@article {pmid40270815,
year = {2025},
author = {Esteves, MAC and Carvalho, MF and Viana, AS and Martini, CL and Longo, LGA and Silva, DNS and Ferreira, ALP and Ferreira-Carvalho, BT and Planet, PJ and Figueiredo, AMS},
title = {Decoding the evolutionary history of ST30 Staphylococcus aureus: insights into a potentially silent MSSA bloodstream pathogen.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1522747},
doi = {10.3389/fmicb.2025.1522747},
pmid = {40270815},
issn = {1664-302X},
abstract = {BACKGROUND: Staphylococcus aureus clonal complex 30 (CC30) is a historically significant pathogen affecting both hospital and community settings. The notable pandemic clones, phage-type 80/81 (PT80/81) and the Southwest Pacific clone (SWP) have spread internationally, contributing to significant morbidity and mortality. Despite their importance, research on the evolution of sequence type (ST) 30 has been limited, often focusing on a small number of strains or specific regions.

METHODS: In this study, we analyzed over 500 ST30 genomes from diverse sources, including Brazilian strains sequenced by our team, using genomic, pangenomic, phylogenetic, and time-calibrated phylogenetic analyses.

RESULTS: We traced key evolutionary events, estimating that the specialization of PT80/81 and SWP occurred after a divergence around 1868, forming a group of PT80/81-related strains and another group formed by SWP-related strains. Our findings highlight major events involving gene acquisition and loss, as well as mobile genetic elements (MGE). Notably, PT80/81 lost most lpl genes during diversification, which may have restricted the circulation of related strains. Contemporary strains-defined as those that emerged in the 21st century-predominantly cluster within a group divided into three subgroups, including Brazilian strains that acquired a novel pathogenicity island. Also clustering within the contemporary group, most toxic shock syndrome toxin-1 (TSST-1)-producing strains are methicillin-susceptible S. aureus (MSSA) that have gained additional virulence traits, including sea, which enhance their adaptability and virulence.

CONCLUSION: Our study revises the evolutionary history of ST30 S. aureus uncovering critical pathoadaptive events that may explain its success. Additionally, our findings emphasize a neglected issue: the high prevalence of MSSA in hospital infections, particularly the silent circulation of TSST-1 producing strains, capable of causing severe infections. Robust surveillance studies to monitor these strains are crucial.},
}

@article {pmid40269327,
year = {2025},
author = {He, F and Chen, S and Zhang, Y and Chai, K and Zhang, Q and Kong, W and Qu, S and Chen, L and Zhang, F and Li, M and Wang, X and Lv, H and Zhang, T and He, X and Li, X and Li, Y and Li, X and Jiang, X and Xu, M and Sod, B and Kang, J and Zhang, X and Long, R and Yang, Q},
title = {Pan-genomic analysis highlights genes associated with agronomic traits and enhances genomics-assisted breeding in alfalfa.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40269327},
issn = {1546-1718},
abstract = {Alfalfa (Medicago sativa L.), a globally important forage crop, is valued for its high nutritional quality and nitrogen-fixing capacity. Here, we present a high-quality pan-genome constructed from 24 diverse alfalfa accessions, encompassing a wide range of genetic backgrounds. This comprehensive analysis identified 433,765 structural variations and characterized 54,002 pan-gene families, highlighting the pivotal role of genomic diversity in alfalfa domestication and adaptation. Key structural variations associated with salt tolerance and quality traits were discovered, with functional analysis implicating genes such as MsMAP65 and MsGA3ox1. Notably, overexpression of MsGA3ox1 led to a reduced stem-leaf ratio and enhanced forage quality. The integration of genomic selection and marker-assisted breeding strategies improved genomic estimated breeding values across multiple traits, offering valuable genomic resources for advancing alfalfa breeding. These findings provide insights into the genetic basis of important agronomic traits and establish a solid foundation for future crop improvement.},
}

@article {pmid40269305,
year = {2025},
author = {Graham, F},
title = {Daily briefing: Potato pangenome reveals the complex genetics of the humble spud.},
journal = {Nature},
volume = {},
number = {},
pages = {},
doi = {10.1038/d41586-025-01282-x},
pmid = {40269305},
issn = {1476-4687},
}

@article {pmid40268598,
year = {2025},
author = {Tai, HH and Shannon, LM and Strömvik, MV},
title = {Polyploidy in potatoes: challenges and possibilities for climate resilience.},
journal = {Trends in genetics : TIG},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tig.2025.03.006},
pmid = {40268598},
issn = {0168-9525},
abstract = {Solanum section Petota Dumort. consists of tuber-bearing species (i.e., the cultivated potatoes and their wild relatives) that have both asexual and sexual propagation, variation in ploidy, and reproductive isolation. These species have undergone adaptation to a diversity of climates, altitudes, photoperiods, and geographical range. The section defies characterization with the biological species concept due to interspecies hybridization, allo- and auto-polyploidy, and phenotypic plasticity. Genetic studies, and more recently genome sequencing and pangenome analyses, are fostering a greater understanding of genetic processes that shape genome evolution and speciation in the section, shedding light on the phylogeny and providing insights on utilization of potato crop wild relatives in breeding for climate-resilient potato varieties.},
}

