness. Genome annotation revealed 5,833 genes, including 5,756 protein-coding sequences and numerous non-coding RNAs. It also harbors 4 different plasmids. Importantly, we identified 25 genomic islands harboring mobile elements and hypothetical proteins, highlighting the strain's dynamic genome evolution. The genome encodes a diverse array of virulence factors linked to insecticidal activity. Notable genes include cry22A and vip3A homologs, multiple bmp1-like metalloproteases, enhancin, cytK, and chiA, as well as various chitinases and serine proteases. The co-occurrence of chromosomal and plasmid-encoded virulence factors suggests modular acquisition mechanisms. Secondary metabolite biosynthetic clusters, such as those for petrobactin, bacillibactin, thuricin CD, and other novel RiPPs and NRPs, were detected, supporting the strain's potential in biological control. Phylogenetic analysis positioned JSd1 within the B. cereus sensu lato group, forming a highly supported clade with B. thuringiensis serovar konkukian and B. anthracis. Comparative genomic and pan-genome analyses revealed substantial genomic diversity among B. thuringiensis strains. The strain's genome contains 2,237 core genes and a large accessory genome, reflecting its ecological adaptability. Our findings suggest that B. thuringiensis JSd1 is a promising candidate for development as a biopesticide targeting insect pests in Bangladeshi agriculture. The comprehensive genomic insights lay the groundwork for further functional validation and field applications, contributing to sustainable pest management strategies in the region.},
}

@article {pmid42622701,
year = {2026},
author = {Smith, LY and Farace, PD and Sabio Y García, J and Vilte, D and Riviere, N and Larzábal, M and Cataldi, A and Marques Da Silva, W},
title = {Comprehensive Genomic Analysis of the pO157 Plasmid in Enterohemorrhagic Escherichia coli O157:H7 Reveals Non-synonymous Variation in Virulence Factors.},
journal = {Current microbiology},
volume = {83},
number = {10},
pages = {},
pmid = {42622701},
issn = {1432-0991},
support = {PICT 2018-0118//Agencia Nacional de Promoción Científica y Tecnológica/ ; STEC/SUH Nº 224RT0152//Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo (CYTED)/ ; PNSA-PDi 113-P23//Instituto Nacional de Tecnología Agropecuaria/ ; },
mesh = {*Escherichia coli O157/genetics/pathogenicity/isolation & purification ; *Virulence Factors/genetics/metabolism ; *Plasmids/genetics ; *Genetic Variation ; Humans ; Escherichia coli Proteins/genetics/metabolism/chemistry ; Genomics ; *Genome, Bacterial ; Escherichia coli Infections/microbiology ; Base Composition ; },
abstract = {Enterohemorrhagic Escherichia coli (EHEC) O157:H7 is a zoonotic pathogen responsible for severe human diseases, including hemolytic uremic syndrome. Its virulence plasmid, pO157, encodes toxins, proteases, and adhesins; however, the extent of genetic variability among strains remains poorly characterized. Here, we analyzed 153 complete pO157 sequences using comparative pan-genomic and structural approaches. Plasmids ranged from 88.2 to 98.1 kb, contained 84-102 coding sequences, and displayed highly conserved GC content (~ 47.85%). The pan-genome comprised 145 genes, including 60 core and 85 accessory genes, many of which encode hypothetical proteins of unknown function. Key pO157-associated genes (ehxA, katP, stcE, espP, and toxB) were present in all analyzed isolates. Subcellular localization predictions indicated that most proteins are cytoplasmic, whereas only a small subset of hypothetical proteins showed potential secretion signals. Comparative structural analyses revealed that the analyzed protein variants maintained highly conserved overall predicted architectures despite localized amino acid variability. Although some substitutions were located within predicted functional regions, the analyses revealed no major structural alterations among variants. Hemolytic activity assays performed in selected strains revealed phenotypic variability that was not exclusively associated with ehxA sequence variation, suggesting the involvement of additional regulatory or genetic factors. Overall, these findings indicate that pO157 maintains a highly conserved genomic organization while preserving limited sequence variability among virulence-associated genes. This study provides a comparative framework for future investigations aimed at understanding the functional significance of pO157-associated genetic variation in EHEC O157:H7.},
}

*Escherichia coli O157/genetics/pathogenicity/isolation & purification
*Virulence Factors/genetics/metabolism
*Plasmids/genetics
*Genetic Variation
Humans
Escherichia coli Proteins/genetics/metabolism/chemistry
Genomics
*Genome, Bacterial
Escherichia coli Infections/microbiology
Base Composition

@article {pmid42616262,
year = {2026},
author = {Barbosa Nunes, IA and de Oliveira, AR and de Oliveira Veras, AA and Silva, A and Costa, EC and Modolon, F and Peres, FV and de Mahiques, MM and Baraúna, RA and de Souza Costa, S and das Graças, DA and Pellizari, VH},
title = {Genomic insights from a long-read assembly of a deep-sea Chromohalobacter israelensis strain from Santos Basin pockmarks field.},
journal = {Brazilian journal of microbiology : [publication of the Brazilian Society for Microbiology]},
volume = {57},
number = {1},
pages = {},
pmid = {42616262},
issn = {1678-4405},
mesh = {*Genome, Bacterial ; *Chromohalobacter/genetics/isolation & purification/classification/metabolism ; Phylogeny ; Genomics ; *Geologic Sediments/microbiology ; *Seawater/microbiology ; Salinity ; },
abstract = {Continental slopes, particularly the pockmark and salt diapir regions of the Santos Basin, represent extreme environments characterized by high hydrostatic pressure, low temperatures, elevated salinity, and limited organic matter, fostering unique bacterial communities. This study aimed to elucidate the metabolic strategies enabling survival in these conditions by exploring the genome of a Chromohalobacter israelensis strain isolated from such sediments, utilizing long-read sequencing. The genome, assembled into a single 3.8 Mb contig with 98.9% completeness, confirmed the strain's taxonomic identity. Analysis revealed genes for metabolizing diverse carbohydrate sources, a complete ectoine synthesis cluster essential for halophily, and genes conferring tolerance to osmotic stress, low temperatures, and pH, underscoring its polyextremophilic capacity. Pangenome analysis identified a substantial core genome with essential metabolic functions, including a species-exclusive sulfur metabolism reaction. These findings highlight the strain's biotechnological potential and contribute to understanding the genus's adaptation to diverse hypersaline habitats and the strain's potential role in the sampled environment.},
}

*Genome, Bacterial
*Chromohalobacter/genetics/isolation & purification/classification/metabolism
Phylogeny
Genomics
*Geologic Sediments/microbiology
*Seawater/microbiology
Salinity

@article {pmid42616428,
year = {2026},
author = {Fan, M and Ding, X and Shi, Q and Wu, S and Zhou, J and Zou, H and Wang, Z and Xie, J and Huang, L},
title = {Pangenome Analysis Uncovers Two Pathotypes of Dickeya dadantii, the Causal Agent of Sweetpotato Stem Rot, and Identifies Virulence-Associated Genes.},
journal = {Journal of agricultural and food chemistry},
volume = {74},
number = {32},
pages = {25075-25088},
doi = {10.1021/acs.jafc.6c06279},
pmid = {42616428},
issn = {1520-5118},
support = {2024CXTD07//Guangdong Provincial Special Fund for Modern Agriculture Industry Technology Innovation Teams/ ; 2024YFD1401203-5//National Key Research and Development Program of China/ ; CARS-10-Sweetpotato//China Agricultural Research System/ ; },
mesh = {*Ipomoea batatas/microbiology ; *Plant Diseases/microbiology ; *Virulence Factors/genetics/metabolism ; Plant Stems/microbiology ; Virulence ; *Dickeya/genetics/pathogenicity/isolation & purification/classification/metabolism ; *Genome, Bacterial ; *Bacterial Proteins/genetics/metabolism ; Phylogeny ; },
abstract = {Bacterial stem and root rot (BSRR), caused by Dickeya dadantii, is a devastating disease affecting sweetpotato [Ipomoea batatas (L.) Lam.] worldwide, yet the pathogen's population structure and core virulence determinants remain poorly understood. Here, we constructed the first comprehensive pangenome of D. dadantii by integrating complete PacBio HiFi sequencing of a representative strain (E36) with resequencing of 32 Chinese isolates and 23 global strains. Population genomic analysis revealed that geographic isolation and host adaptation drive genetic differentiation, with sweetpotato-associated Chinese strains clustering into two major lineages (Groups I and II). Mining the core genome identified 36 conserved candidate effectors, of which CpxP and Spy were experimentally validated as virulence factors: both triggered a hypersensitive response in Nicotiana benthamiana, and their deletion mutants exhibited attenuated virulence on sweetpotato. This study delineates the population architecture of the BSRR pathogen and uncovers key virulence determinants.},
}

*Ipomoea batatas/microbiology
*Plant Diseases/microbiology
*Virulence Factors/genetics/metabolism
Plant Stems/microbiology
Virulence
*Dickeya/genetics/pathogenicity/isolation & purification/classification/metabolism
*Genome, Bacterial
*Bacterial Proteins/genetics/metabolism
Phylogeny

@article {pmid42617150,
year = {2026},
author = {Huang, KT and Yang, YH and Lin, MJ and Lin, YH and Lai, SK and Chou, TH and Lee, CY and Hung, TK and Hsu, CL and Yang, YC and Chen, CY and Chen, PL and Hsu, JS},
title = {gAIRR-wgs: high-resolution T cell receptor allele typing in biobank-scale whole-genome sequencing data.},
journal = {Briefings in bioinformatics},
volume = {27},
number = {4},
pages = {},
doi = {10.1093/bib/bbag441},
pmid = {42617150},
issn = {1477-4054},
support = {111-2320-B-002-091-MY3//National Science and Technology Council in Taiwan/ ; 114-2622-B-002-009//National Science and Technology Council in Taiwan/ ; 112-2622-B-002-012//National Science and Technology Council in Taiwan/ ; IBMS-CRC115-P03//Institute of Biomedical Sciences, Academia Sinica/ ; //National Taiwan University/ ; 112L895201//Higher Education SPROUT Project/ ; 113L892901//Higher Education SPROUT Project/ ; 114L891101//Higher Education SPROUT Project/ ; //Ministry of Education, Taiwan/ ; },
mesh = {Humans ; *Whole Genome Sequencing/methods ; *Alleles ; *Receptors, Antigen, T-Cell/genetics ; *Genome, Human ; },
abstract = {T cell receptor (TR) genes are essential components of the adaptive immune receptor repertoire, and growing evidence links TR germline variants to immune-related diseases. However, their highly allelic diversity and sequence homology make them challenging dark regions of the human genome. Current TR genotyping tools have limited support for population-scale studies using standard-depth (30×) whole-genome sequencing (WGS), leaving a critical gap. We present germline Adaptive Immune Receptor Repertoire (gAIRR)-wgs, the first highly resource-efficient workflow specifically designed for high-resolution TR allele typing from short-read WGS. Benchmarking against 44 assembly-validated Human Pangenome Reference Consortium Release 1 subjects showed high overall accuracy performance across TR loci (mean F1/accuracy: 0.996/0.997), with comparable results in an independent cohort of 182 Release 2 individuals (0.984/0.988). Applying gAIRR-wgs to 1492 Taiwan Biobank (TWB) participants, we identified 450 novel TR alleles absent from the international ImMunoGeneTics (IMGT) information system database, accounting for 57.5% of all identified TR alleles and representing an ~102% expansion of the current IMGT TR repertoire-277 of which were cross-validated in non-East Asian cohorts-and 109 novel TR V alleles with allele frequencies >1% in the TWB. Notably, the tool uncovered population-specific structural polymorphisms, including T cell receptor gamma variable (TRGV) genes (TRGV4/TRGV5 deletions) and T cell receptor beta variable (TRBV) genes (TRBV3-2/TRBV4-3 insertion/deletion), which were overlooked by Illumina Dynamic Read Analysis for GENomics (DRAGEN). Furthermore, we identified 34 TR genes exhibiting significant allelic divergence between Taiwanese and global populations. By enabling accurate TR genotyping from 30× WGS data, gAIRR-wgs effectively unlocks the immunogenomic potential of massive biobank resources, bridging the gap between standard genomic surveys and adaptive immune repertoire analysis.},
}

Humans
*Whole Genome Sequencing/methods
*Alleles
*Receptors, Antigen, T-Cell/genetics
*Genome, Human

@article {pmid42618781,
year = {2026},
author = {Holley, G and Eggertsson, HP and Kristmundsdottir, S and Beyter, D and Skuladottir, AT and Moore, KHS and Olason, PI and Gylfason, A and Magnusson, OT and Oddsson, A and Stefansson, H and Helgason, A and Masson, G and Sulem, P and Gudbjartsson, DF and Stefansson, K and Halldorsson, BV},
title = {An Icelandic pangenome reference.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {42618781},
issn = {1476-4687},
abstract = {Reference bias is an issue that affects most genomic studies analysing short reads mapped to a reference genome[1,2]. It can be mitigated by mapping to multiple haplotypes represented in a pangenome[3-5]. Here we introduce two new methods to address reference bias: Emblask for pangenome construction and Weaver for mapping to pangenomes at scale. Emblask is a hybrid long- and short-read haplotype-resolved dual assembly pipeline for parent-offspring trio data. Using Emblask, we assembled 698 Icelandic haplotypes and added them to the Human Pangenome Reference Consortium (HPRC) pangenome[4] to construct an Icelandic pangenome reference (HPRC-ICE) including 51.41 million small variants. We mapped the short reads of 57,630 Icelanders to HPRC-ICE with Weaver and called 98.96 million variants, representing a 6.17% increase over mapping to a linear reference. We uncovered new variants in low-mappability regions, including a pathogenic single nucleotide polymorphism (SNP) in GBA1 that associates with early onset Parkinson's disease and a missense SNP in CBS that is pathogenic for homocystinuria. We replicated the GBA1 association in the UK Biobank[6] with a targeted remapping of 429,193 British and Irish participants.},
}

@article {pmid42619700,
year = {2026},
author = {Ricono, AM and Myers, ZA and Schoenecker, D and Menon, A and Such, D and Hazen, A and Wise, A and Brůna, T and Jenkins, J and Plott, C and Webber, J and Boston, L and Shu, S and Qiu, Y and Barry, K and Nwakama, CK and Grimwood, J and Schmutz, J and Lovell, JT and Greenham, KM},
title = {Paralog diversification masks conserved diel regulatory programs during cold acclimation in Brassica rapa.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.07.24.740384},
pmid = {42619700},
issn = {2692-8205},
abstract = {Plant stress responses occur within daily cycles of physiology, metabolism, and growth, making timing a critical dimension of acclimation. In Arabidopsis, circadian and diel regulation influence responses to abiotic stress, including cold, but how this temporal regulation is conserved, diversified, or expanded in crop genomes remains unclear. This question is especially challenging in Brassica rapa, which underwent a genome triplication after diverging from Arabidopsis, resulting in multiple retained paralogs that can be grouped by Arabidopsis orthology and ancient homeologous relationships. Here, we generated a B. rapa pangenome spanning six morphotypes and used it to profile diel (24 h) cold acclimation responses across diverse accessions differing in freeze tolerances. Cold altered peak expression time for thousands of genes, which we grouped into distinct phase-change groups. Circadian leaf movement assays revealed accession-specific differences in clock period and temperature compensation under cold, suggesting that altered clock behavior may contribute in part to the diel transcriptome retiming. At the individual gene level, inferred gene regulatory networks (GRNs) were highly accession-specific and lost shared connectivity under cold stress. However, grouping these paralogs by their Arabidopsis orthologs revealed a highly conserved regulatory architecture that was otherwise masked by paralog diversification. Integrating these networks with functional pathways identified key candidate regulators of retimed processes, including modules linked to nighttime phosphorylation and daytime photosynthesis. Finally, analyzing conserved noncoding sequences across the pangenome prioritized specific regulatory targets within cold-retimed groups. Together, these results demonstrate that cold acclimation in B. rapa is shaped by a combination of diel retiming, paralog-specific regulation, and deeply conserved programs.},
}

@article {pmid42619792,
year = {2026},
author = {Lin, MJ and Shivakumar, VS and Langmead, B and , },
title = {ImpuT2T: Pangenome-Based Patching for Human Genome Assemblies.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.07.27.741037},
pmid = {42619792},
issn = {2692-8205},
abstract = {With improvements in sequencing and assembly have come many high-quality telomere-to-telomere assemblies and reference pangenomes. However, the long-read sequencing recipes needed for high quality assemblies are expensive, and out of reach for many research groups. Here we propose ImpuT2T, a method that takes an assembly produced via inexpensive HiFi sequencing reads, and uses a panel of T2T (or near-T2T) assemblies to scaffold and fill ("patch") the gaps between the HiFi contigs. Benchmarking against reference assemblies demonstrates that ImpuT2T is highly effective at patching human HiFi assemblies, consistently outperforming existing patching approaches. Moreover, we show that including more haplotypes in the pangenome improves the quality of the patched assemblies, with the greatest gains achieved using the full HPRC Release 2 pangenome.},
}

@article {pmid42609112,
year = {2026},
author = {Gwak, YS and Suh, HY and Yoon, HR and Kim, S and Bae, CI and Kim, MJ},
title = {Comparative Genomics-Based Evaluation of Lacticaseibacillus rhamnosus KFOM 0134 as a Probiotic against Staphylococcus aureus.},
journal = {Journal of microbiology and biotechnology},
volume = {36},
number = {},
pages = {e2606012},
pmid = {42609112},
issn = {1738-8872},
mesh = {*Probiotics/pharmacology ; *Staphylococcus aureus/drug effects/growth & development ; *Lacticaseibacillus rhamnosus/genetics/isolation & purification/physiology/classification ; Genome, Bacterial/genetics ; Bacteriocins/genetics ; Genomics ; Humans ; Phylogeny ; Whole Genome Sequencing ; Bacterial Adhesion ; Brassica/microbiology ; *Antibiosis ; Animals ; Antimicrobial Peptides/genetics ; Anti-Bacterial Agents/pharmacology ; Food Microbiology ; },
abstract = {Lactic acid bacteria are widely recognized for their probiotic potential and their ability to inhibit pathogenic microorganisms through the production of antimicrobial compounds and competitive exclusion mechanisms. Staphylococcus aureus is a globally significant human and animal foodborne pathogen and a major cause of foodborne diseases, posing serious public health concerns. This study aimed to develop a probiotic strain capable of suppressing S. aureus. Lacticaseibacillus rhamnosus strain KFOM 0134 was isolated from salted kimchi cabbage; it demonstrated strong tolerance to acidic and high-bile conditions. It did not exhibit any cytotoxic effects, but displayed significant anti-inflammatory activity and enhanced intestinal adhesion capacity. Notably, KFOM 0134 exerted pronounced antimicrobial activity against S. aureus, highlighting its potential as a functional probiotic. Whole-genome sequencing revealed bacteriocin- and cryptic antimicrobial peptide (AMP)-related genetic determinants, but not any virulence- or transferable antibiotic resistance-associated genes, supporting its pathogenic safety. To further contextualize this strain within species-wide diversity, 402 L. rhamnosus genomes were compared, revealing extensive diversity characterized by an open pangenome structure and clade-associated metabolic differentiation. Phylogenetic positioning and lineage-specific functional signatures provided additional insight into the genetic basis of antimicrobial competence. Overall, phenogenomics of L. rhamnosus KFOM 0134 confirmed its well-defined probiotic potential via experimental validation of functional traits, comprehensive genome-based safety assessments, and the identification of bacteriocin- and AMP-associated genes. These findings substantiate its safety and antimicrobial functionality, supporting its applicability in food safety management and functional food development.},
}