@article {pmid40268564,
year = {2025},
author = {Barros, JAS and Nunes-Nesi, A and Fernie, AR and Araújo, WL},
title = {Transcriptional crosstalk linking color, acidity, and aroma in peach.},
journal = {Trends in plant science},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tplants.2025.04.003},
pmid = {40268564},
issn = {1878-4372},
abstract = {Color and flavor are key quality traits in fruits. Using a newly constructed peach pangenome, Chen et al. demonstrated that the PbBL gene, a known regulator of peach fruit color, also contributes to malate accumulation. This finding, along with previous studies, unveils a transcriptional mechanism that co-regulates multiple traits in peaches.},
}

@article {pmid40266657,
year = {2025},
author = {Naing, SY and Zomer, A and der Graaf-van Bloois, LV and Houben, M and Junker, K and Schreurs, O and Heuvelink, A and Wagenaar, JA and van Hout, J},
title = {Molecular epidemiology and emergence of sequence type 25 hypervirulent Klebsiella pneumoniae in pigs in the Netherlands (2013-2020): a global comparative analysis with human and pig isolates.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
doi = {10.1099/mgen.0.001388},
pmid = {40266657},
issn = {2057-5858},
mesh = {Animals ; *Klebsiella pneumoniae/genetics/pathogenicity/isolation & purification/classification/drug effects ; Swine ; Humans ; Netherlands/epidemiology ; *Klebsiella Infections/epidemiology/microbiology/veterinary ; Virulence/genetics ; Plasmids/genetics ; Phylogeny ; Molecular Epidemiology ; *Swine Diseases/microbiology/epidemiology ; Drug Resistance, Multiple, Bacterial/genetics ; Virulence Factors/genetics ; },
abstract = {Klebsiella pneumoniae (Kp), a ubiquitous pathogen found in diverse ecological niches, poses a threat to human and animal health. Hypervirulent Kp (hvKp) is concerning for its acquisition of virulence and antimicrobial resistance genes through plasmids. This study investigates hvKp as a cause of septicaemia in piglets in the Netherlands and examines the role of plasmids in virulence and host association. We collected 41 Kp isolates cultured from necropsies submitted from 15 different farms (2013-2020) and sequenced them using long-read sequencing. We identified sequence type (ST) 25 as the dominant Kp (67%, 10/15 farms) associated with septicaemia in pigs in the Netherlands. ST25 isolates displayed a hypervirulent profile, including the K2 hyper-capsule type and carried an iuc3 virulence plasmid. Further analysis revealed two ST25 clonal groups: CG25 and CG3804, a novel porcine clone. Multidrug resistance was identified in CG25 isolates from five pig farms. There was one colistin-resistant isolate carrying mcr-1 on a plasmid. Comparative genomic analysis was performed by including a large dataset of related publicly available Kp genomes from ST25 humans (n=230) and pigs (n=12) of all STs for phylogenetic and plasmid analysis. Pangenomic analysis revealed significantly higher iuc3 prevalence in global CG25 pig isolates (98%, 40/41) compared to humans (10%, 24/234) correlating with their enhanced virulence (scores 3-4 vs 0-1). The study highlights ST25 hvKp causing septicaemia in piglets in the Netherlands for the first time. Aerobactin lineage iuc3 on a plasmid is associated with infections in pigs and is responsible for an increased virulence score.},
}

Animals
*Klebsiella pneumoniae/genetics/pathogenicity/isolation & purification/classification/drug effects
Swine
Humans
Netherlands/epidemiology
*Klebsiella Infections/epidemiology/microbiology/veterinary
Virulence/genetics
Plasmids/genetics
Phylogeny
Molecular Epidemiology
*Swine Diseases/microbiology/epidemiology
Drug Resistance, Multiple, Bacterial/genetics
Virulence Factors/genetics

@article {pmid40265878,
year = {2025},
author = {Tosoroni, A and Di Vittori, V and Nanni, L and Musari, E and Papalini, S and Bitocchi, E and Bellucci, E and Pieri, A and Ghitarrini, S and Susek, K and Papa, R},
title = {Recent Advances in Molecular Tools and Pre-Breeding Activities in White Lupin (Lupinus albus).},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {6},
pages = {},
doi = {10.3390/plants14060914},
pmid = {40265878},
issn = {2223-7747},
support = {862862//Horizon2020/ ; 101081329//Horizon2020/ ; },
abstract = {The higher adaptation of landraces to local agroclimatic conditions resulting from natural and moderate artificial selection by farmers within specific environments makes them a crucial source of alleles and genotypes for cultivation and breeding programs. Unlike modern cultivars, which have been developed under more intense artificial selective pressures, landraces exhibit a broader genetic base that has been documented in landrace collections for many crops. This review provides an overview of the importance of genetic resource valorisation in legume species, focusing on cultivated species of the Lupinus genus, particularly white lupin (Lupinus albus). On the one hand, legumes, including Lupins, are considered a crucial alternative source of protein within the framework of more sustainable agriculture. On the other hand, they are often neglected species in terms of breeding efforts, despite receiving increasing attention in recent years. Here, we also report on the latest advances in the development of genomic tools, such as the novel pangenome of white lupin and the identification of markers and loci for target adaptation traits, such as tolerance to alkaline soils, which can effectively support the breeding of Lupinus albus, especially for the introgression of desirable alleles from locally adapted varieties.},
}

@article {pmid40263939,
year = {2025},
author = {Li, Y and Arús, P and Wu, J and Zhu, G and Fang, W and Chen, C and Wang, X and Cao, K and Wang, L},
title = {Panvariome and pangenome of 1,020 global peach accessions shed light on evolution patterns, hidden natural variations and efficient gene discovery.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2025.04.009},
pmid = {40263939},
issn = {1752-9867},
abstract = {Natural variations are the basis of crop improvement. However, genomic variability remains largely understudied. We present the full-spectrum integrated panvariome and pangenome of 1,020 peach accessions, including 10.5 million SNPs, indels, DELs, INSs, DUPs, INVs, TRAs, CNVs, TIPs, and PAVs, uncovering 70.6% novel variants and 3,289 novel genes. Analysis of the panvariome reconstructs the globally evolutionary history of peach and identifies several novel trait-causally rare variants, improving the power of breeding markers. Landraces and improved accessions encode more genes than wild accessions, implying the gene gains during domestication and improvement. Global introgression patterns reveal its new utilizations in phenotype prediction and gene mining and firstly suggest that the most likely wild progenitor of domesticated peach is Prunus mira and almond was involved in the origin of Prunus davidiana. We develop a novel panvariome-based solution for association study, GWASPV, identifying several trait-conferring genes and more than 2,000 novel associations, that achieves rapid and precise identification of trait-conferring genes using only one-step GWAS. Our study provides a novel solution for gene mining, with important implications in accelerating plant breeding.},
}

@article {pmid40263846,
year = {2025},
author = {Gómez-Baltazar, A and Hernández-Pérez, CF and Franco-Frias, CU and Castañeda-Ruelas, GM and Cabrera-Diaz, E and Hernández-Iturriaga, M},
title = {Genomic diversity and distribution of Listeria monocytogenes strains isolated from imported and national fresh produce in Mexico from 2014 to 2018.},
journal = {Food research international (Ottawa, Ont.)},
volume = {208},
number = {},
pages = {116211},
doi = {10.1016/j.foodres.2025.116211},
pmid = {40263846},
issn = {1873-7145},
mesh = {*Listeria monocytogenes/genetics/isolation & purification/classification/pathogenicity ; Mexico ; *Food Microbiology ; *Genetic Variation ; Virulence Factors/genetics ; Whole Genome Sequencing ; *Genome, Bacterial ; Virulence/genetics ; Drug Resistance, Bacterial/genetics ; Polymorphism, Single Nucleotide ; *Vegetables/microbiology ; Prophages/genetics ; },
abstract = {Listeria monocytogenes is a major foodborne pathogen associated with fresh produce contamination, posing a significant public health risk due to its adaptability and virulence. This study investigates the genomic diversity and distribution of L. monocytogenes strains isolated from imported and domestic fresh produce in Mexico between 2014 and 2018. A total of 113 L. monocytogenes strains were isolated from produce commodities and subjected to whole-genome sequencing. The analysis focused on identifying lineages, serogroups, clonal complexes (CCs), antimicrobial resistance genes, virulence factors, prophage-associated regions, and SNP clusters, while the pangenome was characterized to assess both core and accessory gene diversity. Two main lineages (I and II) were identified, with lineage I predominantly associated with imported produce. Thirty-two CCs were detected, with CC4, CC11, and CC20 being the most prevalent. The pangenome analysis revealed 2188 core genes and 3739 accessory genes. Antimicrobial resistance genes, including fosX, lin, norB, and sul, were present in all strains. Virulence analysis identified 78 virulence genes, with notable differences among serogroups. Prophage analysis revealed 189 prophage-associated regions, with common phages such as A118 and LP-101 detected predominantly in serogroup IIa. The SNP cluster analysis grouped the strains into 33 clusters, with 48 % of the strains from imported produce concentrated in only three major clusters, indicating potential common sources or similar environmental exposures. The significant genomic diversity and SNP clustering of L. monocytogenes strains underscore the pathogen's adaptability and widespread dissemination potential in the global food supply chain. The presence of virulent CCs and antimicrobial resistance genes highlights an ongoing public health risk, emphasizing the need for enhanced surveillance and targeted interventions to prevent listeriosis outbreaks.},
}