*Probiotics/pharmacology
*Staphylococcus aureus/drug effects/growth & development
*Lacticaseibacillus rhamnosus/genetics/isolation & purification/physiology/classification
Genome, Bacterial/genetics
Bacteriocins/genetics
Genomics
Humans
Phylogeny
Whole Genome Sequencing
Bacterial Adhesion
Brassica/microbiology
*Antibiosis
Animals
Antimicrobial Peptides/genetics
Anti-Bacterial Agents/pharmacology
Food Microbiology

@article {pmid42610566,
year = {2026},
author = {Mavima, L and Steenkamp, ET and Soogun, TO and Beukes, CW and Palmer, M and Whitman, WB and Howieson, J and Yates, R and James, EK and De Meyer, SE and Coetzee, MPA and Venter, SN},
title = {Delineation of Paraburkholderia tuberum and description of Paraburkholderia lebeckiae sp. nov. isolated from the root nodules of South African Lebeckia ambigua.},
journal = {International journal of systematic and evolutionary microbiology},
volume = {76},
number = {8},
pages = {},
doi = {10.1099/ijsem.0.007262},
pmid = {42610566},
issn = {1466-5034},
mesh = {South Africa ; *Phylogeny ; *Burkholderiaceae/classification/genetics/isolation & purification ; RNA, Ribosomal, 16S/genetics ; DNA, Bacterial/genetics ; *Root Nodules, Plant/microbiology ; Sequence Analysis, DNA ; Bacterial Typing Techniques ; Nucleic Acid Hybridization ; *Fabaceae/microbiology ; Genome, Bacterial ; },
abstract = {Paraburkholderia tuberum is a diverse beta-rhizobial species (i.e. rhizobia bacteria belonging to the class Betaproteobacteria) indigenous to South Africa that associates mostly with indigenous papilionoid legume species. The taxonomic boundary of this species was reviewed in 2022, which indicated that it includes a number of diverse strains. In fact, some of these P. tuberum strains appear to have sufficient genetic heterogeneity to belong to separate species. The absence of publicly available whole-genome sequences for the majority of P. tuberum strains during the last review of their taxonomy limited the accuracy of their species delineation. In this study, we revise the species delineation of P. tuberum using a comprehensive genome-based approach. With whole-genome sequences of 28 P. tuberum strains now available, we performed genealogical concordance analysis based on 92 conserved gene regions and conducted analysis of average nucleotide identity, digital DNA-DNA hybridization and pangenome coding content. Overall, our analyses grouped the 28 P. tuberum strains into two separate species clusters, which showed sufficient divergence to allow recognition as separate species. The one cluster represents P. tuberum sensu stricto, while the second cluster was described as a novel species. For this novel species, we propose the name Paraburkholderia lebeckiae sp. nov., with the type strain WSM4175[T] (=CMW-IA:007206[T]; DSM 120862[T]; LMG 34098[T]). Our results confirm that whole-genome-based information is crucial in determining accurate species boundaries, and its use should be supported and promoted.},
}

South Africa
*Phylogeny
*Burkholderiaceae/classification/genetics/isolation & purification
RNA, Ribosomal, 16S/genetics
DNA, Bacterial/genetics
*Root Nodules, Plant/microbiology
Sequence Analysis, DNA
Bacterial Typing Techniques
Nucleic Acid Hybridization
*Fabaceae/microbiology
Genome, Bacterial

@article {pmid42612246,
year = {2026},
author = {Chacon, DS and Gonzalez-Garcia, LN and Trinca, V and Varani, A and Guyot, R and Domingues, D},
title = {Coffea Comparative Genomics Reveals Subgenome-Associated Expansion and Diversification of Biosynthetic Gene Clusters.},
journal = {Genome},
volume = {},
number = {},
pages = {},
doi = {10.1139/gen-2026-0007},
pmid = {42612246},
issn = {1480-3321},
abstract = {Biosynthetic gene clusters (BGCs) are important for plant specialized metabolism, but remain poorly characterized in coffee. Given Brazil's importance in coffee production, we performed a comparative genomic analysis of BGCs across the allotetraploid Coffea arabica and its diploid progenitors C. eugenioides and C. canephora. Using standardized genome filtering, annotation, orthogroup inference, and cluster classification, we identified 472 BGCs comprising 3,118 biosynthetic genes, which were grouped into 194 cluster families and integrated with 28,280 orthogroups. Of these, 7,091 orthogroups were shared across all species; Coffea canephora and subgenomes shared 10,923, while Coffea eugenioides and subgenomes shared 11,446. Most BGC-associated orthogroups (86.4%) link to a single pathway class. BGC-associated genes form a highly structured yet lineage-dynamic component of the Coffea pangenome. C. eugenioides and its derived subgenomes in Arabica contributed disproportionately to 14 BGC-associated orthogroups, including flavonoid-, lipid-, and stress-related functions. In contrast, C. canephora derivatives contributed only two terpene-related orthogroups. The parental species showed fewer secondary metabolism-related enriched GO terms (3 and 1) than their subgenomes (53 and 56). Species-specific rearrangements, expansions, and subgenome retention indicate that hybridization and polyploidy shaped BGC diversification. These results advance understanding of specialized metabolism in Coffea and identify targets for coffee improvement and climate resilience.},
}

@article {pmid42613741,
year = {2026},
author = {Mastromatteo, S and Chirmade, S and Roshandel, D and Thiruvahindrapuram, B and Wang, Z and Patel, RV and Sung, WWL and Hajianpour, A and Wang, C and Lin, F and Keenan, K and Avolio, J and Eckford, P and Ratjen, F and , and Strug, LJ},
title = {PangyPlot: multi-scale interactive visualization of pangenome variation graphs.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btag619},
pmid = {42613741},
issn = {1367-4811},
abstract = {SUMMARY: Pangenome variation graphs integrate multiple samples into a unified representation, mitigating the reference bias inherent to linear genomes. However, these graphs can be large and structurally complex. Existing visualization tools are each confined to a fixed scale of resolution, requiring researchers to switch between multiple tools to examine variation at different levels of detail. PangyPlot is an interactive pangenome browser designed for multi-scale exploration of reference variation graphs from full chromosome to nucleotide-level sequence segments. PangyPlot anchors navigation to linear reference coordinates, organizes variation into hierarchical bubble structures, and uses a force-directed layout engine for automatic node arrangement.

An instance preloaded with data is available at https://pangyplot.research.sickkids.ca. Source code and documentation are openly available at https://github.com/strug-hub/pangyplot under the MIT License.},
}

@article {pmid42614613,
year = {2026},
author = {Molina-Mora, JA and Mora, J and Rojas, A},
title = {Pangenome Analysis of Angiostrongylus spp. of Veterinary and Clinical Importance and Exploratory Remarks on Potential New Drugs in Angiostrongylus costaricensis.},
journal = {Phenomics (Cham, Switzerland)},
volume = {6},
number = {2},
pages = {200-204},
pmid = {42614613},
issn = {2730-5848},
abstract = {UNLABELLED: The genus Angiostrongylus includes parasitic nematodes infecting diverse mammalian hosts and characterized by complex life cycles involving gastropod intermediate hosts. Among them, A. costaricensis, A. cantonensis, and A. vasorum cause severe inflammatory diseases affecting mesenteric, cerebral, and cardiopulmonary systems. Notably, A. costaricensis is the etiological agent of abdominal angiostrongyliasis, a condition lacking effective antiparasitic treatment. To better understand host specificity, pathogenicity, and identify potential therapeutic targets, we performed a comparative pan-genomic analysis integrating genomic and transcriptomic data from these three species. A total of 51,955 genes from four genomes were analyzed, with 89.4% assigned to 11,331 orthogroups and ~51.5% comprising the core genome shared across species. This conserved fraction likely reflects similarities in life cycle and pathogenic mechanisms, while accessory and species-specific genes suggest adaptive divergence. In A. costaricensis, 226 preliminary species-specific genes were identified, of which 179 were supported by transcriptomic data. However, most of these encode uncharacterized proteins, highlighting important annotation gaps. Functional and interactome analyses with species-specific genes identified candidate proteins related to enzymatic activity, cytoskeletal structure, and other domains. Drug-target analysis revealed 11 proteins with potential interactions with known compounds, including actin-related proteins predicted to interact with agents such as artenimol and copper. Additional targets included apoptotic protease-activating factor 1, receptor of activated protein C kinase 1, and an uncharacterized species-specific protein (ACOC_0000228101) with no orthologs in other Angiostrongylus. Despite limitations in available data and annotations, this study provides new insights into Angiostrongylus genomics and identifies candidate targets for drug development against abdominal angiostrongyliasis.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s43657-025-00301-1.},
}

@article {pmid42615245,
year = {2026},
author = {Zhang, P and Miao, L and Wang, H and Wang, J and Zhang, G},
title = {A pan-genome perspective uncovers the core genetic basis and evolutionary adaptation of lipid synthesis and vesicular transport in Nannochloropsis.},
journal = {Journal of phycology},
volume = {},
number = {},
pages = {},
doi = {10.1111/jpy.70218},
pmid = {42615245},
issn = {1529-8817},
support = {Project BJK2023042//Science Research Project of Hebei Education Department/ ; },
abstract = {Nannochloropsis microalgae are widely recognized as sustainable cell factories for producing nutritional oils and biofuels due to their high-lipid content. However, a comprehensive understanding of the genetic basis of their oleaginous traits across diverse species has been limited. Here, we constructed a pan-genome of 17 Nannochloropsis species comprising 14,851 gene families. Our analysis defined a distinct genetic architecture for lipid metabolism: Gene families associated with vesicular transport formed a conserved core functional module, whereas the genetic collection for lipid metabolism showed greater plasticity and was primarily classified as part of the soft-core genome. This finding establishes a genetic blueprint for the coevolution between a stable cellular "logistics network" and an adaptable "biosynthetic factory." Evolutionary analysis further indicated that the DGAT and fatty acid desaturase families have species-specific expansions in Nannochloropsis, suggesting a potential role in enhancing lipid accumulation. By integrating 231 transcriptome datasets, we identified key genes (ACP2 and DGAT2) that were highly upregulated under nitrogen deprivation and pinpointed a set of core genes with high expression levels involved in vesicular transport. This "Infrastructure-Toolkit" model provides both genetic targets for strain improvement and a broader framework for understanding lipid accumulation in oleaginous microorganisms.},
}

@article {pmid42615649,
year = {2026},
author = {Bahati, SY and Mwakalapa, EB and Mung'ong'o, HG and Makaranga, A and Kidenya, B and Maghembe, RS},
title = {Conserved intracellular virulence architecture and focal genomic diversification in sub-Saharan African Brucella melitensis.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0170326},
doi = {10.1128/spectrum.01703-26},
pmid = {42615649},
issn = {2165-0497},
abstract = {UNLABELLED: Brucella melitensis has a highly conserved genome, but the distribution of core-genome, gene-content, virulence-associated, mobile-element-associated, and antimicrobial-resistance-relevant variation among available sub-Saharan African genomes has not been examined in an integrated regional analysis. We analyzed 51 curated B. melitensis genomes from human and animal hosts using core-genome phylogenomics, pangenome reconstruction, virulence profiling, mobile genetic element (MGE) analysis, and mutation-based screening of antimicrobial resistance (AMR)-associated loci. A phylogeny reconstructed from 6,060 shared SNP sites resolved a dominant ST12-associated lineage, together with ST7, ST8, ST42, and novel sequence type branches. Individual genomes differed from the reference by 1,677-2,579 SNPs. The pangenome comprised 3,457 gene families, including 3,049 persistent families, indicating strong genome conservation, and limited accessory expansion. Virulence profiling identified 66 VFDB-associated genes; 48 genomes carried all 66, and the remaining three retained more than 98% of the virulence repertoire. Conserved determinants included the VirB type IV secretion system, lipopolysaccharide biosynthesis, intracellular survival pathways, and stress-response functions. MGE-associated variation was restricted to a small number of regions dominated by transposases and insertion-sequence-associated proteins. A GspF-domain-containing secretion-associated locus was detected only in BM2, although no complete type II secretion system gene cluster was identified. Recurrent substitutions occurred in AMR-relevant chromosomal loci, including rpoB, gyrA, gyrB, parC, parE, folA, folP, bepCDEFG, and mprF, but none corresponded to validated resistance-conferring alleles. The available regional genomes therefore comprise multiple phylogenetic lineages within a strongly conserved gene and intracellular virulence framework, with diversity concentrated in core-genome SNPs and localized genomic regions.

IMPORTANCE: Brucella melitensis is a major zoonotic pathogen at the livestock-human interface, but genome-resolved evidence from sub-Saharan Africa remains limited. This study curates available regional genomes and shows that the population is dominated by a conserved intracellular virulence backbone, strong core-genome conservation, and focal genomic diversification rather than by extensive accessory-genome expansion. By integrating phylogenomics, pangenome analysis, virulence profiling, mobile-element characterization, and mutation screening of antimicrobial-resistance-associated loci, the work provides a regional framework for One Health genomic surveillance and identifies candidate loci requiring phenotype-linked validation.},
}

@article {pmid42616173,
year = {2026},
author = {Dar, HA and Chughtai, AS and Baig, AH and Asghar, K},
title = {Integrated genomic analysis of Salmonella Typhi from Pakistan: Antimicrobial resistance determinants, pangenome structure, and reverse vaccinology-driven vaccine target discovery.},
journal = {Functional & integrative genomics},
volume = {26},
number = {1},
pages = {},
pmid = {42616173},
issn = {1438-7948},
mesh = {*Salmonella typhi/genetics/pathogenicity/immunology/drug effects ; Reverse Vaccinology ; Pakistan ; Humans ; *Genome, Bacterial ; *Drug Resistance, Bacterial/genetics ; *Typhoid Fever/microbiology/prevention & control ; Plasmids/genetics ; Genomics ; Genomic Islands ; },
abstract = {Salmonella enterica serovar Typhi (S. Typhi) is the aetiologic agent of typhoid fever in humans. The burden of typhoid is highest in low- and middle-income countries such as Pakistan. Moreover, the increasing emergence of antibiotic-resistant and hypervirulent S. Typhi strains highlights the need for deeper genomic understanding as current treatment regimens become progressively less effective. Therefore, this study analyzed publicly available S. Typhi genomes from Pakistan to characterize genomic diversity, sequence types, plasmid content, and antimicrobial resistance and virulence profiles. Subsequently, pangenome analysis identified conserved core proteins, which were screened via reverse vaccinology to prioritize potential vaccine candidates. Analysis of 71 high-quality S. Typhi genomes identified ST-1 and ST-2 as the predominant sequence types, a finding aligned with global trends. While plasmids were detected in 32% (n = 23) of isolates, these strains exhibited significantly higher antimicrobial resistance and virulence factor gene counts compared to plasmid-free strains (p < 0.05). All isolates were found to have the aac(6')-Iaa gene. The isolates harbored Salmonella Pathogenicity Islands (SPIs), including SPI-1 through SPI-10 and SPI-12. Pangenome analysis revealed an open pangenome, with calculated pangenome size of 5912 and core genome size of 3849. Reverse vaccinology analysis prioritized three broad-spectrum S. Typhi antigens STY1784, STY1830, and STY2871 as prime vaccine candidates, with support from cross-pathogen data in the literature. Additionally, our study identified nine antigenic, strong-binding, promiscuous HLA class I epitopes. This study provides updated genomic insights into circulating S. Typhi in Pakistan and proposes novel, computationally validated vaccine targets, laying a crucial foundation for subsequent experimental investigation.},
}

*Salmonella typhi/genetics/pathogenicity/immunology/drug effects
Reverse Vaccinology
Pakistan
Humans
*Genome, Bacterial
*Drug Resistance, Bacterial/genetics
*Typhoid Fever/microbiology/prevention & control
Plasmids/genetics
Genomics
Genomic Islands

@article {pmid42616232,
year = {2026},
author = {Sena, S and Kumar, V},
title = {Empowering Plant Biotechnology Research: Super-Pangenomes as a Novel Arsenal for Crop Breeding and Improvement.},
journal = {Molecular biotechnology},
volume = {},
number = {},
pages = {},
pmid = {42616232},
issn = {1559-0305},
abstract = {The continuous innovations in sequencing methods have revolutionized the plant genomics research by capturing species diversity. Pangenome incorporates data from multiple genomes to generate a comprehensive and reference bias genomic architecture within a population. In recent years, several studies have provided the unprecedented advances in the field of plant pangenomes and enables the detection of structural variations, candidate genes, shedding lights into crop breeding and improvement. Further, expanding the scope of using accessions from multiple species at genus-level, the concept of pangenome has gradually evolved into a super-pangenome. Representing both cultivated and wild relatives within a genus, plant super-pangenome offers a novel insight in plant genomic information, adaptation, domestication and molecular breeding. By bridging the gap between complex genomic variants and genus-level taxa, these unprecedented advancements are reshaping the genetic landscape of gene repertoire, driving improved crop breeding in a time of global food security risk. This article focuses on the recent advancements of super-pangenome in plant research over the past few years. We also emphasize the different strategies for building plant super-pangenome and their potential applications and future perspectives which can help to expand the scope of plant genomics research.},
}

@article {pmid42599079,
year = {2026},
author = {Wen, Z and Kong, Y and Ling, M and Zhang, J and Du, B and Yu, Z and Yan, C and Xue, G and Gan, L and Feng, J and Fan, Z and Fu, T and Xu, Z and Yang, Y and Zhang, T and Feng, Y and Zhao, H and Cui, J and Yuan, J},
title = {Multidrug resistance and genomic characteristics of nontypeable Haemophilus influenzae isolates from the respiratory tract of pediatric patients.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0049826},
doi = {10.1128/spectrum.00498-26},
pmid = {42599079},
issn = {2165-0497},
abstract = {UNLABELLED: Nontypeable Haemophilus influenzae (NTHi) is a common colonizer of the human upper respiratory tract and one of the major pathogens responsible for pediatric respiratory tract infections. Given the increasing severity of its multidrug resistance (MDR), this study comprehensively investigated the genomic characteristics of circulating NTHi isolated from sputum and bronchoalveolar lavage fluid (BALF). A total of 104 H. influenzae isolates (69 from sputum; 35 from BALF) were collected from pediatric patients between January 2024 and January 2025. All isolates underwent whole-genome sequencing and antimicrobial susceptibility testing, followed by core/pan-genome phylogenetic analysis, multilocus sequence typing (MLST), and resistome profiling. Among them, 103 were identified as NTHi. We identified 29 known sequence types (STs) and 10 novel STs, with ST-107 (14.4%), ST-57 (10.6%), and ST-11 (8.7%) being the major circulating lineages. However, core-genome phylogenetic analysis provided a more granular view of the genetic variation within these identical STs. All the isolates showed high resistance to ampicillin (98.1%) and cefuroxime (84.6%). Genomically, the multidrug efflux pump gene hmrM was ubiquitous (100%). Ampicillin resistance was predominantly driven by blaTEM-1 carriage (77.9%), with minor contributions from chromosomal ftsI mutations. Fifteen plasmid replicons were predicted from 25 isolates, which highly coincided with the carriage of blaTEM-1 and other acquired resistance genes. This study demonstrates that MDR in pediatric NTHi is primarily driven by acquired resistance genes and chromosomal mutations, with specific resistant clones persisting and enriching under clinical antibiotic pressures. These findings underscore the importance of continuous high-resolution genomic surveillance in guiding rational antibiotic stewardship.