*Listeria monocytogenes/genetics/isolation & purification/classification/pathogenicity
Mexico
*Food Microbiology
*Genetic Variation
Virulence Factors/genetics
Whole Genome Sequencing
*Genome, Bacterial
Virulence/genetics
Drug Resistance, Bacterial/genetics
Polymorphism, Single Nucleotide
*Vegetables/microbiology
Prophages/genetics

@article {pmid40261029,
year = {2025},
author = {Espinoza, ME and Swing, AM and Elghraoui, A and Modlin, SJ and Valafar, F},
title = {Interred mechanisms of resistance and host immune evasion revealed through network-connectivity analysis of M. tuberculosis complex graph pangenome.},
journal = {mSystems},
volume = {10},
number = {4},
pages = {e0049924},
doi = {10.1128/msystems.00499-24},
pmid = {40261029},
issn = {2379-5077},
support = {R01AI105185//HHS | NIH | National Institute of Allergy and Infectious Diseases (NIAID)/ ; R01AI163202//HHS | NIH | National Institute of Allergy and Infectious Diseases (NIAID)/ ; },
mesh = {*Mycobacterium tuberculosis/genetics/immunology/drug effects ; *Genome, Bacterial ; Humans ; *Immune Evasion/genetics ; *Tuberculosis/microbiology/immunology ; Drug Resistance, Bacterial/genetics ; Host-Pathogen Interactions/genetics/immunology ; Antitubercular Agents/pharmacology ; Bacterial Proteins/genetics ; },
abstract = {Mycobacterium tuberculosis complex successfully adapts to environmental pressures through mechanisms of rapid adaptation which remain poorly understood despite knowledge gained through decades of research. In this study, we used 110 reference-quality, complete de novo assembled, long-read sequenced clinical genomes to study patterns of structural adaptation through a graph-based pangenome analysis, elucidating rarely studied mechanisms that enable enhanced clinical phenotypes offering a novel perspective to the species' adaptation. Across isolates, we identified a pangenome of 4,325 genes (3,767 core and 558 accessory), revealing 290 novel genes, and a substantially more complete account of difficult-to-sequence esx/pe/pgrs/ppe genes. Seventy-four percent of core genes were deemed non-essential in vitro, 38% of which support the pathogen's survival in vivo, suggesting a need to broaden current perspectives on essentiality. Through information-theoretic analysis, we reveal the ppe genes that contribute most to the species' diversity-several with known consequences for antigenic variation and immune evasion. Construction of a graph pangenome revealed topological variations that implicate genes known to modulate host immunity (Rv0071-73, Rv2817c, cas2), defense against phages/viruses (cas2, csm6, and Rv2817c-2821c), and others associated with host tissue colonization. Here, the prominent trehalose transport pathway stands out for its involvement in caseous granuloma catabolism and the development of post-primary disease. We show paralogous duplications of genes implicated in bedaquiline (mmpL5 in all L1 isolates) and ethambutol (embC-A) resistance, with a paralogous duplication of its regulator (embR) in 96 isolates. We provide hypotheses for novel mechanisms of immune evasion and antibiotic resistance through gene dosing that can escape detection by molecular diagnostics.IMPORTANCEM. tuberculosis complex (MTBC) has killed over a billion people in the past 200 years alone and continues to kill nearly 1.5 million annually. The pathogen has a versatile ability to diversify under immune and drug pressure and survive, even becoming antibiotic persistent or resistant in the face of harsh chemotherapy. For proper diagnosis and design of an appropriate treatment regimen, a full understanding of this diversification and its clinical consequences is desperately needed. A mechanism of diversification that is rarely studied systematically is MTBC's ability to structurally change its genome. In this article, we have de novo assembled 110 clinical genomes (the largest de novo assembled set to date) and performed a pangenomic analysis. Our pangenome provides structural variation-based hypotheses for novel mechanisms of immune evasion and antibiotic resistance through gene dosing that can compromise molecular diagnostics and lead to further emergence of antibiotic resistance.},
}

*Mycobacterium tuberculosis/genetics/immunology/drug effects
*Genome, Bacterial
Humans
*Immune Evasion/genetics
*Tuberculosis/microbiology/immunology
Drug Resistance, Bacterial/genetics
Host-Pathogen Interactions/genetics/immunology
Antitubercular Agents/pharmacology
Bacterial Proteins/genetics