IMPORTANCE: This study highlights the critical importance of high-resolution genomic surveillance in managing pediatric nontypeable Haemophilus influenzae (NTHi) infections. By utilizing whole-genome sequencing, we uncovered the pathogen's highly dynamic population structure and complex multidrug resistance (MDR) mechanisms. Crucially, our findings reveal a strong, non-random coupling between core genomic architectures, virulence factors, and MDR elements, driven by dual environmental and pharmacological pressures. This "virulence-MDR" co-evolutionary trend underscores the persistent clinical threat of locally adapted high-risk clones. These findings provide important insights for guiding rational clinical antibiotic stewardship, optimizing treatment strategies, and improving regional infection control.},
}

@article {pmid42599638,
year = {2026},
author = {Abd-Alazeez, RA and Al-Janabi, SS and Mashaan, AO},
title = {Adaptive Evolution in Aminoacyl-tRNA Synthetases Drives Antibiotic Tolerance and Resistance in Clinical Klebsiella pneumoniae Isolates.},
journal = {Molecular biotechnology},
volume = {},
number = {},
pages = {},
pmid = {42599638},
issn = {1559-0305},
abstract = {Klebsiella pneumoniae is a major global health threat due to the rapid spread of antimicrobial resistance (AMR), which severely limits treatment options. Although horizontal gene transfer of mobile genetic elements is a key driver of multidrug resistance, this study explores how adaptive evolution within the core genome may also contribute to the clinical success of resistant strains. Using whole-genome sequencing-based pangenome analysis of clinically relevant classical K. pneumoniae isolates, we identified 3159 variants distributed across 414 core genes, indicating that even highly conserved cellular functions accumulate mutations in clinical environments. Functional enrichment analysis revealed a significant concentration of mutations in the aminoacyl-tRNA synthetase (aaRS) pathway, a central component of protein synthesis and a known antibiotic target. Multiple missense variants were detected in eight aaRS genes, with the Asn366Asp mutation in metG present in all analyzed isolates. We hypothesize that this conserved, recurrent mutation may contribute to bacterial adaptation, potentially by modulating protein synthesis, although this proposed mechanism remains speculative and requires experimental validation. Recurrent mutations were also observed in ileS and leuS, both targets of existing antimicrobials, while a Ser480Pro mutation in pyrG (CTP synthase) was identified in several isolates. Overall, these findings highlight core genome variation as a potential contributor to antimicrobial resistance in K. pneumoniae and suggest that conserved mutations such as metG Asn366Asp may represent candidate genomic biomarkers warranting further investigation. Because this study is based solely on comparative genomics, the proposed functional and mechanistic interpretations should be regarded as hypotheses for future experimental testing.},
}

@article {pmid42607688,
year = {2026},
author = {Salehi Nowbandegani, P and Zhang, S and Hu, H and Li, H and O'Connor, LJ},
title = {Defining and cataloging variants in pangenome graphs.},
journal = {Cell genomics},
volume = {},
number = {},
pages = {101327},
doi = {10.1016/j.xgen.2026.101327},
pmid = {42607688},
issn = {2666-979X},
abstract = {Structural variation causes some human haplotypes to align poorly with the linear reference genome, and this leads to "reference bias." A pangenome reference graph could ameliorate this bias by relating a sample to multiple reference assemblies. However, this approach requires a new definition of a "genetic variant." We define pangenome variants against a reference tree that includes all nodes (sequences) of the pangenome graph but only a subset of its edges; non-reference edges are variant edges. Analyzing the Minigraph-Cactus draft human pangenome reference graph, we identified 29.6 million genetic variants. 3.5 million variants (11.7%) have a reference allele that is not on GRCh38; these variants are difficult to detect without a pangenome reference and are found within tangled, multiallelic regions. We analyze the HLA-A and RHD gene regions and identify thousands of small variants entangled with several structural variants. We release the open-source pantree and a variant call format (VCF) variant catalog.},
}

@article {pmid42595445,
year = {2026},
author = {Roback, EY and X, M and Ricemeyer, ES and Warlen, A and Carroll, RA and Elsik, CG and Keene, AC and Rohner, N and McGaugh, SE and Warren, WC},
title = {A pangenome framework uncovers the role of deletions in repeated evolution of cave-derived traits.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.281719.125},
pmid = {42595445},
issn = {1549-5469},
abstract = {Structural variants (SVs) are increasingly recognized as key contributors to adaptive evolution, yet they remain underexplored compared with single-nucleotide variation. To understand how large-scale genomic changes shape repeated evolution, we leveraged multiple levels of sequence data across the powerful evolutionary model system of the Mexican tetra fish (Astyanax mexicanus). We constructed one of the first pangenome graphs from a naturally evolving vertebrate, enabling comprehensive discovery of SVs among 120 fish from 11 populations. We discover substantial amounts of structural variation and explore the roles of genomic biases and selection in shaping the distribution of these variants. More than 2400 high-confidence cave-specific deletions are enriched in biological pathways involved in vision, metabolism, and behavior and cluster nonrandomly in quantitative trait loci linked to cavefish traits. Additionally, 67 genes harbor unique deletions between independent cavefish lineages. These reused genes show evidence of population-specific selection (99% contain selective sweeps compared with 8%-15% in genes lacking SVs), indicating that deletions likely rose in frequency through repeated positive selection rather than drift. Together, these results reveal that recurrent deletion events have repeatedly contributed to the evolution of cave-adapted phenotypes and highlight deletions as underexplored contributors of adaptive evolution in extreme environments.},
}

@article {pmid42591579,
year = {2026},
author = {González-Espinoza, G and Molina-Mora, JA and Chaves-Leon, C and Solis-Jiménez, K and Vega-Álvarez, G and Zúniga-Pereira, AM and Chacón-Díaz, C and Rojas-Campos, N},
title = {First isolation and genomic insights of Bartonella henselae from domestic cats and dogs in Costa Rica.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1870135},
pmid = {42591579},
issn = {1664-302X},
abstract = {Bartonella spp. are vector-borne zoonotic pathogens responsible for cat-scratch disease and several other human disease manifestations. Previous studies in Costa Rica have reported Bartonella DNA in ectoparasites and bats; however, data from companion animals remain limited. Here, we investigated the occurrence of Bartonella spp. in domestic cats and dogs and characterized the circulating strains using molecular, culture-based, and genomic approaches. Blood samples were collected from 152 domestic cats and 188 domestic dogs from different Costa Rican regions. Conventional polymerase chain reaction (PCR) assays targeting citrate synthase (gltA) and the beta subunit of bacterial RNA polymerase (rpoB) were used to detect Bartonella spp. DNA was detected in 44% of the cats and 34% of the dogs. Partial gltA sequencing identified B. henselae, B. rochalimae, and B. clarridgeiae. Four B. henselae isolates recovered from feline blood were subjected to whole-genome sequencing. Comparative pan-genome and multilocus sequence typing (MLST) analyses identified sequence types ST1 and ST5 circulating in Costa Rica. These findings provide the first genomic characterization of Bartonella spp. from companion animals in Costa Rica and expand the current knowledge of the genetic diversity and epidemiology of Bartonella in Central America.},
}

@article {pmid42595398,
year = {2026},
author = {Yin, Z and Li, J},
title = {Co-application of pan-genomics and machine learning uncovers novel insights into the maintenance and evolution of microcystins production trait in Microcystis.},
journal = {Harmful algae},
volume = {158},
number = {},
pages = {103128},
doi = {10.1016/j.hal.2026.103128},
pmid = {42595398},
issn = {1878-1470},
mesh = {*Microcystins/genetics/biosynthesis/metabolism ; *Microcystis/genetics/metabolism ; *Machine Learning ; Genomics ; Phylogeny ; Evolution, Molecular ; Genome, Bacterial ; Gene Transfer, Horizontal ; Multigene Family ; },
abstract = {Microcystins (MCs), the potent hepatotoxins produced by toxic strains of Microcystis and other cyanobacteria, pose a major threat to freshwater ecosystems worldwide. However, the regulatory mechanisms, evolutionary origin, and maintenance of this energy-intensive toxigenicity remain largely unresolved. Based on 132 non-redundant Microcystis strains, this study combined pan-genomics analysis, phylogenetic reconstruction, pan-genome-wide association analysis and machine learning approaches to investigate the regulatory and evolutionary basis of MCs production. Results suggest that MCs production likely originated as an ancestral trait in Microcystis, while secondary horizontal gene transfer (HGT) and homologous recombination across the MCs biosynthesis-related (mcy) gene cluster and its flanking regions might have contributed to its distribution among polyphyletic lineages. Enrichment analysis further indicated distinct metabolic strategies between toxic and non-toxic Microcystis strains. Toxic strains are enriched in secondary metabolism, whereas non-toxic strains prioritize core metabolic pathways. Through co-occurrence analysis and multi-method screening, this study identified a candidate type II toxin-antitoxin (TA) system (TumE-TumA) that may be synergistically associated with mcy gene cluster. Structural and energetic analyses predicted a potential interaction between the TumE-family toxin protein and mcyA RNA (ΔiG= -44.6 kcal/mol), suggesting its potential regulatory role in MCs biosynthesis. Taken together, these findings support a proposed co-evolutionary framework in which secondary HGT may contribute to the phylogenetic distribution of mcy gene cluster, while the TA system may form a synergistic network with mcy gene cluster, contributing to the maintenance and evolution of MCs production by balancing metabolic costs with ecological benefits. While these in silico predictions require experimental validation, they provide new insights into the adaptive evolution of cyanobacterial toxigenicity and inform future strategies for managing harmful algal blooms.},
}

*Microcystins/genetics/biosynthesis/metabolism
*Microcystis/genetics/metabolism
*Machine Learning
Genomics
Phylogeny
Evolution, Molecular
Genome, Bacterial
Gene Transfer, Horizontal
Multigene Family

@article {pmid42579175,
year = {2026},
author = {Ali, SB and Ahmed, AA},
title = {Comparative genomic analysis of clinical Pseudomonas aeruginosa isolates from Iraq: insights into genome diversity, antimicrobial resistance, and phylogenetic relatedness.},
journal = {Molecular biology reports},
volume = {53},
number = {1},
pages = {},
pmid = {42579175},
issn = {1573-4978},
mesh = {*Pseudomonas aeruginosa/genetics/isolation & purification/drug effects ; Phylogeny ; Iraq ; Humans ; Genome, Bacterial/genetics ; Whole Genome Sequencing/methods ; Genomics/methods ; Drug Resistance, Multiple, Bacterial/genetics ; Anti-Bacterial Agents/pharmacology ; Genetic Variation ; Pseudomonas Infections/microbiology/genetics ; Drug Resistance, Bacterial/genetics ; Microbial Sensitivity Tests ; },
abstract = {Pseudomonas aeruginosa is a high-priority opportunistic pathogen of public health concern. Its large, complex genome, rich in transferable genetic elements, enables rapid acquisition of antibiotic resistance and contributes to its natural tolerance to antibiotics and disinfectants. Among fifty-two clinical isolates, shotgun whole-genome sequencing was conducted on four clinical isolates of P. aeruginosa from Erbil, Iraq (PA-1 to PA-4) and the laboratory strain PA-NCIMB 8626. The antibiotic susceptibilities of these strains were assessed using the Kirby-Bauer disk diffusion method. The clinical isolates selected for this study were PA-1 (multidrug-resistant, MDR), PA-2 (susceptible, S), PA-3 (extensively drug-resistant, XDR), and PA-4 (pan-drug-resistant, PDR), in addition to the standard strain NCIMB 8626. All strains underwent shotgun whole-genome sequencing and comprehensive bioinformatics analysis. Genomic DNA sequencing was performed on an MGI T7 platform using a unique DNA nanoball technology, followed by quality control, read assembly, gap closing, and annotation. Since the potential of Iraqi strains remains incompletely understood, whole-genome sequence (WGS) data from five P. aeruginosa strains were analyzed to compare genomic divergence in size, structure, and content, assess evolutionary relationships, and identify genes associated with antibiotic resistance and virulence. Virulence factor profiling identified key genes involved in adhesion, secretion, quorum sensing, iron acquisition, and biofilm formation, with isolate-specific differences. Gene analysis aligned efflux pump-related, β-lactam, and aminoglycoside resistance genes with phenotypic susceptibility profiles, except for one susceptible strain. Phylogenetic and evolutionary analyses indicated genomic diversity without sequence type clumping.},
}

*Pseudomonas aeruginosa/genetics/isolation & purification/drug effects
Phylogeny
Iraq
Humans
Genome, Bacterial/genetics
Whole Genome Sequencing/methods
Genomics/methods
Drug Resistance, Multiple, Bacterial/genetics
Anti-Bacterial Agents/pharmacology
Genetic Variation
Pseudomonas Infections/microbiology/genetics
Drug Resistance, Bacterial/genetics
Microbial Sensitivity Tests

@article {pmid42580335,
year = {2026},
author = {Zhang, K and He, Y and Lin, H and He, J and Wang, Z and Li, W and Chen, Y and Li, J and Shi, Y and Huang, X and Ding, M and Yang, P and Chen, Z and Chitikineni, A and Li, J and Gao, J and Feng, B and Zhang, Z and Hao, M and Mir, RR and Liu, D and Woo, SH and Janovská, D and Quinet, M and Fernie, AR and Liao, W and Feng, X and Gauchan, DP and Dhami, N and Kreft, I and Piński, A and Betekhtin, A and Spannagl, M and Liu, X and Varshney, RK and Liu, J and Zhou, M},
title = {Pangenome-guided breeding restores high-altitude adaptation and improves yield in Tartary buckwheat.},
journal = {Cell},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.cell.2026.07.035},
pmid = {42580335},
issn = {1097-4172},
abstract = {Tartary buckwheat is a nutritionally important crop of the Himalayas and is crucial for local economies and food security. However, key genes and superior alleles for high-altitude adaptability and yield remain poorly defined, constraining the breeding of high-altitude buckwheat varieties. Here, we generated a telomere-to-telomere reference genome and a 16-accession pangenome spanning Himalayan wild populations and globally distributed landraces. We identified 123,131 non-redundant structural variations in 16 accessions, including gene copy-number variations. The graph-based pangenome revealed FtRNH, a wild-specific gene that enhances high-altitude adaptability. We also identified a copy-number variation at the FtPLATZ locus and a 28-bp insertion in the FtPLATZ3 promoter that together contribute to seed-size variation across wild buckwheat and landraces. Leveraging these superior FtRNH and FtPLATZ alleles, we developed buckwheat lines with enhanced high-altitude adaptability and improved yields across sites. These findings establish a pangenome-guided strategy for recovering wild alleles and combining stress adaptation with yield improvement in crops.},
}

@article {pmid42584072,
year = {2026},
author = {Eiler, A},
title = {Rethinking evolutionary inference in metagenomic time series.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0069326},
doi = {10.1128/msystems.00693-26},
pmid = {42584072},
issn = {2379-5077},
abstract = {As ecologists increasingly use metagenomic time series to track evolution in the wild, there is a risk of misinterpreting ecological dynamics as rapid adaptation. This Perspective identifies methodological limitations that generate misleading signatures of microbial evolution. A primary issue is confusing evolutionary change (driven by de novo mutation or horizontal gene transfer) with ecological lineage turnover, such as seasonal oscillations or the reactivation of dormant lineages. Current metagenome-assembled genomes can collapse micro-diverse lineages and decouple adaptive mobile elements, creating inaccurate genomic signatures of sweeps or stasis. To address these issues, I propose a framework integrating long-read sequencing, pangenome graph theory, and forward-time simulations to model populations as temporal genetic networks and better resolve microbial evolutionary dynamics.},
}

@article {pmid42588512,
year = {2026},
author = {Zhou, B and Nie, X and Fan, H and Mao, X and Zhan, Z and Zhou, C and Xiong, J and Gao, J and Zhang, M and Li, L and Gan, B and Wu, X},
title = {A Novel LAMP-Based Lateral Flow Dipstick Technique for Rapid and Visual Detection of Burkholderia gladioli pv. cocovenenans.},
journal = {Molecules (Basel, Switzerland)},
volume = {31},
number = {15},
pages = {},
doi = {10.3390/molecules31152664},
pmid = {42588512},
issn = {1420-3049},
support = {20242BAB20333//Jiangxi Provincial Natural Science Foundation/ ; 20252BAC240614//Jiangxi Provincial Natural Science Foundation/ ; GSJK202401//Science and Technology Project of Jiangxi Provincial Administration for Market Regulation/ ; ZYK202403//Research Project of Jiangxi General Institute of Testing and Certification/ ; },
mesh = {*Burkholderia gladioli/genetics/isolation & purification ; *Nucleic Acid Amplification Techniques/methods ; *Molecular Diagnostic Techniques/methods ; Rapid Diagnostic Tests ; Humans ; Limit of Detection ; Sensitivity and Specificity ; Food Microbiology ; },
abstract = {Burkholderia gladioli pv. cocovenenans (B. gladioli pv. cocovenenans), the most representative pathovar of B. gladioli, is capable of producing thermostable and highly virulent bongkrekic acid, which can result in multiple organ failure and an extremely high case fatality rate in humans. This research aims to mine specific targets for B. gladioli pv. cocovenenans and develop a rapid and accurate assay for the detection of B. gladioli pv. cocovenenans in food. Two novel specific target genes (group_0918 and group_0110) were successfully screened through pan-genome analysis, and the excellent specificity and sensitivity of both targets were verified in comparison to PCR assays. Based on these targets, a loop-mediated isothermal amplification (LAMP) method was developed to specifically identify B. gladioli pv. cocovenenans. In pure culture and spiked fresh black fungus samples, the LAMP assay achieved a limit of detection (LOD) of 4.1 × 10[1] CFU/mL and 4.1 × 10[2] CFU/g for the detection of B. gladioli pv. cocovenenans, respectively. To enable point of care testing, a LAMP-based lateral flow dipstick(LFD) assay was established with a detection sensitivity of 4.1 × 10[3] CFU/g in fresh black fungus. Tests on naturally infected food samples demonstrated that the developed LAMP and LAMP-assisted visual detection assays can serve as an effective alternative for the accurate identification of B. gladioli pv. cocovenenans. The novel molecular detection technology established in this study offers an efficient and reliable detection method for the prevention and control of B. gladioli pv. cocovenenans contamination in food, which holds significant application value and promotion prospects.},
}

*Burkholderia gladioli/genetics/isolation & purification
*Nucleic Acid Amplification Techniques/methods
*Molecular Diagnostic Techniques/methods
Rapid Diagnostic Tests
Humans
Limit of Detection
Sensitivity and Specificity
Food Microbiology

@article {pmid42591269,
year = {2026},
author = {Rigano, G and Giuffrè, L and Strangio, S and Criseo, G and Cascio, GL and Alati, C and Meliadò, A and Martino, M and Principe, L and Romeo, O},
title = {Genomic epidemiology and phylogenomics of Magnusiomyces clavatus: a comparative analysis of novel italian and publicly available genomes.},
journal = {Frontiers in cellular and infection microbiology},
volume = {16},
number = {},
pages = {1872401},
pmid = {42591269},
issn = {2235-2988},
mesh = {Italy/epidemiology ; *Phylogeny ; *Genome, Fungal ; *Mycoses/epidemiology/microbiology ; Humans ; Molecular Epidemiology ; Polymorphism, Single Nucleotide ; Genetic Variation ; Genomics ; Whole Genome Sequencing ; },
abstract = {BACKGROUND: Magnusiomyces clavatus is an emerging fungal pathogen primarily infecting immunocompromised patients hospitalized in hematological wards. Its remarkable genetic homogeneity makes high-resolution phylogenetic analysis challenging, hindering efforts to accurately discriminate strains and complicating epidemiological surveillance, particularly in the context of hospital outbreaks.

METHODS: In this study, we provide the most comprehensive phylogenomic framework to date for this species by analyzing a dataset of 62 whole-genome sequences, including four novel genomes from clinical and environmental strains recovered in a large hospital in southern Italy.

RESULTS: Using a pangenome graph-based variant calling strategy on 1,624 high-quality single nucleotide polymorphisms, we delineated eight genetically distinct clades (A-H) that accurately reflect the geo-epidemiological history of this fungus. Population structure analysis revealed significant genetic differentiation among geographically separated populations, suggesting localized diversification. Furthermore, only the MATα idiomorph was identified across strains, supporting the highly clonal nature of M. clavatus. Finally, comparative mitogenomic analysis revealed 43 conserved translational bypass (byps) elements and identified four possible mitotypes based on presence or absence of specific inverted regions.

CONCLUSIONS: This work provides a robust, high-resolution framework for future genomic epidemiology studies and outbreak investigations of this important emerging fungal pathogen.},
}

Italy/epidemiology
*Phylogeny
*Genome, Fungal
*Mycoses/epidemiology/microbiology
Humans
Molecular Epidemiology
Polymorphism, Single Nucleotide
Genetic Variation
Genomics
Whole Genome Sequencing

@article {pmid42576353,
year = {2026},
author = {Mejía-Limones, I and Avellán-Llaguno, RD and Morey-León G, G and Andrade-Molina, D},
title = {Characterizing the pangenome-based virulome and resistome of uropathogenic Escherichia coli from Ecuador.},
journal = {Virulence},
volume = {17},
number = {1},
pages = {2707776},
doi = {10.1080/21505594.2026.2707776},
pmid = {42576353},
issn = {2150-5608},
mesh = {Ecuador/epidemiology ; *Uropathogenic Escherichia coli/genetics/pathogenicity/drug effects/isolation & purification/classification ; Humans ; *Escherichia coli Infections/microbiology/epidemiology ; *Urinary Tract Infections/microbiology/epidemiology ; *Genome, Bacterial ; Whole Genome Sequencing ; *Virulence Factors/genetics ; *Drug Resistance, Bacterial/genetics ; Virulence/genetics ; },
abstract = {Uropathogenic Escherichia coli (UPEC) is one of the leading causes of bacterial Urinary Tract Infections (UTIs) worldwide. In this study, we characterized the UPEC pangenome in Ecuador, focusing on the virulome and resistome of 142 genomes sequenced using whole-genome sequencing (WGS). Our analysis revealed a structure of 16,732 genes, including a conserved core of 3,385 genes and a dynamic accessory genome of 13,347 genes. The ST131 lineage was predominant, accounting for 42.3 % of the total, whereas the O25:H4 serotype was present in 42.96 % of the cases. The resistome was associated with a large accessory gene repertoire, with 3,712 significant associations identified across 29 antimicrobial resistance genes (ARGs). The virulome was organized into 23 main profiles, with adhesion and siderophore genes being the most abundant. These findings demonstrate the presence of high-risk variants in terms of virulence and resistance circulating in Ecuador, which requires the establishment of improved health control strategies in the region.},
}

Ecuador/epidemiology
*Uropathogenic Escherichia coli/genetics/pathogenicity/drug effects/isolation & purification/classification
Humans
*Escherichia coli Infections/microbiology/epidemiology
*Urinary Tract Infections/microbiology/epidemiology
*Genome, Bacterial
Whole Genome Sequencing
*Virulence Factors/genetics
*Drug Resistance, Bacterial/genetics
Virulence/genetics

@article {pmid42570694,
year = {2026},
author = {Wang, Y and Wu, Q and Li, J and Hu, P and Liu, Q and Lin, A and Lin, R and Liu, L and Wang, C and Kang, H and Li, C},
title = {Pangenomic sequencing and gene-unit genome-wide association study insights into genome plasticity and gene functions in Magnaporthe oryzae.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2026.08.020},
pmid = {42570694},
issn = {2090-1224},
abstract = {INTRODUCTION: Magnaporthe oryzaeis a model pathogenic fungus that causes serious disease in the two most important staple crops, rice and wheat. Elucidating the genetic variation within natural populations ofM. oryzaeand identifying genes involved in pathogenicity and environmental adaptation are essential for sustainable disease control.

OBJECTIVES: This study aimed to elucidate the mechanisms underlying genomic variation within the M. oryzae population and to develop a novel GWAS method specifically tailored to this species.

METHODS: The genomes ofM. oryzaediversity population 1 (MDP1), comprising 118 strains, were sequenced andde novoassembled. In addition, a novel gene-unit GWAS (GU-GWAS) method was developed to identify associated loci.

RESULTS: Phylogenetic analyses revealed three subgroups among the sequenced strains, which were associated with indica and japonica rice differentiation. We also characterized core and accessory genes in theM. oryzaepopulation through pan-genome analysis. Using GU-GWAS followed by functional validation, we cloned three new genes associated with pathogenesis (SPP1), fungicide tolerance (MoFCS1), and heavy metal tolerance (MoHMT1).

CONCLUSION: This study provides new insights into the pangenome ofM. oryzaeand introduces a method for the identification of functionally important genes in fungal species.},
}

@article {pmid42573514,
year = {2026},
author = {Brach, G and Schacherer, J},
title = {From one genome to thousands, and beyond.},
journal = {FEMS yeast research},
volume = {},
number = {},
pages = {},
doi = {10.1093/femsyr/foag038},
pmid = {42573514},
issn = {1567-1364},
abstract = {Over the past three decades, Saccharomyces cerevisiae has gone from being the first eukaryote to have its genome fully sequenced to one of the most studied biological systems. Advances in sequencing technologies, functional genomics, and population genomics have expanded the scope of study from a single laboratory reference genome to thousands of natural isolates, and the species-wide pangenome. These advances have revealed vast genetic and structural diversity, shaped by evolution, ecology, and domestication, while large-scale experimental resources have made yeast a model organism of choice in systems biology. In this review, we trace this transition from a reference genome view to an understanding of diversity at the population level, highlighting how telomere-to-telomere assemblies, graph-pangenome, and multi-omics approaches are transforming our ability to link genomic variation to phenotype. Together, these advances place S. cerevisiae at the forefront of efforts to understand and predict genotype-phenotype relationships in eukaryotes.},
}

@article {pmid42575389,
year = {2026},
author = {Guo, L and Meng, Z and Ma, X and Liu, Z and Zhang, C and He, J and Shi, M and Zou, C and Zhou, R and Song, X},
title = {TBGR-v2: an integrated pan-genome and evolutionary resource for Brassicaceae genomic research.},
journal = {Journal of genetics and genomics = Yi chuan xue bao},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jgg.2026.08.004},
pmid = {42575389},
issn = {1673-8527},
}

@article {pmid42565592,
year = {2026},
author = {Briaud, P and Schumacher, J and Whiteley, M},
title = {Discovery of Staphylococcus aureus small RNAs highly expressed during human chronic infection.},
journal = {mBio},
volume = {},
number = {},
pages = {e0063726},
doi = {10.1128/mbio.00637-26},
pmid = {42565592},
issn = {2150-7511},
abstract = {UNLABELLED: Understanding bacterial gene expression in natural environments remains challenging because most regulatory networks are inferred from in vitro models that poorly capture in situ environmental conditions. Here, we present NEMO (network transcriptomics of microbes in native environments), a generalizable pangenome-based metatranscriptomic framework for extracting microbial transcriptional programs from metatranscriptomes generated from natural samples. We applied NEMO to Staphylococcus aureus metatranscriptomes from human chronic wounds and cystic fibrosis sputum, revealing infection-associated transcriptional states that diverged markedly from in vitro growth conditions. Notably, small RNAs (sRNAs) were key drivers of the transcriptional divergence between human infection-derived and in vitro transcriptomes. Among these, we identify rsaX20 as a previously uncharacterized, zinc-responsive sRNA that also encodes a small peptide. Meta-analysis of more than 2,000 publicly available S. aureus RNA-seq data sets showed that rsaX20 is induced under zinc limitation and host-associated stress and is co-regulated with known metal-responsive sRNAs. Genetic, transcriptomic, and proteomic analyses demonstrated that rsaX20 is repressed by the zinc regulator Zur and functions as a dual-purpose sRNA/small open reading frame, with the RNA and peptide exerting distinct, sometimes opposing, effects on target proteins. Together, these findings establish NEMO as a broadly applicable framework for interrogating microbial gene regulation directly from native metatranscriptomes and identify rsaX20 as a key regulator of zinc homeostasis during chronic human S. aureus infection.

IMPORTANCE: Most knowledge of bacterial gene regulation comes from laboratory cultures, yet pathogens behave very differently inside the human body. We introduce NEMO, a pangenome-based framework that enables direct analysis of microbial gene expression from natural infection samples. Applying NEMO to human Staphylococcus aureus infections revealed transcriptional programs that differ substantially from standard in vitro models and highlighted small regulatory RNAs as major drivers of this divergence. Using this approach, we discovered rsaX20, a previously uncharacterized zinc-responsive regulatory RNA that also encodes a small peptide with distinct biological functions. These findings demonstrate the power of studying microbes in their native environments and uncover a key regulator of zinc homeostasis during chronic human infection.},
}

@article {pmid42569956,
year = {2026},
author = {Pandey, N and Rajagopal, R},
title = {Comparative genomics and metabolic model analysis of primary and secondary endosymbionts present in different species of whitefly.},
journal = {Journal of insect science (Online)},
volume = {26},
number = {4},
pages = {},
pmid = {42569956},
issn = {1536-2442},
mesh = {Animals ; *Hemiptera/microbiology ; *Symbiosis ; *Genome, Bacterial ; Genomics ; *Halomonadaceae/genetics/physiology ; },
abstract = {Candidatus Portiera aleyrodidarum (hereafter Portiera) is the primary endosymbiont of whiteflies (Hemiptera: Aleyrodidae), residing in specialized bacteriocytes that also co-localize diverse secondary endosymbionts. This study aimed to carry out in-depth genomic analysis of different strains of Portiera and secondary endosymbionts namely Arsenophonus, Cardinium, Hamiltonella, Rickettsia, and Wolbachia obtained from different whitefly species (data obtained from NCBI). Interestingly, hierarchical clustering of the amino acid identity data resulted in a dendrogram that resolved the different strains of Portiera into 3 separate genetic clusters. Pan-genome analysis of endosymbionts indicates that even closely related strains of a species, when isolated from different hosts, show unique genomic compositions due to their capability to adapt to a specific environment. COG/KEGG analysis revealed that amino acid metabolism is second most represented functional category of Portiera genomes whereas it is almost negligible in genomic repertoire of secondary endosymbionts except in Hamiltonella. Biosynthetic pathway analysis shows that threonine is the only essential amino acid for which complete set of genes is present in all strains of Portiera followed by leucine and tryptophan which is synthesized by all except 1 (China) and 2 strains (AD-CAI and SiSi), respectively. However, both amino acid lysine and arginine could be synthesized by only 4 strains namely AD-CAI, AF-CAI, PeMo, and TV. Further, the study established that secondary endosymbionts are capable of enriching the host's diet with protective organic compounds, B vitamins, and cofactors which is in contrast to the role of Portiera. Results of pathway-specific metabolic modelling were highly congruent with KEGG pathway predictions, depicting a positive correlation between the genotype and phenotype of endosymbionts.},
}

Animals
*Hemiptera/microbiology
*Symbiosis
*Genome, Bacterial
Genomics
*Halomonadaceae/genetics/physiology

@article {pmid42561951,
year = {2026},
author = {Li, K and Ciosek, JL and Koren, S and Phillippy, AM and Zhu, Y and Lauer, WA and Brooks, SY and Bouffard, GG and Pickett, BD and Dumont, BL and Smith, ML and Kalbfleisch, TS and Doris, PA},
title = {Telomere-to-telomere genome assembly and a pangenome for the rat.},
journal = {Cell genomics},
volume = {},
number = {},
pages = {101281},
doi = {10.1016/j.xgen.2026.101281},
pmid = {42561951},
issn = {2666-979X},
abstract = {We report a complete rodent telomere-to-telomere genome assembly from the brown rat, Rattus norvegicus. Annotation was enriched with multi-tissue long-read RNA sequencing and uncovered numerous novel genes. Assembly of both sex chromosomes reveals the absence of gene coding in the presumed pseudo-autosomal regions and the presence of centromeric satellite repeats on distal chromosome Y (chrY). We provide evidence of meiotic conjunction between Xp and Yq. The genome assembly reveals several expanded autosomal regions enriched for testis-expressed genes. Finally, we have generated a pangenome from recent high-quality assemblies of 8 distinct inbred rat strain genomes. This allows the strain-specific distribution of structural variation to be examined. Non-allelic homologous recombination has produced multiple copies of several genes with evidence of transcription from duplicated copies.},
}

@article {pmid42561953,
year = {2026},
author = {Li, K and Cappelletti, E and Dessaix, C and Ciosek, J and Robyn, E and Johnson, L and AbouEl Ela, NH and Arias, X and Adelson, DL and Raudsepp, T and Piras, FM and Smith, ML and Hudson, E and Pickett, BD and Koren, S and Walenz, BP and Brooks, SY and Sison, C and Crawford, J and Bouffard, G and Phillippy, AM and Miller, D and Antczak, DF and Cullen, J and Stroupe, S and Davis, BW and McCue, M and Durward-Akhurst, SA and Petersen, JL and Giulotto, E and Kalbfleisch, T},
title = {Phased T2T horse and donkey assemblies from a mule reveal peculiar equid centromere evolution.},
journal = {Cell genomics},
volume = {},
number = {},
pages = {101307},
doi = {10.1016/j.xgen.2026.101307},
pmid = {42561953},
issn = {2666-979X},
abstract = {We present telomere-to-telomere genome assemblies of a Thoroughbred horse and a donkey derived from their mule offspring. Now adopted and annotated by NCBI as reference genomes, these assemblies resolve previously inaccessible regions, including satellite arrays, duplications, and telomeres. Equids are known to exhibit an uncoupling between satellite DNA and centromeric function. The completeness of these assemblies enabled annotation of both satellite-based and satellite-free centromeres, as well as non-centromeric satellite loci, revealing notable centromeric plasticity. They also allowed detailed characterization of the variable binding domains of CENP-A-the epigenetic determinant of centromere identity-and CENP-B, whose association with CENP-A, previously considered typical based on a few model organisms, is absent in equids. Comparative analyses of satellite repeats and centromere positions provide new insights into the accelerated karyotypic reshuffling in equid evolution. These assemblies represent foundational resources for equine genomics and support ongoing initiatives such as the Equine Pangenome Project.},
}

@article {pmid42561915,
year = {2026},
author = {Hebbar, P and Potapova, T and Loucks, H and Ray, K and Rodrigues, MF and Ryabov, F and Malukiewicz, J and Yoo, D and Gomes de Lima, L and Haber, A and Kumar, S and Banerjee, S and Borchers, M and Garcia, GH and Gardner, J and Hachem, S and Heath, HD and Ha, SK and Mastoras, M and McNulty, B and Menendez, J and Munson, KM and Pal, K and Park, J and Plösch, S and Roos, C and Seligmann, WE and Shepelev, V and Spruce, C and Violich, I and Walter, L and Makova, KD and Thathiah, A and Sukoff Rizzo, SJ and Silva, AC and Carter, GW and Miga, KH and Eichler, EE and Conrad, DF and Gerton, JL and Alexandrov, IA and Paten, B},
title = {A complete genome for the common marmoset.},
journal = {Cell},
volume = {189},
number = {16},
pages = {4891-4908.e12},
doi = {10.1016/j.cell.2026.07.017},
pmid = {42561915},
issn = {1097-4172},
mesh = {Animals ; *Callithrix/genetics ; *Genome ; Centromere/genetics ; Telomere/genetics ; Evolution, Molecular ; Humans ; Female ; DNA, Satellite/genetics ; },
abstract = {The common marmoset is a New World monkey widely used to study primate evolution and human disease. We present a telomere-to-telomere (T2T) reference assembly for the species, plus three near-T2T haplotypes. These resolve previously inaccessible regions, including the centromeres, sex chromosomes, subterminal satellites, acrocentric chromosomes, and the major histocompatibility complex (MHC). We find marmoset centromeres carry dimeric alpha satellites with chromosomal specificity, flanked by inactive layers interpreted as ancestral centromere remnants. We assemble gene-poor, satellite-rich short arms of the acrocentrics and find that most can harbor rDNA and all share pseudo-homolog regions (PHRs). PHR-sharing chromosomes also share closely related centromeric satellites, consistent with a model of ongoing rDNA-facilitated recombinational exchange between heterologous chromosomes. We further identify over 500 marmoset-lineage-specific transcribed genes with previously unknown transcript models or expansions. These resources, along with a preliminary pangenome, improve the utility of the marmoset as a model organism and address gaps in primate genome evolution.},
}