@article {pmid40261018,
year = {2025},
author = {Chi, W and Zhang, H and Li, X and Zhou, Y and Meng, Q and He, L and Yang, Y and Liu, S and Shi, K},
title = {Comparative genomic analysis of 255 Oenococcus oeni isolates from China: unveiling strain diversity and genotype-phenotype associations of acid resistance.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0326524},
doi = {10.1128/spectrum.03265-24},
pmid = {40261018},
issn = {2165-0497},
abstract = {Oenococcus oeni, the only species of lactic acid bacteria capable of fully completing malolactic fermentation under challenging wine conditions, continues to intrigue researchers owing to its remarkable adaptability, particularly in combating acid stress. However, the mechanism underlying its superior adaptation to wine stresses still remains elusive due to the lack of viable genetic manipulation tools for this species. In this study, we conducted genomic sequencing and acid resistance phenotype analysis of 255 O. oeni isolates derived from diverse wine regions across China, aiming to elucidate their strain diversity and genotype-phenotype associations of acid resistance through comparative genomics. A significant correlation between phenotypes and evolutionary relationships was observed. Notably, phylogroup B predominantly consisted of acid-resistant isolates, primarily originating from Shandong and Shaanxi wine regions. Furthermore, we uncovered a noteworthy linkage between prophage genomic islands and acid resistance phenotype. Using genome-wide association studies, we identified key genes correlated with acid resistance, primarily involved in carbohydrates and amino acid metabolism processes. This study offers profound insights into the genetic diversity and genetic basis underlying adaptation mechanisms to acid stress in O. oeni.IMPORTANCEThis study provides valuable insights into the genetic basis of acid resistance in Oenococcus oeni, a key lactic acid bacterium in winemaking. By analyzing 255 isolates from diverse wine regions in China, we identified significant correlations between strain diversity, genomic islands, and acid resistance phenotypes. Our findings reveal that certain prophage-related genomic islands and specific genes are closely linked to acid resistance, offering a deeper understanding of how O. oeni adapts to acidic environments. These discoveries not only advance our knowledge of microbial stress responses but also pave the way for selecting and engineering acid-resistant strains, enhancing malolactic fermentation efficiency and wine quality. This research underscores the importance of genomics in improving winemaking practices and addressing challenges posed by high-acidity wines.},
}

@article {pmid40259521,
year = {2025},
author = {Gatica-Soria, LM and Roulet, ME and Tulle, WD and Sato, HA and Barrandeguy, ME and Sanchez-Puerta, MV},
title = {Highly variable mitochondrial chromosome content in a holoparasitic plant due to recurrent gains of foreign circular DNA.},
journal = {Physiologia plantarum},
volume = {177},
number = {2},
pages = {e70231},
doi = {10.1111/ppl.70231},
pmid = {40259521},
issn = {1399-3054},
support = {06/A092-T1//Secretaría de Investigación, Internacionales y Posgrado, Universidad Nacional de Cuyo/ ; PICT2020-01018//Fondo para la Investigación Científica y Tecnológica/ ; PICT2021 -GTR_TI-00435//Fondo para la Investigación Científica y Tecnológica/ ; },
mesh = {Gene Transfer, Horizontal/genetics ; DNA, Mitochondrial/genetics ; *Chromosomes, Plant/genetics ; *DNA, Circular/genetics ; *Genome, Mitochondrial/genetics ; Evolution, Molecular ; Phylogeny ; },
abstract = {Multichromosomal mitochondrial genomes (mtDNAs) in eukaryotes exhibit remarkable structural diversity, yet intraspecific variability and the origin of the individual chromosomes remain poorly understood. We focus on a holoparasitic angiosperm with an mtDNA consisting of 65 chromosomes largely composed of foreign DNA acquired by horizontal gene transfer (HGT) from its mimosoid hosts. The frequency, timing and population dynamics of these HGT events have not been examined. Here, we sampled different individuals of the holoparasite Lophophytum mirabile, along with their host plants, to assess mtDNA intraspecific variability and capture recent events that may bring insights into the HGT process. We also gathered mitochondrial data from 43 mimosoids to identify older and recent HGT events and assess precisely the proportion of foreign DNA. Through comparative genomic and evolutionary analyses, we uncovered great intraspecific variability in chromosome content and defined the mitochondrial pangenome of L. mirabile with 105 distinct chromosomes. The estimated foreign content reaches 93.5% of the mtDNA, including 73 fully foreign chromosomes that support the circle-mediated HGT model as a key mechanism for their acquisition. We inferred recurrent DNA transfers from the host plants, leading to new mitochondrial chromosomes that replicate autonomously. Our results emphasize the importance of adopting a pangenomic approach to fully capture the genetic diversity and evolution of multichromosomal mitochondrial genomes. This study shows that HGT can strongly influence the mtDNA content and generate enormous intraspecific variability even in geographically close individuals.},
}

Gene Transfer, Horizontal/genetics
DNA, Mitochondrial/genetics
*Chromosomes, Plant/genetics
*DNA, Circular/genetics
*Genome, Mitochondrial/genetics
Evolution, Molecular
Phylogeny

@article {pmid40258473,
year = {2025},
author = {Gao, Y and Yang, L and Kuhn, K and Li, W and Zanton, G and Bowman, M and Zhao, P and Zhou, Y and Fang, L and Cole, JB and Rosen, BD and Ma, L and Li, C and Baldwin, RL and Van Tassell, CP and Zhang, Z and Smith, TPL and Liu, GE},
title = {Long read and preliminary pangenome analyses reveal breed-specific structural variations and novel sequences in Holstein and Jersey cattle.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2025.04.014},
pmid = {40258473},
issn = {2090-1224},
abstract = {INTRODUCTION: Most SV studies in livestock rely on short-read sequencing, posing challenges in accurately characterizing large genomic variants due to their limited read length.