Animals
*Callithrix/genetics
*Genome
Centromere/genetics
Telomere/genetics
Evolution, Molecular
Humans
Female
DNA, Satellite/genetics

@article {pmid42553532,
year = {2026},
author = {Ortiz-Flores, C and Romero-Rodríguez, A and Villanueva-Enríquez, R and Ceapă, CD and Gómez-Rivera, N and Velázquez-Romero, M and Mendoza-Torres, F and Arenas-Hernández, MMP and Martínez de la Peña, C},
title = {Comparative genomic analysis of Clostridioides difficile strains in Mexico: insights into virulence and resistance.},
journal = {Access microbiology},
volume = {8},
number = {7},
pages = {},
pmid = {42553532},
issn = {2516-8290},
abstract = {Clostridioides difficile infection (CDI) remains a major global health threat due to the emergence of hypervirulent, multidrug-resistant lineages. However, the evolutionary dynamics and resistance-associated genomic profiles of strains circulating in underrepresented regions, such as Mexico, remain poorly characterized. Here, we present a comprehensive genomic and phylogenetic analysis of 77 Mexican C. difficile strains compared with 74 strains from other parts of the world. Using whole-genome sequencing and core-genome MLST, we identified 19 sequence types (STs) grouped across 3 clades, with hypervirulent ST01 dominating clade 2. Virulome analysis showed conserved toxin gene profiles (tcdA, tcdB and cdtAB) across strains, while clade-specific differences were observed in adhesion and survival genes. These variations, particularly pronounced in clade 2 strains from both global and Mexican collections, may contribute to enhanced persistence and transmissibility. Pangenome analysis of 151 genomes highlighted distinct genomic architectures. Clade 2, enriched in ST01 epidemic lineages, contained 5,480 genes (58% core, 42% accessory), showing a compact structure consistent with recent clonal expansion. In contrast, clade 1 displayed the highest diversity, with 8,584 genes (30% core, 70% accessory), indicative of an open and dynamic pangenome, while clade 4 showed a smaller, more conserved profile (4,784 genes, 63% core). These findings underscore the contrasting evolutionary strategies among clades. Notably, Mexican ST01 strains exhibited a distinct resistome, including the high prevalence of the vanG operon and the VanR T115A substitution (94% vs. 23% globally), as well as near-complete prevalence of the PnimB[G] mutation associated with reduced metronidazole susceptibility. This pattern may reflect local selective pressures associated with antimicrobial exposure. Phenotypic susceptibility testing of newly sequenced isolates showed that most ST01 strains remained susceptible to metronidazole and vancomycin despite carrying resistance-associated determinants. Our findings highlight the urgent need to recognize hypervirulent and resistant C. difficile lineages arising outside traditional surveillance regions. These Mexican strains not only reflect regional antibiotic usage patterns but also represent a potential reservoir of globally significant resistance traits. This work underscores the importance of integrating genomic surveillance across all continents to refine treatment protocols, prevent outbreaks and contain the spread of resistant CDI.},
}

@article {pmid42553545,
year = {2026},
author = {Wen, H and Bai, Y and Guo, Z and Qian, W and Huang, Y and Liang, Y and Yang, G and Zhang, Y},
title = {Pangenome and Pan-Transcriptome Analysis of the WOX Gene Family Reveals Evolutionary Conservation and Diversification in Alfalfa.},
journal = {Ecology and evolution},
volume = {16},
number = {8},
pages = {e74048},
pmid = {42553545},
issn = {2045-7758},
abstract = {The WUSCHEL-related homeobox (WOX) gene family encodes plant-specific transcription factors that play pivotal roles in meristem maintenance, organogenesis, regeneration, and developmental phase transitions. Despite their importance, the pangenome-scale composition, expansion dynamics, and evolutionary constraints of WOX genes in alfalfa (Medicago sativa) remain poorly understood. Here, we performed an integrated pangenome and pan-transcriptome analysis of the WOX gene family using 24 high-quality alfalfa genomes. A total of 432 WOX genes were identified and clustered into 24 orthologous gene groups (OGGs). Pangenome profiling revealed that the WOX family is highly conserved across alfalfa accessions, with members of the Ancient clade showing greater conservation than those of the Intermediate and WUS clades. Duplication pattern analysis indicated that dispersed duplication was the primary force driving WOX family expansion, whereas whole-genome duplication (WGD) events predominantly contributed to the long-term retention of core and softcore members. Pairwise Ka/Ks analysis indicated strong purifying selection on most WOX gene pairs, whereas wild-germplasm genes and Intermediate-clade members showed elevated selective pressures. Notably, MsWOX9-related homologs had exceptionally high Ka/Ks values, suggesting potential functional divergence linked to agronomically relevant traits. Furthermore, pan-transcriptome analysis revealed that WOX genes could be classified into three distinct expression patterns during leaf senescence. Collectively, this study presents the first comprehensive pangenome- and pan-transcriptome-based characterization of the WOX family in alfalfa, providing new insights into its evolutionary dynamics and expression divergence.},
}

@article {pmid42554460,
year = {2026},
author = {Sun, N and Chen, Y and Wu, X and Gao, D and Zhu, P and Wu, Q and Shi, L and Xia, X},
title = {Comparative genomic characterization and antimicrobial resistance of bacteremia-causing Enterococcus faecium and Enterococcus faecalis in a Chinese hospital.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0061626},
doi = {10.1128/spectrum.00616-26},
pmid = {42554460},
issn = {2165-0497},
abstract = {Enterococci are common commensals of the human gut and important opportunistic pathogens, with Enterococcus faecium and Enterococcus faecalis being the most clinically prevalent species. A significant epidemiological shift has emerged with an increasing clinical burden of E. faecium. To compare genomic evolution of E. faecium and E. faecalis, we performed whole-genome sequencing on 93 E. faecium and 32 E. faecalis isolates causing bloodstream infections at a single hospital (2022-2024). Analysis of patient demographics revealed that E. faecium infections originated from fewer sources than E. faecalis, with a higher proportion deriving from intra-abdominal infections. Multilocus sequence typing identified ST78 and ST789 as the predominant sequence types for E. faecium, whereas ST16 and ST179 were most common for E. faecalis. E. faecium carried more antimicrobial resistance genes and putative virulence marker (PVM)-type virulence genes than E. faecalis, with vancomycin resistance predominantly mediated by vanHAX (33/93, 35.5%) and a single E. faecalis isolate also carrying vanHAX (1/32, 3.1%); the structurally incomplete vanHMX gene cluster was detected in 11 E. faecium isolates. Pan-genome analysis indicated a larger core genome in E. faecalis compared to E. faecium, consistent with greater plasmid replicon diversity in the latter. Intra-host comparisons showed that two E. faecalis pairs from the same patient were clonally related, with one isolate acquiring a vanHAX plasmid conferring vancomycin resistance. In contrast, E. faecium isolates exhibited marked genomic diversity even among clonally related pairs. These findings suggest that E. faecium possesses greater genomic plasticity and adaptive potential to the clinical environment.IMPORTANCEThis study provides a detailed comparison of clinical and genomic features between Enterococcus faecium and Enterococcus faecalis from the same hospital setting. We show that E. faecium isolates, mainly ST78/ST789, carry more antimicrobial resistance genes and a higher number of putative virulence marker (PVM) genes than E. faecalis, reflecting their hospital-adapted nature. E. faecium also exhibits a smaller core genome and greater diversity of plasmid replicon types, indicating higher genomic plasticity and capacity for horizontal gene transfer. By contrast, E. faecalis retains a larger core genome and a set of classical virulence factors, and its within-host isolates are clonally related. These distinct genomic profiles help to understand how the two species adapt to clinical environments and may inform more targeted infection control strategies and resistance surveillance.},
}

@article {pmid42557571,
year = {2026},
author = {Zhang, D and Ding, Y and Kang, W and Zhu, X and Cao, Z and Li, Y and Lai, J and Feng, J and Wang, X and Hou, G and Wang, Y and Li, X and Wang, Y and Liang, X and Hao, L and Zou, P and Li, J and Xiao, R and Wang, H and Pan, C and Wang, Y},
title = {Comprehensive genomic characterization of extraintestinal pathogenic Escherichia coli isolated from neonates: multiple center insights into virulence, resistance, and transmission dynamics.},
journal = {Genome medicine},
volume = {18},
number = {1},
pages = {},
pmid = {42557571},
issn = {1756-994X},
support = {3502Z20227297//Natural Science Foundation of Xiamen, China/ ; specialty in neonatology//Project of Clinical key specialty of Fujian Province/ ; XZYC-2025-08//New Quality Fund of Capital Institute of Pediatrics/ ; 92478116//National Natural Science Foundation of China/ ; 82574169//National Natural Science Foundation of China/ ; 20240484724//Beijing Nova Programme Interdisciplinary Cooperation Project/ ; 7232009//Beijing Natural Science Foundation/ ; Academic leader -03-02//High-level Public Health Technical Personnel Construction Project of the Beijing Municipal Health Commission/ ; },
mesh = {Humans ; Phylogeny ; *Extraintestinal Pathogenic Escherichia coli/genetics/pathogenicity/isolation & purification/drug effects/classification ; *Escherichia coli Infections/microbiology/transmission/epidemiology ; Virulence Factors/genetics ; Infant, Newborn ; Virulence/genetics ; *Genome, Bacterial ; Gene Transfer, Horizontal ; Genomics/methods ; *Drug Resistance, Bacterial/genetics ; Whole Genome Sequencing ; },
abstract = {BACKGROUND: Neonatal extraintestinal pathogenic Escherichia coli (ExPEC), which can cause severe long-term sequelae by systemic infections, is gradually becoming the primary pathogen threatening neonatal health. The lack of large-scale genomic epidemiological investigation hinders further understanding of neonatal ExPEC. We conducted this nationwide multicenter study to support further strategies for improving neonatal ExPEC management.

METHODS: The neonatal ExPEC strains and clinical information, including antimicrobial resistance phenotype, were collected from nine centers within 7 provinces across China between 2018 and 2023. Whole-genome sequencing was performed. Sequence types (ST) and serotypes were acquired to characterize the strains. Phylogenetic analysis and pan-genomic analysis were conducted to identify the population structure. Bioinformatics analysis associated with virulence factors, antimicrobial resistance genes, and mobile genetic elements were conducted. To characterize the situation of horizontal gene transfer, we developed a computational tool for identifying horizontal evolutionary patterns from large-scale genomic draft assemblies. Co-occurrence and co-localization metrics were used to describe the synergistic effects and transmission mechanism of genes.

RESULTS: A total of 411 neonatal ExPEC strains were included. ST1193 (18·0%) was the main ST, while O75 (15·8%) was the most common serotype. Virulence factors and antimicrobial resistance genes were widely distributed across various STs, provinces, years, and isolation sites. Co-occurrence analysis revealed multiple clusters of virulence factors and antimicrobial resistance genes, suggesting co-transmission or co-evolution. Multiple kinds of mobile genetic elements were widely distributed throughout the country. The predicted plasmid-derived contig, genome islands, prophages, and transposons carry different pathogenic genes, respectively. Multiple pathogenic genes exhibited co-occurrence with a specific plasmid replicon, suggesting the critical role of plasmids in the evolution of ExPEC.

CONCLUSIONS: Our findings indicate that neonatal ExPEC had a shared phylogenetic spectrum with adult ExPEC isolates, but distinct dominant subtypes. Multiple virulence factors and drug resistance genes form a complex network that enhances pathogenicity. The formation of these gene clusters is associated with both the inherent genetic factors of ExPEC and the involvement of complex mobile genetic elements. These data accelerate the understanding of neonatal ExPEC, revealing the distribution of STs, serotypes, pathogenic genes, and transmission dynamics.},
}

Humans
Phylogeny
*Extraintestinal Pathogenic Escherichia coli/genetics/pathogenicity/isolation & purification/drug effects/classification
*Escherichia coli Infections/microbiology/transmission/epidemiology
Virulence Factors/genetics
Infant, Newborn
Virulence/genetics
*Genome, Bacterial
Gene Transfer, Horizontal
Genomics/methods
*Drug Resistance, Bacterial/genetics
Whole Genome Sequencing

@article {pmid42560744,
year = {2026},
author = {Xie, J and Liu, T and Zhang, M and Gao, F and Zhao, L and Yan, T and Weng, Z and Yang, Q and Yang, C and Kang, Z and Pu, J and Zheng, H and Shi, Y and Xu, J and Dong, K},
title = {Cutibacterium nasicola sp. nov., isolated from nasal swabs of coal miners.},
journal = {International journal of systematic and evolutionary microbiology},
volume = {76},
number = {8},
pages = {},
doi = {10.1099/ijsem.0.007267},
pmid = {42560744},
issn = {1466-5034},
mesh = {*Phylogeny ; RNA, Ribosomal, 16S/genetics ; Fatty Acids/chemistry ; DNA, Bacterial/genetics ; Bacterial Typing Techniques ; Sequence Analysis, DNA ; Nucleic Acid Hybridization ; Base Composition ; *Coal Mining ; Genome, Bacterial ; *Pasteurellaceae/genetics/classification/isolation & purification ; Phospholipids/chemistry ; *Nose/microbiology ; },
abstract = {Two Gram-stain-positive, catalase-positive, oxidase-negative, non-spore-forming, aerotolerant anaerobic and non-motile short rod-shaped bacterial strains, designated V947[T] and V970, were isolated from nasal swab samples of coal miners. Phylogenetic analyses based on 16S rRNA gene sequences and whole-genome sequences revealed that strains V947[T] and V970 represent a distinct lineage within the genus Cutibacterium, most closely related to Cutibacterium avidum ATCC 25577[T] (16S rRNA gene sequence similarity of 97.09%). Whole-genome comparative analyses showed that the average nucleotide identity values between the two strains and all validly published species of the genus Cutibacterium with correct nomenclature ranged from 76.55 to 90.26%, while the digital DNA-DNA hybridization values ranged from 21.80 to 40.40%, both of which are well below the accepted thresholds for species delineation. Pangenome analysis identified 711 species-specific gene clusters present in strains V947[T] and V970 but absent from all reference type strains of the genus, which were predominantly involved in carbohydrate transport and metabolism, inorganic ion transport and signal transduction mechanisms, suggesting distinct metabolic capabilities and potential for environmental adaptation. These genomic features not only support the delineation of a novel species but also expand the known genomic and functional diversity within the genus Cutibacterium. The predominant cellular fatty acids were iso-C15:0 and anteiso-C15:0. The major polar lipids of strain V947[T] were diphosphatidylglycerol, phosphatidylinositol and phosphatidylcholine, and the predominant menaquinones were MK-8(H4) and MK-9(H6). On the basis of phylogenetic, genomic, chemotaxonomic and phenotypic characteristics, strains V947[T] and V970 represent a novel species of the genus Cutibacterium, for which the name Cutibacterium nasicola sp. nov. is proposed. The type strain is V947[T] (=CGMCC 1.5844[T]=KCTC 59608[T]).},
}

*Phylogeny
RNA, Ribosomal, 16S/genetics
Fatty Acids/chemistry
DNA, Bacterial/genetics
Bacterial Typing Techniques
Sequence Analysis, DNA
Nucleic Acid Hybridization
Base Composition
*Coal Mining
Genome, Bacterial
*Pasteurellaceae/genetics/classification/isolation & purification
Phospholipids/chemistry
*Nose/microbiology

@article {pmid42549057,
year = {2026},
author = {Qi, W and Wang, J and Chang, J and Bu, H and Xiao, J and Zhang, N and Ren, Z},
title = {Pan-genome analysis reveals structural variation- associated expression and evolutionary diversity of the ZmCYP450 gene family in maize.},
journal = {Frontiers in plant science},
volume = {17},
number = {},
pages = {1874015},
pmid = {42549057},
issn = {1664-462X},
abstract = {The plant cytochrome P450 (CYP450) superfamily plays a key role in metabolic diversity and environmental adaptation; however, systematic analyses of its intraspecific structural variation, copy number dynamics, and evolutionary mechanisms remain limited. Using 27 high-quality maize reference genomes, we performed a pan-genomic analysis of the ZmCYP450 family, identifying 282 orthogroups (OGs) and 7,282 genes. The family exhibits a pattern of predominantly conserved genes with localized expansions and open pan-genome properties. PAV and CNV analyses revealed extensive gene deletions and copy number fluctuations outside core OGs, reflecting substantial intraspecific structural diversity. Analysis of duplication types and local colinearity suggested that proximal and dispersed duplications are the primary contributors to drive family expansion. Ka/Ks analysis indicated that most OGs are under purifying selection, while a subset shows evidence of positive selection. Further integration of structural variation and transcriptomic data suggested that SVs may affect gene function through mechanisms such as gene deletion, protein truncation, and remodeling of regulatory elements, suggesting a dual role of potential loss of function and expression modulation. Despite a relatively stable overall copy number, structural variant categories ('Typical', 'Atypical', and 'Missing') are widespread, and expression levels do not always correlate with copy number, suggesting a complex regulatory patterns. Tissue-specificity analysis revealed a large number of highly specific ZmCYP450 genes involved in secondary metabolism and environmental responses, with distinct expression profiles across different genetic backgrounds. This study provides a comprehensive pan-genomic view of structural variation, evolutionary patterns, and expression regulation in the ZmCYP450 family, offering a foundation for future functional studies and maize trait improvement.},
}

@article {pmid42551681,
year = {2026},
author = {Geng, Y and Abideen, MZU and Shaukat, A and Zia, MAB and Raza, QU and Rehim, A and Bashir, MA},
title = {SNP discovery and applications in plant genetics for sustainable food security: A review.},
journal = {International journal of biological macromolecules},
volume = {},
number = {},
pages = {153912},
doi = {10.1016/j.ijbiomac.2026.153912},
pmid = {42551681},
issn = {1879-0003},
abstract = {Single nucleotide polymorphisms represent the most abundant form of genetic variation in plant genomes and have become fundamental markers in modern plant genetics and breeding. Increasing global demand for food, combined with the pressures of climate change, environmental stress, and declining arable land, requires accelerated crop improvement strategies that exceed the capacity of conventional breeding approaches. In this context, SNP-based genomic technologies provide high-resolution tools for analyzing genetic diversity, identifying trait-associated loci, and enhancing selection efficiency in breeding programs. This review provides a comprehensive synthesis of SNP discovery methodologies, tracing their development from early Sanger sequencing approaches to advanced next-generation sequencing technologies, including whole-genome resequencing, genotyping-by-sequencing, and high-density SNP arrays. The article further examines the diverse applications of SNP markers in plant genetics, including genetic diversity analysis, linkage mapping, genome-wide association studies, marker-assisted selection, genomic selection, and evolutionary research. Key analytical and technical challenges, particularly those related to polyploid genome complexity, large-scale genomic data processing, and accurate variant interpretation, are critically discussed. In addition, emerging developments such as graph-based pangenomes, long-read sequencing technologies, machine learning-assisted SNP prioritization, and multi-omics integration are highlighted as promising directions for future research. By integrating recent technological advances with established genomic approaches, this review emphasizes the central role of SNP-based genomics in accelerating crop improvement and enabling climate-resilient, sustainable agricultural systems that support global food security.},
}

@article {pmid42552324,
year = {2026},
author = {Jiang, S and Li, S and Han, S and Li, C and Cao, X and Liu, C and Miao, C and Dong, C and Zhang, Y and Liu, K and Liu, Y and Wang, Q and Wang, HY and Shao, C},
title = {Near telomere-to-telomere genome assembly of the rainbow trout (Oncorhynchus mykiss).},
journal = {Scientific data},
volume = {13},
number = {1},
pages = {},
pmid = {42552324},
issn = {2052-4463},
support = {tsqnz20250759//the Taishan Scholars Program/ ; tstp20221149//the Taishan Scholars Program/ ; NO. 20603022025008//the Central Public-interest Scientific Institution Basal Research Fund, YSFRI, CAFS/ ; 2024YFD2400901//National Key R&D Program of China/ ; 2024YFD2400901//National Key R&D Program of China/ ; 2025CXGC010802//the Key Research and Development Project of Shandong Province/ ; 2024LZGC005//the Key Research and Development Project of Shandong Province/ ; 2017ASTCP-ES06//the AoShan Talents Cultivation Program Supported by Qingdao National Laboratory for Marine Science and Technology/ ; 2024//the Improvement of Aquaculture Seed Industry Program of Yantai/ ; 2023TD19//the Central Public-interest Scientific Institution Basal Research Fund, CAFS/ ; },
mesh = {Animals ; *Oncorhynchus mykiss/genetics ; *Telomere/genetics ; *Genome ; },
abstract = {The rainbow trout (Oncorhynchus mykiss) exhibits extensive karyotypic diversity (2n = 58-64) driven by Robertsonian translocations, yet widely used reference genomes are derived from North American lineages, leaving Chinese aquaculture populations underrepresented. Here, we present a near telomere-to-telomere (T2T) genome assembly of a farmed rainbow trout from China. Integrating PacBio HiFi, ONT ultra-long reads, and Hi-C data, we assembled a 2.29 Gb genome with 99.04% anchored to 30 chromosomes. Notably, the genome contains only 18 gaps, with 16 gap-free chromosomes and 13 achieving T2T status. Comparative synteny analysis revealed a third chromosomal fission/fusion iteration in which Swanson Omy14 splits into Arlee Omy14 and Omy32. Annotation identified 43,137 protein-coding genes, with a BUSCO completeness of 98.9%. This dataset provides a valuable resource for resolving lineage-specific structural variation, supporting pangenome construction and facilitating molecular breeding in rainbow trout.},
}

Animals
*Oncorhynchus mykiss/genetics
*Telomere/genetics
*Genome

@article {pmid42552613,
year = {2026},
author = {Lee, K and Korani, W and Pokhrel, S and Wright, H and Bentz, PC and Ozias-Akins, P and Chu, Y and Harkess, A and Vaughn, J and Clevenger, J},
title = {Long-read low-pass sequencing enhances variant detection in a peanut MAGIC population.},
journal = {G3 (Bethesda, Md.)},
volume = {},
number = {},
pages = {},
doi = {10.1093/g3journal/jkag196},
pmid = {42552613},
issn = {2160-1836},
abstract = {Accurate genotyping accelerates crop improvement, yet long-read sequencing remains underused in breeding due to cost. We present a scalable long-read low-pass (LRLP) sequencing framework for high-throughput variant discovery and trait mapping. Using PacBio HiFi reads in an allotetraploid peanut (Arachis hypogaea; AABB, 2n = 4x = 40) MAGIC population, we generated both LRLP and short-read low-pass (SRLP) data. At comparable depths, LRLP achieved substantially greater whole-genome and gene-space coverage than SRLP. Data were analyzed using both a single-reference genome and an 18-parent pangenome graph constructed with KhufuPan, a new tool for graph-based genotyping. Across analytical approaches, LRLP consistently identified more SNPs, indels (2-1,000 bp), and structural variants (>1 kb) than SRLP, improving genotype resolution and selection accuracy, particularly for large structural variants. By reducing cost barriers and increasing variant discovery in complex genomes, LRLP provides a practical path for deploying advanced genomics in under-resourced and orphan crops critical to global food security.},
}

@article {pmid42553232,
year = {2026},
author = {Thanh, LU and Tan, VN and Huyen, TTN and Phuong, TL and Tam, HN and Loi, LP},
title = {Genomic characterization of Bacillus velezensis BP5 and BP103: insights into biocontrol potential against bacterial leaf spot on pepper.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1757903},
pmid = {42553232},
issn = {1664-302X},
abstract = {Bacillus velezensis strains BP5 and BP103, isolated from pepper rhizosphere soil in the Mekong Delta, Vietnam, displayed potent antagonistic activity against Xanthomonas euvesicatoria, which causes pepper bacterial spot. In dual-culture assays, BP5 formed the largest inhibition zone (36.7 mm), outperforming BP103 (32.1 mm) and oxolinic acid (31.3 mm). Both Gram-positive, rod-shaped strains produced extracellular protease, lipase, amylase, cellulase, and siderophores. Whole-genome sequencing revealed compact and genetically stable genomes: BP5 (4.08 Mb, 46.04% GC, 4,047 protein-coding genes, 5 prophages) and BP103 (3.91 Mb, 46.46% GC, 3,793 genes, 2 prophages). Phylogenetic reconstruction and average nucleotide identity (ANI of more than 98%) confirmed their assignment to B. velezensis, with closest relatedness to strain 160. Orthologous gene analysis across 28 B. velezensis genomes and B. subtilis DSM10 identified 2,593 single-copy genes. Compared to BP103, BP5 harbors greater numbers of multi-copy orthologs, other orthologs, and unique paralogs (388, 910, and 5 in BP5 with 336, 763, and 1 in BP103, respectively). Pangenome analysis showed that the core genome size decreased progressively with the addition of new genomes; BP5 showed more pronounced genetic divergence driven by expanded unique paralogs and shell gene families (with 456 in BP5 compared with 203 in BP103). Both strains encode 13 secondary metabolite biosynthetic gene clusters, including surfactin, fengycin, bacillaene, macrolactin, difficidin, bacilysin, bacillibactin, mersacidin, and locillomycin, plus four previously undescribed terpene/PKS. The CAZyme repertoire was richest in BP5 (133 genes), exceeding BP103 and the commercial strain FZB42 (both 129 genes), thereby enhancing adhesion and adhesion and rhizosphere colonization. These findings establish BP5 and BP103 as highly promising biocontrol agents, combining high genetic stability with diverse secondary metabolite profiles, suitable for development into sustainable microbial bio-bactericides.},
}

@article {pmid42539208,
year = {2026},
author = {Lucas, JK and Hebbar, P and Liao, WW and Macias-Velasco, JF and Novak, AM and Asri, M and Balacco, JR and Blair, AP and Ebler, J and Gardner, JMV and Geleta, M and Groza, C and Guarracino, A and Heringer, P and Hickey, G and Lu, S and Marin, MG and Markovic, C and Mastoras, M and Mayoud, C and McNulty, B and Menendez, JM and Minkina, A and Mohanty, SK and Monlong, J and Munson, KM and Oshima, KK and Porubsky, D and Ranallo-Benavidez, TR and Seligmann, WE and Shemirani, R and Violich, I and Yoo, D and Zhuo, X and Albracht, D and Alexandrov, IA and Allen, J and Alsheikh-Ali, AA and Andrews, C and Antipov, D and Antonacci-Fulton, L and Arguello, A and Ayllon, M and Belter, EA and Bender, HD and Bolognini, D and Bonini, KE and Buonaiuto, S and Cao, S and Cartney, AMM and Chang, PC and Chang, X and Cheema, J and Ciofi, C and Clawson, H and Cody, S and Colonna, V and Conwell, HC and Diekhans, M and Diroma, MA and Dong, Z and Dubocanin, D and Eizenga, JM and Eskandar, P and Ferro, E and Ford, SM and Ford, WW and Frankish, A and Freeberg, MA and Fu, Q and Gao, S and Gao, Y and Garcia, GH and Garcia, OA and Garza, JE and Ghorbani, M and Graves-Lindsay, TA and Gu, B and Haggerty, L and Hansen, NF and Hao, Y and Hillaker, TL and Hossain, SN and Huang, N and Hunt, SE and Hunt, T and Jafarzadeh, N and Jain, N and Jehangir, M and Jiang, J and Kim, J and Koo, B and Kremitzki, M and Li, D and Li, R and Lin, J and Liu, T and Lorig-Roach, R and Loucks, H and Loveland, JE and Lu, J and Ma, W and Marsico, FL and Medico, JA and Mokrab, Y and Moosa, S and Moreno-Ochando, A and Morishita, S and Mudge, JM and Mwaniki, N and Nassir, N and Natali, C and Negi, S and Ni, L and Okamoto, F and Owa, C and Paez, S and Peano, C and Pickett, BD and Pignata, L and Prodanov, T and Radhakrishnan, A and Raney, BJ and Raveane, A and Rechtsteiner, A and Ren, L and Rhie, A and Ryabov, F and Sacco, S and Salehi, F and Sehgal, A and Shabani, M and Shahatit, S and Shivakumar, VS and Sinha, S and Smeds, L and Solar, SJ and Sollitto, M and Soranzo, N and Suner, MM and Suzuki, Y and Soylev, A and Tierney, JAS and Tomlinson, C and Tricomi, FF and Ungaro, MT and Varki, R and Walenz, BP and Wang, C and Wang, LE and Wenger, AM and Whelan, CV and Xin, Z and Xu, Z and Zhang, W and Zhou, Y and Zunino, G and Altemose, N and Barthel, FP and Boucher, C and Bourque, G and Carroll, A and Cechova, M and Chaisson, MJP and Cheng, H and Cook-Deegan, R and Doerr, D and Durbin, R and Fiston-Lavier, AS and Formenti, G and Fullerton, SM and Fulton, RS and Garg, S and Garrison, NA and Green, RE and Greider, CW and Gymrek, M and Haeussler, M and Hashmi, MA and Haussler, D and Ioannidis, AG and Koren, S and Langley, CH and Langmead, B and Lawson, HA and Logsdon, GA and Makova, KD and Martin, FJ and Mitchell, MW and Ossorio, PN and Pisanti, N and Prins, P and Rautiainen, M and Schatz, MC and Scheinfeldt, LB and Shafin, K and Siren, J and Stergachis, AB and Abou Tayoun, A and Uddin, M and Villani, F and Vollger, MR and Ye, K and Eichler, EE and Garrison, E and Hall, IM and Jarvis, ED and Kenny, EE and Li, H and LoTempio, J and Marschall, T and Miga, KH and Phillippy, AM and Wang, T and Paten, B},
title = {HPRC2: A human pangenome reference with near-complete coverage of common genetic variation.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.07.21.739710},
pmid = {42539208},
issn = {2692-8205},
abstract = {A pangenome reference overcomes the inherent limitation of any individual reference genome by integrating the variation present in a population. We present the Human Pangenome Reference Consortium's (HPRC) Release 2 (HPRC2), an openly available, second phase pangenome that is an approximately fivefold expansion in genome number over HPRC Release 1 (HPRC1) and measurable improvement in genome completeness, contiguity, and accuracy. Selecting samples with a principled algorithm prioritising common variant coverage, HPRC2 contributes 460 haplotypes that together capture over 99% of common variation observed in the All of Us Research Program v8 cohort. Combining high-coverage long and ultra-long reads with modern assemblers and polishers, we produce thousands of telomere-to-telomere (T2T) chromosomes, and relative to HPRC1 halve the number of structurally unreliable regions as well as individual base errors per haplotype. We complement the assemblies with whole genome multiple alignments and gene annotations, and derive formal pangenome coordinate systems for addressing off-reference variation, demonstrating that individual human genomes contain more than one hundred thousand variants not succinctly described with respect to existing reference genomes. We also present the first matched long-read backed pantranscriptome and panepigenome at this scale, provide continuous local-ancestry estimates spanning every genome, and outline a host of new tools and applications that leverage the pangenome resource for improved genomics analysis.},
}

@article {pmid42539257,
year = {2026},
author = {Cohen, ZP and Perkin, L and Frandsen, PB and DeGiorgio, M and Assis, R},
title = {Bacterial DNA invasion triggers transposable element proliferation and genome expansion.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.07.14.738529},
pmid = {42539257},
issn = {2692-8205},
abstract = {Genome size variation in eukaryotes is driven largely by transposable elements (TEs), yet the biological mechanisms that initiate their proliferation remain understudied. Here, we identify a recurrent association between bacterial horizontal gene transfer (HGT) and bursts of TE activity that contribute to genome expansion. By leveraging comparative genomics and genus-level pangenome analyses across three species of the nut weevil, Curculio , we detect extensive bacterially derived DNA sequences embedded within structurally dynamic genomic regions. These HGT-associated regions are dominated by a small number of young, proliferating TE families, particularly DNA type II Mavericks, which encapsulate transferred bacterial sequences and comprise a substantial fraction of recent genomic DNA in derived lineages. Analyses of codon usage bias, intron length, and functional enrichment suggest that most transferred genes undergo progressive pseudogenization over evolutionary time, whereas a subset of selectively advantageous HGTs persist. Together, our findings support a model linking foreign DNA invasion with TE proliferation, genome size variation, and molecular innovation.},
}

@article {pmid42542337,
year = {2026},
author = {Rosenbaum, SW and Escalona, M and May, SA and Whiteley, AR},
title = {A Mid-Atlantic Brook Trout (Salvelinus fontinalis) genome to advance conservation and comparative genomics.},
journal = {G3 (Bethesda, Md.)},
volume = {},
number = {},
pages = {},
doi = {10.1093/g3journal/jkag209},
pmid = {42542337},
issn = {2160-1836},
abstract = {Brook Trout (Salvelinus fontinalis) are experiencing genomic erosion and demographic declines across the southern portion of their native distribution. A regionally representative reference genome is necessary to support conservation genomic initiatives for this species. While Brook Trout exhibit substantial phylogenetic structure across their range, only a single reference genome from Northeastern Canada (ASM2944872v1) is currently used to guide range-wide analyses. Consequently, reference bias is expected to cause erroneous sequence alignment and spurious variant detection for Brook Trout from divergent lineages. To prevent reference bias and invalid inference when studying Mid-Atlantic Brook Trout, we assembled a de novo, chromosome-level genome using a wild individual from Virginia, USA and produced a gene annotation with publicly available RNA-seq data. The assembly combined three complementary sequencing types (PacBio HiFi, Oxford Nanopore Ultra-Long, and Dovetail Omni-C) and benefited from manual curation using the Pretext software suite. The 2.91 Gb genome, known as mSalvFont1.0, consists of 3,333 contigs (N50 = 3.3 Mb) and 1,299 scaffolds (N50 = 55 Mb), with 81% of the assembly contained within 42 chromosome-scale scaffolds. Indices of accuracy and completeness reveal a quality value of 59 (99.999% accuracy), k-mer completeness of 95%, and 99.3% complete BUSCOs from the Actinopterygii orthologous gene set. Additionally, we identified reference bias (26.94% heterozygosity inflation) when variant detection of a Mid-Atlantic-origin sample relied on alignment to ASM2944872v1, instead of mSalvFont1.0. We anticipate that mSalvFont1.0 will increase the accuracy and precision of regional conservation genomic initiatives and expedite the genesis of a Brook Trout pangenome.},
}

@article {pmid42539198,
year = {2026},
author = {Shen, J and Fu, Q and Macias-Velasco, JF and Li, D and Wang, T},
title = {Pansoma, a machine learning tool for identifying somatic variants using pangenome graphs.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.05.27.726245},
pmid = {42539198},
issn = {2692-8205},
abstract = {Somatic variant calling, the identification of mutations in non-germline cells acquired over an individual's lifetime, is critical for studying diseases, including cancer, and for developing precision oncology strategies. Traditional somatic variant calling methods rely on linear reference genomes, which do not adequately capture human genetic diversity and result in reference bias, compromising the accuracy of somatic variant detection. Recently developed graph-based human pangenome reference represents diverse genetic variants across human populations and has promised to drive advances in many genetics and genomics studies. In this study, we introduced Pansoma, a novel pangenome-native and machine learning-based tool specifically designed for somatic variant calling using a pangenome graph reference. Pansoma performs somatic variant detection from both short- and long-read sequencing data by learning tensor representations of alignment on graph nodes rather than on a linear reference. Pansoma outputs variant representations anchored to the pangenome graph paths and conventional somatic variant calls remapped to the linear reference. Additionally, we provide accompanying bioinformatics tools tailored for graph-based genomic data management and variant calling results analysis. Benchmarking shows that Pansoma not only improves tumor-only somatic variant detection but also preserves graph-specific variant representations that are not directly recoverable from linear- reference outputs.},
}