OBJECTIVES: Our goal is to reveal structural variation and novel sequences specific to Holstein and Jersey cattle breeds using long-read and pan-genome analyses.

METHODS: We sequenced 20 Holsteins and 8 Jersey cattle using PacBio HiFi to 20×, and integrated five read-based and one assembly-based SV caller to determine SVs.

RESULTS: We assembled the 28 genomes averaging 3.25 Gb with a contig N50 of 69.36 Mb and using the ARS-UCD1.2 reference, we acquired Holstein/Jersey SV catalogs with 74,068/54,689 events spanning 202/135 Mb (7.43 %/4.97 % of the genome). SVs were enriched in less conserved, non-coding, and non-regulatory regions. Comparing Holsteins with differing feed efficiency (FE), SVs unique to high FE were linked to energy metabolism and olfactory receptors, while those specific to low FE were associated with material transport. We constructed Holstein/Jersey pangenome graphs with 148,598/105,875 nodes and 208,891/147,990 edges, representing 47,028/37,137 biallelic and multi-allelic events, and 63.75/42.34 Mb of novel sequence. We observed SV count saturation with 20 Holsteins, while adding Jerseys significantly increased the SV count, highlighting breed-specific SV events.

CONCLUSION: Our long-read data and SV catalogs are valuable resources, revealing that the cattle genome is more complex than previously thought.},
}

@article {pmid40258447,
year = {2025},
author = {Liu, J and Mo, D and Luo, L and Shi, Y and Xu, S},
title = {Sheep pan-genome retrieves the lost sequences and genes during domestication and selection.},
journal = {Genomics},
volume = {},
number = {},
pages = {111047},
doi = {10.1016/j.ygeno.2025.111047},
pmid = {40258447},
issn = {1089-8646},
abstract = {The reference genome plays a crucial role in uncovering genomic variations, which increase our understanding of the molecular mechanisms influencing biological traits. However, most of the sheep reference genomes derive from a single sheep individual, which couldn't adequately represent the genetic diversity of sheep. The map-to-pan strategy was used to construct the sheep pan-genome based on 801 samples with short read whole genome sequencing data including 724 domestic individuals from 151 sheep populations/breeds and 77 wild individuals from seven genus Ovis species, and a total of 195 Mb of nonreference sequences were assembled that absent from the ARS-UI_Ramb_v2.0 reference. MAKER2 pipeline, integrating ab initio gene prediction, RNA-Seq, and protein homology was used to annotate the nonreference sequences. As a result, a total of additional 2678 genes were predicted in the nonreference sequences. We also identified 13,317 novel single nucleotide polymorphisms (SNPs) by mapping the sequences that could not be aligned to ARS1-UI_Ramb_v2.0 to the nonreference sequences. Population genetic analysis, including principal component analysis (PCA), phylogenetic tree, and ADMIXTURE based on the novel SNPs revealed a clear phylogenetic relationship of the world's domestic sheep, as well as their close wild relatives. Additionally, pangenome-wide presence and absence variations (PAVs) analysis exhibited a decreasing trend in gene number from wild populations to domestic populations. Several genes, GZMH, NFE2L3, GPR146 and CALHM6 with significant changes of presence frequencies during the evolutionary history of sheep were identified by PAV selection analysis. Functional annotation revealed that these genes were primarily associated with immune responses. Our results highlight the implications of the sheep pan-genome in identifying previously unknown genetic variations. PAVs can be used to track and reveal the changes in genomic architecture throughout the evolutionary history of sheep, such as, gene loss. The genes, GZMH, NFE2L3, GPR146 and CALHM6 related to immune regulation and inflammatory responses may play important roles during the domestication history of sheep. These findings broaden our knowledge about the genetic diversity in sheep genomes, and provide insight into the domestication and breeding history of sheep.},
}