@article {pmid42528375,
year = {2026},
author = {Meng, F and Li, R and Yu, Y and Zhang, X and Dai, W and Cui, X and Sun, L and Lang, F and Yang, L and Cheng, Z},
title = {Cross-host transmission of Riemerella anatipestifer to chickens: Genomic evolution and identification of the novel vapX-like-vapD toxin-antitoxin system.},
journal = {Virulence},
volume = {17},
number = {1},
pages = {2711521},
doi = {10.1080/21505594.2026.2711521},
pmid = {42528375},
issn = {2150-5608},
mesh = {Animals ; *Riemerella/genetics/pathogenicity/classification ; *Chickens/microbiology ; *Flavobacteriaceae Infections/transmission/veterinary/microbiology ; *Poultry Diseases/microbiology/transmission ; Phylogeny ; Ducks/microbiology ; Virulence/genetics ; *Toxin-Antitoxin Systems/genetics ; *Evolution, Molecular ; Genome, Bacterial ; Polymorphism, Single Nucleotide ; Drug Resistance, Multiple, Bacterial/genetics ; Bacterial Proteins/genetics ; Genomics ; Virulence Factors/genetics ; },
abstract = {Riemerella anatipestifer (R. anatipestifer), a well-known waterfowl pathogen, increasingly threatens Chinese poultry by spreading to chickens. The genetic differentiation and host adaptation following cross-host transmission remain unclear. Here, we characterized a highly virulent, multidrug-resistant chicken-source strain (SDAU-RA1) and performed comparative genomics with global R. anatipestifer strains to elucidate population structure and evolutionary dynamics. SNP phylogeny revealed significant geographic clustering and dominant clonal groups. Strains from different hosts showed a pattern of "overall mixing with local clustering," and ancestral state reconstruction (ASR) identified multiple independent duck-to-chicken spillover events, confirming cross-host transmission rather than strict host-specific evolution. In terms of virulence, certain virulence genes are enriched specifically in chicken-source strains. Notably, the study is the first to identify and confirm vapX-like-vapD as a functional type II toxin-antitoxin system in chicken-source R. anatipestifer, demonstrating that it enhances biofilm formation, intracellular survival, and antibiotic persistence. Analysis of the geographical distribution and temporal dynamics of antibiotic resistance genes (ARGs) reveals high heterogeneity among R. anatipestifer strains from different hosts. Pangenome analysis revealed that R. anatipestifer possesses an open pangenome, conferring high genetic plasticity. In conclusion, our study shows R. anatipestifer transmits to chickens without strict host-specific adaptation, though incipient genetic differentiation has emerged. The discovery of plasmid pRASD and its carried vapX-like-vapD system suggests key mechanisms for the adaptive evolution and enhanced pathogenicity of R. anatipestifer. These findings enhance our understanding of cross-host transmission and underscore the importance of continuous surveillance of chicken-source R. anatipestifer and its novel mobile genetic elements.},
}

Animals
*Riemerella/genetics/pathogenicity/classification
*Chickens/microbiology
*Flavobacteriaceae Infections/transmission/veterinary/microbiology
*Poultry Diseases/microbiology/transmission
Phylogeny
Ducks/microbiology
Virulence/genetics
*Toxin-Antitoxin Systems/genetics
*Evolution, Molecular
Genome, Bacterial
Polymorphism, Single Nucleotide
Drug Resistance, Multiple, Bacterial/genetics
Bacterial Proteins/genetics
Genomics
Virulence Factors/genetics

@article {pmid42530976,
year = {2026},
author = {Xiao, C and Jiang, S and Guo, Z and Ho, PL and Dai, J and Cao, H and Yang, Z},
title = {Integrating genomic and transcriptomic analyses reveals virulence factors and bloodstream infection mechanisms of Acinetobacter junii.},
journal = {Microbial genomics},
volume = {12},
number = {7},
pages = {},
doi = {10.1099/mgen.0.001749},
pmid = {42530976},
issn = {2057-5858},
mesh = {*Virulence Factors/genetics ; *Acinetobacter/genetics/pathogenicity/classification/drug effects/isolation & purification ; Humans ; Genome, Bacterial ; *Acinetobacter Infections/microbiology ; Genome-Wide Association Study ; Gene Expression Profiling ; Genomics ; Virulence/genetics ; Plasmids/genetics ; *Bacteremia/microbiology ; },
abstract = {Acinetobacter junii, an emerging pathogen of the Acinetobacter genus, exhibits concerning environmental persistence and clinical virulence potential. Despite its growing significance in bloodstream infections (BSIs), the genetic determinants distinguishing pathogenic from environmental strains remain poorly characterized, limiting our understanding of its transmission dynamics and host adaptation mechanisms. We explored the diversity and population structure of A. junii using a comprehensive genome dataset, including four strains isolated from China, one of which (acj0210) was derived from BSIs. We analysed the pangenome of A. junii and characterized its virulence and antibiotic resistance profile. Bacterial genome-wide association studies (bGWAS) were performed to identify the virulence potential. The virulence potential for BSIs was further investigated through RNA-seq analysis under different conditions. Additionally, transmission dynamics of bla NDM-carrying plasmids in carbapenem-resistant A. junii were inferred from plasmid network analysis. We identified seven lineages within A. junii, with BAPS1 as the dominant group. Discrepancies in accessory genes were observed between lineages, along with unique genes, particularly one novel capsular polysaccharide variant in acj0210. Using bGWAS, we uncovered key genetic differences, including transporter-encoding genes (tauA, urtD), regulatory mutations and exopolysaccharide-encoding genes that distinguish human and environmental strains. Transcriptomic analysis revealed potential virulence factors in BSIs, with distinct gene expression patterns between blood and immune cells, despite shared fatty acid metabolism profiles. As critical resistance determinants, bla NDM genes may have been acquired from A. baumannii. A. junii has adapted to diverse geographical and ecological niches, particularly in BSIs, with lineage-specific virulence factors aligned with antibiotic resistance genes, especially those carried by bla NDM harbouring plasmids.},
}

*Virulence Factors/genetics
*Acinetobacter/genetics/pathogenicity/classification/drug effects/isolation & purification
Humans
Genome, Bacterial
*Acinetobacter Infections/microbiology
Genome-Wide Association Study
Gene Expression Profiling
Genomics
Virulence/genetics
Plasmids/genetics
*Bacteremia/microbiology

@article {pmid42536082,
year = {2026},
author = {Balogun, IO and Mancuso, CP and Lieberman, TD},
title = {High-precision binary trait association on phylogenetic trees.},
journal = {Microbial genomics},
volume = {12},
number = {7},
pages = {},
pmid = {42536082},
issn = {2057-5858},
mesh = {*Phylogeny ; *Genome-Wide Association Study/methods ; Escherichia coli/genetics/virology ; Genome, Bacterial ; Computer Simulation ; Epistasis, Genetic ; },
abstract = {Traditional methods for identifying associations between genomic features and traits, or between pairs of genomic traits, struggle when applied to bacterial genomes. While several microbial genome-wide association study (mGWAS) methods have been developed to account for the fact that genome-wide linkage in bacteria creates strong evolutionary-induced associations, these methods have high false discovery rates or lack statistical power, have poor performance on negative interactions and face computational limits at the scale required for pangenome-wide study of gene-gene interactions. Here, we present Simulation-based Phylogenetic iNteraction Inference (SimPhyNI), a computationally optimized framework for efficient and rigorous mGWAS studies. SimPhyNI builds null co-occurrence distributions by independently simulating traits using phylogenetically informed parameters, novelly including time to first event. The constrained variation in these simulations, combined with log odds ratio scoring for comparing across traits, robustly identifies both positive and negative associations. Using synthetic datasets mimicking both gene-gene and gene-trait associations, we demonstrate that SimPhyNI achieves high precision and recall for both positive and negative interactions. We demonstrate SimPhyNI's utility by detecting interactions between phage defence systems in Escherichia coli and gene-gene interactions across the entire E. coli pangenome (>9 million tests). Though developed here for binary traits, SimPhyNI's design supports extension to multi-state and continuous traits using generalized models of stochastic simulation. SimPhyNI's performance and scalability enable genome-wide discovery of genetic interactions that drive microbial function, ecology and disease.},
}

*Phylogeny
*Genome-Wide Association Study/methods
Escherichia coli/genetics/virology
Genome, Bacterial
Computer Simulation
Epistasis, Genetic

@article {pmid42539132,
year = {2026},
author = {Megalovasilis, G and Bochalis, E and Chartoumpekis, D and Vasquez, K and Georgakopoulos-Soares, I},
title = {Z-DNA-induced genomic instability in the human pangenome.},
journal = {Research square},
volume = {},
number = {},
pages = {},
doi = {10.21203/rs.3.rs-10129918/v1},
pmid = {42539132},
issn = {2693-5015},
abstract = {Z-DNA is a non-canonical, left-handed nucleic acid conformation with roles in gene regulation, genomic variation, and genome instability. Recent advances in long-read sequencing enable systematic interrogation of Z-DNA in repetitive and previously unresolved parts of the human genome. Leveraging the complete telomere-to-telomere reference human genome and 464 haplotype-resolved genome assemblies from individuals of multiple ethnicities, we systematically mapped Z-DNA-forming sequences and investigated their genomic and mutational landscape. We show that Z-DNA density is highly constrained across human haplotypes and superpopulations, with substantial enrichment in repetitive regions absent or unresolved in GRCh38, including centromeric, pericentromeric, and acrocentric loci. By analyzing more than 52 million variants across multiple mutation categories in the human pangenome, we show that Z-DNA loci are strongly enriched for mutational events not explained by sequence composition alone. The strongest associations were observed for small insertions, deletions, and complex structural variants. Finally, we replicated our findings using more than 250,000 de novo mutations. Together, these findings establish Z-DNA as a functional element of the human genome, with important implications for genome instability and human disease.},
}

@article {pmid42527688,
year = {2026},
author = {Nguyen, CTK and Dinh, HT and Dang, DQB and Le, HH and Nguyen, HD},
title = {Genomic and pan-genomic analyses of Bacillus subtilis B13 provide insights into biosynthetic potential and genetic traits associated with environmental adaptation.},
journal = {Antonie van Leeuwenhoek},
volume = {119},
number = {8},
pages = {},
pmid = {42527688},
issn = {1572-9699},
mesh = {*Bacillus subtilis/genetics/metabolism/classification/physiology ; *Genome, Bacterial ; Multigene Family ; *Adaptation, Physiological/genetics ; Genomics ; Anti-Bacterial Agents/biosynthesis ; Bacteriocins/biosynthesis ; Lipopeptides/biosynthesis ; Phylogeny ; Base Composition ; Dipeptides ; Oligopeptides ; Polyenes ; },
abstract = {This study describes the genomic features of Bacillus subtilis B13 (= VTCC 910231) to elucidate the genetic basis underlying its reported antimicrobial activity, metabolic versatility, and environmental adaptability. The draft genome comprised 4,349,051 bp with a GC content of 43.5% and 4436 predicted coding sequences. Genome-based analyses assigned B13 to B. subtilis subsp. subtilis, supported by high average nucleotide identity (98.3%) and digital DNA-DNA hybridization (99.7-99.8%) values. Genome mining identified one gene cluster encoding an unidentified sactipeptide along with seven biosynthetic clusters involved in the production of compounds with potential antibacterial activity, including fengycin, surfactin, bacillaene, bacillibactin, bacilysin, subtilosin A, and sporulation-killing factor. These clusters may contribute to its observed bioactive properties. Comparative pan-genome analysis suggested an open genomic architecture dominated by accessory genes, with B13 harboring 67 unique gene clusters at the species level and 336 strain-specific gene clusters in a niche-focused dataset, most of which remain functionally uncharacterised. The annotated genes are associated with environmental adaptation. The genome revealed mobile elements, indicating genome plasticity and potential horizontal gene transfer, but no plasmids were detected. Three high-confidence genomic islands (251 kb, 5.8% of the genome) contained mobility-related genes but lacked a virulence gene cluster and antibiotic resistance genes. Functional profiling explored a collection of genes associated with stress response, signal transduction, transport, motility, chemotaxis, and DNA repair. These findings provide insights into genomic features related to the biosynthetic potential, genomic plasticity, and safety profile of B13, and suggest putative determinants of environmental adaptation, while reflecting pan-genome diversity in strain-specific traits.},
}

*Bacillus subtilis/genetics/metabolism/classification/physiology
*Genome, Bacterial
Multigene Family
*Adaptation, Physiological/genetics
Genomics
Anti-Bacterial Agents/biosynthesis
Bacteriocins/biosynthesis
Lipopeptides/biosynthesis
Phylogeny
Base Composition
Dipeptides
Oligopeptides
Polyenes

@article {pmid42525349,
year = {2026},
author = {Dos Reis, JBA},
title = {Functional diversity and ecological consequences of endophytic Bacillus-plant interactions.},
journal = {Folia microbiologica},
volume = {},
number = {},
pages = {},
pmid = {42525349},
issn = {1874-9356},
abstract = {The genus Bacillus, particularly endophytic species, has been widely studied as a source of plant growth-promoting bacteria in agricultural systems. These microorganisms contribute to plant performance through nutrient acquisition, phytohormone production, pathogen suppression, microbiome modulation, and enhanced tolerance to biotic and abiotic stresses. However, their ecological roles, functional plasticity, and genomic diversity remain poorly integrated into conceptual frameworks that extend beyond crop-based applications. Functional plasticity is reflected in their ability to colonize diverse plant hosts and tissues and to promote similar plant responses through distinct molecular mechanisms. Likewise, genomic diversity is evidenced by variation in accessory genomes, biosynthetic gene clusters, and regulatory networks that shape ecological functions and metabolite production. This review examines endophytic Bacillus as a model for understanding how metabolically versatile and genomically plastic bacteria establish functional, but context-dependent, associations with plants. Drawing on evidence from functional genomics, pangenomics, metabolomics, and microbial ecology, we discuss mechanisms associated with plant growth promotion and emphasize their dependence on host identity, environmental conditions, and microbial interactions. We address functional convergence arising from distinct genetic and metabolic routes, the contribution of accessory genomes and regulatory variation, and the ecological consequences of microbial inoculation in resident plant-associated microbiomes. We also highlight the limitations of in vitro screening approaches and the need for experimental validation across multiple biological scales to establish robust genotype-phenotype relationships. Finally, we extend the discussion beyond agricultural systems to consider the use of endophytic Bacillus in wild plant systems and ecological restoration, emphasizing the importance of evaluating both functional outcomes and ecological impacts.},
}

@article {pmid42527608,
year = {2026},
author = {Gao, S and Oshima, KK and Chuang, SC and Loftus, M and Potapova, TA and Montanari, A and Gordon, DS and Yang, Z and , and , and Mao, Y and Hsieh, P and Gerton, JL and Konkel, MK and Ventura, M and Logsdon, GA},
title = {A global view of human centromere variation and evolution.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {42527608},
issn = {1476-4687},
abstract = {Centromeres are essential chromosomal regions that ensure accurate chromosome segregation during cell division, yet their highly repetitive sequence has historically hindered their complete assembly and characterization[1]. Consequently, the full spectrum of centromere diversity across individuals, populations and evolutionary contexts remains largely unexplored. Here we address this gap in knowledge by assembling and characterizing 2,110 centromeres from diverse individuals representing 5 continental and 28 population groups. Using bioinformatic tools tailored for centromeres, we identify variation, including 226 centromere haplotypes and 1,870 α-satellite higher-order repeat variants. While most centromeres have a single kinetochore site, we find that around 6% have di-kinetochores, and less than 1% have tri-kinetochores, which we confirm using long-read chromatin profiling and multigenerational inheritance. We also show that kinetochore position is closely associated with the underlying sequence and structure of the centromere. To understand the nature of evolutionary change, we compared these centromeres to 5,747 centromeres assembled by the Human Pangenome Reference Consortium. We show that centromeres have a 20-fold variation in mutation rate, and a subset of centromeres has evidence of archaic hominin introgression. We validate these mutation rates in a 4-generation, 28-member family and show that the kinetochore site is the most rapidly mutating region in the centromere. We propose a model that reveals an 'arms race' between centromeric sequence and proteins, with frequent mutations within the kinetochore site that lead to changes in genetic and epigenetic landscapes and, ultimately, rapid evolution of these critically important regions.},
}

@article {pmid42511554,
year = {2026},
author = {Marino, A and Stracquadanio, S and Cosentino, F and Coco, M and La Via, L and Franzò, A and Spampinato, S and Venanzi Rullo, E and Maniaci, A and Nunnari, G},
title = {Beyond the Usual Suspects: Emerging Pseudomonas Species in Clinical and Environmental Niches.},
journal = {International journal of molecular sciences},
volume = {27},
number = {14},
pages = {},
pmid = {42511554},
issn = {1422-0067},
mesh = {Humans ; *Pseudomonas/genetics/classification/pathogenicity ; *Pseudomonas Infections/microbiology/epidemiology ; Genome, Bacterial ; Gene Transfer, Horizontal ; Virulence Factors/genetics ; *Environmental Microbiology ; Virulence ; Multilocus Sequence Typing ; },
abstract = {Non-aeruginosa Pseudomonas (NAP) species represent a diverse and ubiquitous group of Gram-negative bacteria inhabiting a wide range of environmental niches, from soil and water to plant rhizospheres and clinical settings. While Pseudomonas aeruginosa has historically dominated clinical and research focus, the significance of NAP species, such as Pseudomonas fluorescens, Pseudomonas putida, and Pseudomonas stutzeri, as both opportunistic human pathogens and versatile biotechnological agents is increasingly recognized. Their remarkable genomic plasticity, driven by large accessory genomes and mobile genetic elements, underpins their metabolic versatility and adaptability but also facilitates the acquisition of virulence determinants and antibiotic resistance genes, contributing to their emergence in healthcare settings, particularly among immunocompromised individuals. This review provides a comprehensive analysis of NAP species, focusing on recent advances in their taxonomy facilitated by genomic tools like Whole-Genome Sequencing (WGS) and Multilocus Sequence Typing (MLST), which reveal complex species groups and challenge traditional classifications. We delve into the genomic landscape, exploring pangenome dynamics, horizontal gene transfer (HGT), and the genomic signatures that may differentiate clinical from environmental isolates. The clinical relevance of NAPs is examined, detailing the spectrum of infections, epidemiological trends, risk factors, and insights into virulence mechanisms, including secretion systems (T3SS, T6SS) and pathogenicity islands. Addressing a critical need, this review incorporates detailed sections on the diagnostic challenges posed by NAPs, including common misidentifications and the role of modern techniques like MALDI-TOF MS and WGS, and outlines current and novel therapeutic strategies, considering the growing problem of antimicrobial resistance (AMR) within this group. Furthermore, the biotechnological applications of NAPs in bioremediation and biocatalysis are discussed alongside evolving biosafety considerations, reflecting the shift from strict containment to integrated monitoring approaches for genetically engineered strains. By synthesizing current knowledge and highlighting research gaps, this review underscores the necessity of integrated, One Health approaches to understand and manage the dual nature of non-aeruginosa Pseudomonas species as both environmental inhabitants and clinically relevant pathogens.},
}

Humans
*Pseudomonas/genetics/classification/pathogenicity
*Pseudomonas Infections/microbiology/epidemiology
Genome, Bacterial
Gene Transfer, Horizontal
Virulence Factors/genetics
*Environmental Microbiology
Virulence
Multilocus Sequence Typing

@article {pmid42513931,
year = {2026},
author = {Qiao, Y and Zhang, X and Jing, R and Du, J and Liu, Y and Zhou, Y and Zhang, D and Zhou, X},
title = {Molecular Epidemiology, Phenotypic and Genomic Characterization of Multidrug-Resistant Enterococcus Faecium Isolated from Bovine Mastitis in Ningxia, China (2019-2024).},
journal = {Microorganisms},
volume = {14},
number = {7},
pages = {},
doi = {10.3390/microorganisms14071424},
pmid = {42513931},
issn = {2076-2607},
support = {2024AAC02028//the Natural Science Foundation Project of Ningxia Hui Autonomous Region/ ; 32460902//National Natural Science Foundation of China/ ; 2021GKLRLX10//Cultivation Project for Leading Talents in Science and Technology Innovation of Ningxia Hui Autonomous Region/ ; },
abstract = {Multidrug-resistant (MDR) Enterococcus faecium is an opportunistic pathogen. Its resistance and virulence genes can spread through the food chain, posing risks to public health. This study investigated the antimicrobial resistance and genomic characteristics of MDR E. faecium isolated from milk samples from cows with mastitis in Ningxia between 2019 and 2024. From 2019 to 2024, 1341 milk samples were collected in Yinchuan, Yinnan, and Yinbei. MDR E. faecium was identified using plate screening, mass spectrometry, broth microdilution, and hemolysis detection. Whole-genome sequencing enabled SNP, MLST, pan-genome, and COG analyses, focusing on ARGs and MGEs. MRPP, AMOVA and PCoA were applied to compare gene communities and identify driver genes. Ninety-one E. faecium strains were isolated. Resistance to florfenicol, ceftiofur, and chloramphenicol exceeded 60%, while resistance to vancomycin and linezolid showed an overall increasing trend over the study period. Phylogenetic clustering revealed two subtypes, three clades, and 10 novel STs. Spearman correlation analysis revealed strong positive correlations among the resistance genes optrA, cfr(A), and vanF. Antibiotic resistance, particularly MDR, increased over time, and strains carried diverse ARGs and MGEs. Overall, strengthened surveillance of mastitis-derived E. faecium is warranted to support the control of bovine mastitis and safeguard public health.},
}

@article {pmid42516972,
year = {2026},
author = {Shapovalova, VV and Shaidullina, ER and Ivanchik, NV and Chebotar, IV and Mikotina, AV and Chagaryan, AN and Skleenova, EY and Azizov, IS and Romanov, AV and Dekhnich, AV and Kozlov, RS and Edelstein, MV},
title = {Genomic phylogeny, taxonomic classification, genetic landscape, and antibiotic resistance of clinical Stenotrophomonas isolates.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1854839},
pmid = {42516972},
issn = {1664-302X},
abstract = {BACKGROUND: Stenotrophomonas spp. are increasingly recognized opportunistic pathogens characterized by intrinsic multidrug resistance. Despite recent taxonomic reclassification and the delineation of new species within the S. maltophilia complex (Smc), routine diagnostics often misidentify these species, and their distinctive antibiotic resistance traits and genetic makeup remain underexplored. We aimed to characterize the phylogenomic diversity, genotypic and phenotypic antibiotic resistance traits, virulence markers and horizontally transferrable elements in a large national cohort of clinical Stenotrophomonas isolates.