@article {pmid40253154,
year = {2025},
author = {Yadav, S and Rahim, MS and Devi, A and Sharma, RK},
title = {Revolutionizing Speciality Teas: Multi-omics prospective to breed anthocyanin-rich tea.},
journal = {Food research international (Ottawa, Ont.)},
volume = {209},
number = {},
pages = {116312},
doi = {10.1016/j.foodres.2025.116312},
pmid = {40253154},
issn = {1873-7145},
mesh = {*Anthocyanins/biosynthesis ; *Camellia sinensis/genetics/metabolism ; *Tea/chemistry/genetics/metabolism ; *Plant Breeding/methods ; Gene Expression Regulation, Plant ; Metabolomics ; *Genomics/methods ; Transcriptome ; Multiomics ; },
abstract = {Variations in metabolite accumulation particularly anthocyanins have been of keen interest to the global tea industry due to their potential health benefits. Previous studies on tea genome, transcriptome, and metabolome provided an integrated spectrum of bioactive metabolites biosynthesis in tea plants. However, comprehending knowledge of anthocyanin biosynthesis and its accumulation in tea plants needed to be unified with multi-omics approaches that can build a complete depiction of the regulatory genomic machinery for improving quality characteristics in tea. Furthermore, true visualization, interpretation, and precise dissection of key traits required significant enrichment of multi-omics data for integration of machine learning. This review emphasizes the role of genetics, epigenetics, and transcriptional regulation of early (EBG) and late biosynthetic genes (LBG) involved in anthocyanin biosynthesis and accumulation in purple tea. Additionally, other factors including key transcription factors, transporters, photosynthesis, vacuole pH, and co-biosynthesis of other flavonoids were discussed. We envision an integration of pangenome and genome-wide strategies (GWAS, mGWAS, EWAS) which can offer new insights for the breeding of anthocyanin-rich tea cultivars to fetch better trade revenue and nutraceutical benefits.},
}

*Anthocyanins/biosynthesis
*Camellia sinensis/genetics/metabolism
*Tea/chemistry/genetics/metabolism
*Plant Breeding/methods
Gene Expression Regulation, Plant
Metabolomics
*Genomics/methods
Transcriptome
Multiomics

@article {pmid40248511,
year = {2025},
author = {Boby, F and Bhuiyan, DMNH and Khan, DMS and Parvez, MM},
title = {Draft genome sequence data on Bacillus safensis FB03 isolated from the rhizosphere soil of leguminous plant in Bangladesh.},
journal = {Data in brief},
volume = {60},
number = {},
pages = {111527},
pmid = {40248511},
issn = {2352-3409},
abstract = {With the aim of investigating the biotechnological potential of Bacillus safensis' FB03, isolated from the rhizosphere soil of Bahrind region of Bangladesh, the current work focused on its complete genomic analysis and phenotypic description. The size of the genome of the isolate was 3.6 Mb with 41.59 % GC content. Genome annotation revealed the presence of many genes related to siderophore production, enzyme degradation, UV and stress tolerance. Six biosynthesis gene clusters for bacillibacin, bacilysin, bottromycin, Schizokinen, fengycin, and lychensin were identified through genome mining. Significantly, FB03 was found to contain only two acquired antimicrobial resistance genes and was anticipated to be non-pathogenic to humans. The openness of the Bacillus safensis pan-genome was demonstrated by the pan-genome analysis. According to this research, Bacillus safensis FB03 may be a good fit for a variety of biotechnological applications.},
}

@article {pmid40247941,
year = {2025},
author = {Zhang, J and Chen, C and Yang, Q and Xu, J and Han, Z and Ma, W and Zhang, X and Xu, K and Zhao, J and Chen, X},
title = {Evolution of HD-ZIP transcription factors and their function in cabbage leafy head formation.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1583110},
pmid = {40247941},
issn = {1664-462X},
abstract = {INTRODUCTION: The HD-ZIP protein, a unique class of transcription factors in plants, plays a crucial role in plant growth and development. Although some HD-ZIP transcription factors have been associated with leafy head formation in Chinese cabbage, their regulatory mechanisms remain poorly understood.

METHODS: This study identified the HD-ZIP family using HMM and TBtools, constructed a phylogenetic tree with OrthoFinder, and analyzed gene family expansion and contraction using CAFE. Conserved features were analyzed with MAFFT, MEME, and TBtools; regulatory networks were predicted using ATRM and PlantTFDB; and gene expression was validated by qRT-PCR.

RESULTS AND DISCUSSION: In this study, HD-ZIP gene sequences from 87 species were analyzed to explore the evolutionary history of this gene family. Despite significant variation in gene family expansion and contraction across species, our findings indicated that HD-ZIP family proteins were conserved in both lower (Charophyta) and higher plants, where they were potentially involved in root, stem, and leaf differentiation. In our analysis of 22 Brassica species, HD-ZIP III protein sequences and domains were conserved. However, within the pan-genome A of 18 Brassica rapa species, differences were observed in auxin-related cis-elements within the HD-ZIP III promoter regions between heading and non-heading cabbage varieties. RNA-seq analysis of wild-type A03 (heading) and mutant fg-1 (non-heading) revealed that 131 genes formed a protein interaction network or clustered in the same branch as HD-ZIP family genes. Through GO enrichment and qRT-PCR, several key candidate genes of Brassica rapa ssp. pekinensis A03 associated with leafy head formation in cabbage were identified. These findings established a foundation for understanding the molecular mechanisms by which the HD-ZIP gene family regulated head growth in Chinese cabbage.},
}