METHODS: We analyzed 323 clinical isolates from the Russian sentinel surveillance program (2002-2021). Analysis included MALDI-TOF MS identification, broth microdilution susceptibility testing to six agents [aztreonam-avibactam, colistin, levofloxacin, minocycline, tigecycline, and trimethoprim-sulfamethoxazole (TMP-SMX)], and long-read Nanopore WGS with hybrid polishing. We performed average nucleotide identity (ANI)-based classification, core- and accessory-genome comparisons, and comprehensive profiling of antibiotic resistance genes (ARGs), virulence factors (VFs), plasmids, and prophages.

RESULTS: While MALDI-TOF MS identified all isolates as S. maltophilia, ANI (≥95% threshold) and core-genome phylogeny revealed 17 distinct species: 52% S. maltophilia sensu stricto, 36.8% across eight other ICNP-named Smc species, and 11.2% within eight "novel" genomic lineages identified elsewhere. Pan-genome comprised 24,815 genes (9.6% core genes), with accessory genes showing robust species-level clustering in UMAP. TMP-SMX resistance was prevalent (40.2%) among all species, though only 13.1% of resistant isolates harbored sul genes. Intrinsic β-lactamase genes (bla L1- and bla L2-like) were ubiquitous but exhibited high sequence variability (up to 20.6% and 25.1%) and evidence of inter-species exchange. Phosphoethanolamine transferase genes (mcr-5- and mcr-8-like) were identified as intrinsic chromosomal components. Acquired ARGs were primarily associated with chromosomal integrative conjugative and mobilizable elements (ICEs/IMEs). Plasmids (2.5 to >334 kb) were identified in 8% of isolates across 10 species, including a cluster of eight nearly identical replicons distributed among five species despite lacking canonical mobilization genes. Prophages were ubiquitous (median: 4 per genome), dominated by Caudoviricetes and Inoviridae. Several VFs linked to motility, capsule formation, and invasion/toxicity were universally present across the genus.

CONCLUSION: Our findings demonstrate that current routine diagnostics fail to resolve the significant taxonomic diversity within clinical Stenotrophomonas isolates, leading to widespread species misidentification. Integrating the genomic and phenotypic insights from this study into routine surveillance is essential to overcome these diagnostic limitations and to modernize the clinical management of infections caused by this formidable genus.},
}

@article {pmid42523175,
year = {2026},
author = {Pani, S and Dabbaghie, F and Marschall, T and Söylev, A},
title = {gaftools: a toolkit for analyzing and manipulating pangenome alignments.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btag406},
pmid = {42523175},
issn = {1367-4811},
abstract = {MOTIVATION: Linear reference genomes are ubiquitously used in genomics research, despite known biases associated with their use. In recent years, there has been a shift towards graph-based reference genomes to address some of these biases, which has required development of new algorithms and file formats. This has created a necessity for new tools capable of utilizing these formats and performing operations similar to those carried out by traditional methods.

RESULTS: In this paper we present "gaftools", a multi-purpose tool that introduces several utilities for processing graph alignments in GAF format. Gaftools enables users to index and sort alignments, with graph ordering serving as a necessary step for the sorting process. Additionally, it allows users to view subsets of alignments and perform realignment using the wavefront alignment algorithm, among other features. Many of these functionalities are inspired by SAMtools, which provides similar operations for linear genomes, while gaftools adapts and extends them for pangenomes.

AVAILABILITY: gaftools is available under MIT license at https://github.com/marschall-lab/gaftools.},
}

@article {pmid42523307,
year = {2026},
author = {Smith, OER and Clemente, CM and Andreeva, A and Wang, Z and Weimann, A and Dinan, A and Houghton-Flory, C and Tarafder, AK and Böhning, J and O'Toole, GA and Floto, RA and Mobarec, JC and Bateman, A and Bharat, TAM},
title = {Structural basis of biofilm formation mediated by the Pseudomonas aeruginosa fibrillar adhesin CdrA.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.07.13.738186},
pmid = {42523307},
issn = {2692-8205},
abstract = {Many bacteria, including the important human pathogen Pseudomonas aeruginosa , are naturally found in antibiotic-tolerant, multicellular biofilms. Cell-cell interactions within P. aeruginosa biofilms are mediated by a large fibrillar adhesin called CdrA in an extracellular polysaccharide-dependent manner. Here, we report an electron cryomicroscopy structure of the 60 kDa CdrA adhesive N-terminus, which combined with electron cryotomography of focused-ion beam milled specimens, allows us to derive a complete in situ model of the native adhesin. Our structure reveals a small adhesive domain (called ADEPT) at the distal tip of CdrA that is nearly perfectly conserved across the P. aeruginosa pangenome, with structural similarity to previously reported sugar-binding domains in multiple bacterial species. Inhibitory nanobodies targeting CdrA that reduce biofilm formation bind to epitopes in, or close to, the ADEPT on bacterial cells. Furthermore, structure-guided mutagenesis of residues within the ADEPT abolishes bacterial aggregation, and genomic deletion of the whole ADEPT leads to strong attenuation of biofilm formation. Our data forms a rational basis for future targeted inhibition of pathogenic P. aeruginosa biofilms and elucidates the mechanism of biofilm formation mediated by fibrillar adhesins that are widespread in bacteria.},
}

@article {pmid42523892,
year = {2026},
author = {Abdurakhmonov, IY},
title = {Plant RNA interference from antiviral silencing to multiplex trait engineering for climate-resilient crops.},
journal = {Frontiers in plant science},
volume = {17},
number = {},
pages = {1871239},
pmid = {42523892},
issn = {1664-462X},
abstract = {RNA interference (RNAi) in plants has evolved from an unexplained antiviral and transgene interference phenomenon into a general regulatory platform for sequence-guided gene suppression, chromatin control, systemic signaling, and phenotypic plasticity. This Review synthesizes six decades of plant RNAi, tracing its progression through conceptual bottlenecks and technological solutions. Early work established that RNA-derived homology could suppress viral infection and transgene expression. Mechanistic studies then revealed a diversified plant silencing system involving Dicer-like proteins, Argonautes, RNA-dependent RNA polymerases, systemic movement, and RNA-directed DNA methylation. In parallel, RNAi moved into crop design, enabling targeted modification of yield, fiber quality, flowering, disease resistance, allergenicity, fertility, plant architecture, lignin content, nutrient composition, and pest resistance across diverse species. Importantly, RNAi is not merely a historical precursor to genome editing. It retains distinct value because it can tune gene dosage, silence multigene families, uncover compensatory network responses, and perturb upstream regulatory nodes, such as phytochrome RNAi in cotton, where partial suppression simultaneously improves several negatively correlated traits. Most recently, host-induced silencing, spray-induced dsRNA, nanocarrier delivery, and CRISPR-associated RNA tools have repositioned RNAi as a versatile breeding platform. The future lies in convergence with genome editing, using pangenome-informed, allele-aware target design and combined RNAi-editing pipelines. The lesson learned is that useful crop engineering often requires rebalancing endogenous networks rather than permanent gene knockout. In this review, the historical developmental phases are used carefully: the formal molecular term RNA interference emerged in the late 1990s, while earlier plant work on antiviral resistance, co-suppression and post-transcriptional gene silencing anticipated the same sequence-guided logic. At the same time, practical deployment remains constrained by variable knockdown, off-target risk, construct instability, environmental degradation of sprayed RNA, delivery cost, resistance evolution in target pests or pathogens, regulatory classification, and public acceptance; these constraints are discussed as platform-specific design and risk-assessment issues rather than as generic barriers.},
}

@article {pmid42506269,
year = {2026},
author = {Tan, H and Yang, S and Zhang, X},
title = {The Neurospora crassa Pangenome: A Robust Framework for Population-Scale Analysis and Structural Variant Discovery.},
journal = {Journal of fungi (Basel, Switzerland)},
volume = {12},
number = {7},
pages = {},
pmid = {42506269},
issn = {2309-608X},
abstract = {Neurospora crassa is a widely distributed ascomycete with high genetic diversity, yet reliance on limited reference genomes has hindered a comprehensive understanding of its genetic landscape. To address this limitation, we integrated the functional annotation of the FGSC2225 genome with a comprehensive comparative genomic analysis of N. crassa strains. FGSC2225 gene and transposable element (TE) proportions mirrored those of FGSC2489, though TE levels were significantly higher than those in sister species Sordaria macrospora. Phylogenetic analysis resolved the N. crassa population into two primary lineages: Clade A (including FGSC2489 and FGSC2225) and Clade B (including FGSC4830), with the former exhibiting larger genome sizes. Leveraging de novo assemblies of 72 high-quality draft genomes, we constructed a comprehensive pangenome to investigate the molecular evolution of various gene families. For example, systematic phylogenetic analysis of the HET-domain-containing gene family and three stress-related families-heat shock transcription factor, basic leucine zipper, and Cytochrome P450-demonstrated varying degrees of conservation and presence/absence variation across the lineages. Addressing the limitations of current genomic resources, this work provides a pangenomic framework to detect rapid adaptive evolution in filamentous fungi. This methodology serves as a robust template for identifying transcription factors, effectors, and structural variations critical to stress response and virulence in diverse fungi.},
}

@article {pmid42507078,
year = {2026},
author = {Ma, R and Wang, H and Wei, Y and Sun, Y and Xue, J and Qin, Y and Tao, S and Liu, Y},
title = {Population genomics reveals gene flow and positive selection patterns in the wine-related yeast Hanseniaspora uvarum.},
journal = {Stress biology},
volume = {6},
number = {1},
pages = {},
pmid = {42507078},
issn = {2731-0450},
support = {U21A20269//National Natural Science Key Foundation of China/ ; 32171458//National Natural Science Foundation of China/ ; CARS-29-jg-3//Earmarked Fund for China Agriculture Research System/ ; XJHQNY-2025-7//Special project of scientific and technological innovation of Xinjiang Research Institute of Arid Area Agriculture/ ; },
abstract = {Hanseniaspora uvarum is a representative non-Saccharomyces species that plays a significant role in fermentation processes such as winemaking. In recent years, this species has gained attention in food engineering and evolutionary biology. However, the population genomic signatures in this species remain poorly understood. In this study, a population genomics analysis was conducted on 151 H. uvarum strains (45 from Ningxia, China; 21 from other regions of China; 67 from Australia; and 18 from other regions or of unspecified origin), and a pangenome analysis was performed on 159 strains, incorporating eight additional genome assemblies. Phylogenetic analysis, ancestry coefficient analysis, and principal component analysis generally distinguished Chinese strains from those sampled on other continents. However, substantial post-divergence gene flow and introgression were inferred between intercontinentally paired clades. Positively selected candidate genes exhibited region-specific patterns: GO terms related to the positive regulation of filamentous growth in response to external stimuli were significantly enriched in the Ningxia strains; the stress-related GO term "cytoplasmic stress granule" was significantly enriched in both the Ningxia and Australian strains, but with distinct sets of associated genes. Although the samples were primarily isolated from anthropogenic environments, H. uvarum exhibited an open pangenome, indicating substantial adaptive potential to diverse stresses. This study advances our understanding of the evolutionary dynamics of H. uvarum and establishes a genomic foundation for future ecological and industrial research on this yeast.},
}

@article {pmid42508303,
year = {2026},
author = {Ghareeb, AM},
title = {Investigation in genomic signatures of helicobacter pylori through a microbial-genome wide association study exploring virulence variation.},
journal = {Diagnostic microbiology and infectious disease},
volume = {116},
number = {3},
pages = {117567},
doi = {10.1016/j.diagmicrobio.2026.117567},
pmid = {42508303},
issn = {1879-0070},
abstract = {BACKGROUND: Helicobacter (H.) pylori is characterized by a high degree of genomic diversity, with regional differences in virulence determinants. This study aims to explore genomic composition, phylogeography and accessory-gene relationships of Iraqi H. pylori isolates in a global contextualized dataset.

METHODS: A total of 198 H. Pylori genomes were reviewed, including 41 isolates sequenced from gastric samples of patients undergoing diagnostic endoscopy at Al-Yarmouk Teaching Hospital, Baghdad from June 2024 to February 2025. Illumina MiSeq was used to sequence genomes, which were quality-filtered and assembled using SPAdes. Prokka was used to perform annotation and Roary to infer pan-genome structure. FastTree was used to reconstruct core-genome phylogeny. Anatomical micro-niche (corpus vs. other gastric sites) were explored with pan-genome-wide association study (pan-GWAS) with Pyseer (linear mixed model, kinship based on the core alignment).

RESULTS: The H. Pylori pan-genome showed 955 core gene families and 9,400 accessory genes. Isolates from Iraq were polyphyletic, mixing with European and Middle Eastern lineages. In the primary Pyseer linear mixed-model analysis, Benjamini-Hochberg correction across 3,259 valid lrt-pvalue tests identified 151 FDR-significant associations; after excluding rows with problematic Pyseer diagnostic notes, 70 unflagged loci remained significant. The strongest unflagged positive association was group_2036, whereas a co-occurring block including cagS, cagT, and virB4_1 was strongly depleted in corpus-derived isolates. These signals implicate accessory-genome variation in gastric micro-niche adaptation while also underscoring the need to interpret flagged Pyseer rows cautiously.

CONCLUSIONS: The genomic variation of squamous H. Pylori isolates in Iraq corresponds to the global recombination trends and to the regional admixture. The corpus sampling-related accessory-gene cluster implies possible micro-niche adaptation. These preliminary results highlight the necessity of large, stratified Middle Eastern cohorts and long-read sequencing to dispel functional genetic constructions of tissue tropism and virulence.},
}

@article {pmid42510761,
year = {2026},
author = {Tian, M and Liang, Y and Lu, J and Shi, W and Zhao, Y and Gan, W and Jia, S and Xiao, C and Zhao, T and Zhang, H},
title = {Global Genomic Analysis of Bovine-Associated Klebsiella pneumoniae Reveals Genetic Diversity and Resistance-Virulence Profiles.},
journal = {Biology},
volume = {15},
number = {14},
pages = {},
doi = {10.3390/biology15141215},
pmid = {42510761},
issn = {2079-7737},
support = {BT-2025-TCYC-0066//Xinjiang Uyghur Autonomous Region "Tianchi Talent" Youth Doctoral Talent Program/ ; RCZK202578//Shihezi University/ ; 2024AB034//Science and Technology Development Project of Xinjiang Production and Construction Program/ ; 2025YD013//Central Government-Guided Local Science and Technology Development Project/ ; 2025AB083, 2024AB034 and 2024AB035//Scientific and Technological Tackling Plan for Key Fields of Xinjiang Production and Construction/ ; },
abstract = {Bovine-associated Klebsiella pneumoniae is an important bacterial species linking animal health, microbial ecology, and One Health-oriented antimicrobial resistance research. In this study, we performed a global genomic analysis of 1291 publicly available bovine-associated K. pneumoniae genomes collected from 18 countries between 2005 and 2024 using data retrieved from NCBI. MLST, core-genome phylogenetic analysis, pangenome analysis, CARD, VFDB, and PlasmidFinder were used to characterize sequence types, genomic diversity, antimicrobial resistance-associated genes, virulence-associated genes, and plasmid replicons. A total of 256 sequence types were identified, among which ST107 was the most common. Core-genome phylogenetic analysis revealed multiple genomic lineages, while pangenome analysis identified 46,325 gene clusters, including 1967 core genes and 40,595 cloud genes, indicating an open pangenome structure and substantial accessory gene diversity. Virulence-associated genes were unevenly distributed, with yagZ/ecpA being the most frequently detected determinant. In total, 138 antimicrobial resistance-associated genes or potential resistance determinants were detected across 16 antimicrobial categories, including clinically important β-lactamase- and carbapenemase-associated genes. IncF-family plasmid replicons, particularly IncFIB(K)_1_Kpn3, were frequently detected, suggesting widespread plasmid replicon-associated genomic backgrounds; however, physical co-localization between resistance genes and specific plasmid backbones could not be confirmed. Overall, this study reveals the genetic diversity, resistance-associated gene reservoir potential, heterogeneity of virulence-associated genes, and plasmid replicon backgrounds of bovine-associated K. pneumoniae. Importantly, the genome-predicted AMR potential identified in this study should not be interpreted as confirmed phenotypic resistance without further experimental validation. These findings provide genomic insights for risk surveillance, candidate control-target screening, and microbiota-oriented intervention research.},
}