@article {pmid40245288,
year = {2025},
author = {Wang, Z and Fan, Y and Sun, J and Ma, S and Wang, Z and Li, J and Liu, K and Xiong, Z and Li, C and Wang, D and Zhang, H and Hua, J and Bao, Y},
title = {Pan-analysis of intra- and inter-species diversity reveals a group of highly variable immune receptor genes in rice.},
journal = {The Plant journal : for cell and molecular biology},
volume = {122},
number = {1},
pages = {e70163},
doi = {10.1111/tpj.70163},
pmid = {40245288},
issn = {1365-313X},
support = {JSSCBS20230082//Shuangchuang Program of Jiangsu Province/ ; JBGS2021040//Seed Industry Revitalization Project of Jiangsu Province/ ; NAUSY-MS06//Guidance Foundation, the Sanya Institute of Nanjing Agricultural University/ ; 31871602//National Natural Science Foundation of China/ ; 32072033//National Natural Science Foundation of China/ ; 32301884//National Natural Science Foundation of China/ ; 32472216//National Natural Science Foundation of China/ ; 323MS070//Hainan Provincial Natural Science Foundation of China/ ; 325QN368//Hainan Provincial Natural Science Foundation of China/ ; },
mesh = {*Oryza/genetics/immunology ; *Plant Proteins/genetics/metabolism ; *Genetic Variation ; *Plant Immunity/genetics ; NLR Proteins/genetics ; Phylogeny ; Species Specificity ; Genome, Plant/genetics ; Genes, Plant/genetics ; Gene Expression Regulation, Plant ; Receptors, Pattern Recognition/genetics ; },
abstract = {Plant immune receptors and their natural variations play a central role in combating disease-causing pathogens. These immune receptors include intracellular nucleotide-binding leucine-rich repeat (LRR) receptors (NLRs) and cell-surface pattern recognition receptors (PRRs) that can be further classified as receptor-like proteins (RLPs) and receptor-like kinases (RLKs). Although the NLRome has been characterized, the repertoire and extent of diversity of PRRome remain undetermined in rice. In this study, we examined the diversity of immune receptor genes using high-quality genomes of 309 rice accessions from 8 species within the genus Oryza. A total of 376 310 immune receptor genes were identified, including 149 592 NLR-coding genes and 226 718 PRR coding genes. Shannon entropy analysis revealed a set of immune receptors that display significant intra-species and inter-species diversity in rice. In general, RLPs are more variable than RLKs, while NLRs and LRR-RLPs are more variable than LRR-RLKs. Additionally, NLR and PRR genes exhibit contrasting shoot/root expression patterns, with NLRs generally skewed towards root expression. Furthermore, we found that the size of the LRR-RLK gene families correlates with local annual precipitation, suggesting a stronger selection pressure on LRR-RLK genes in rice accessions grown under wet conditions than dry conditions. In sum, this pan-genomic analysis not only reveals the extensive diversity of the immune receptor repertoires in rice but also provides potential target genes for improving disease resistance in rice.},
}

*Oryza/genetics/immunology
*Plant Proteins/genetics/metabolism
*Genetic Variation
*Plant Immunity/genetics
NLR Proteins/genetics
Phylogeny
Species Specificity
Genome, Plant/genetics
Genes, Plant/genetics
Gene Expression Regulation, Plant
Receptors, Pattern Recognition/genetics

@article {pmid40245044,
year = {2025},
author = {Mendoza-Mujica, G and Calvay-Sanchez, KD and Zarate-Sulca, Y and Jimenez-Vasquez, V},
title = {New insights into the genomic information of an overlooked human pathogen: Bartonella rochalimae causative agent of Carrion's disease.},
journal = {PLoS neglected tropical diseases},
volume = {19},
number = {4},
pages = {e0013040},
doi = {10.1371/journal.pntd.0013040},
pmid = {40245044},
issn = {1935-2735},
abstract = {The Bartonella genus includes over twenty species, most transmitted by arthropods and possibly eleven related to human diseases, though some currently lack specific vectors or hosts. Bartonella rochalimae, a Gram-negative pleomorphic bacterium, was first isolated in 2007 from a woman who traveled to Peru and developed Carrion's disease-like symptoms. Hence, this study aims to report on bacterial isolates from patients diagnosed with Carrion's disease, which were found to be caused by B. rochalimae rather than B. bacilliformis, and to characterize the genomic aspects of B. rochalimae as a human pathogen. Five strains of B. rochalimae were identified using pangenomic and phylogenetic analysis. Additional analyses included core and clade-specific genes, gene ontology (GO), virulence factors (VF), and subcellular localization. This study identified five B. rochalimae strains from the regions of Ancash, Cajamarca, and Huánuco in Peru, suggesting regional circulation. The findings emphasize the importance of further research on B. rochalimae gene functions and its role in outbreak developments, highlighting the importance of improved diagnostics and enhanced surveillance.},
}

@article {pmid40243587,
year = {2025},
author = {Gutiérrez, AV and Matthews, M and Diaz, M and Le Viet, T and de Oliveira Martins, L and Jørgensen, F and Aird, H and Painset, A and Som, N and Omelchenko, O and Adriaenssens, EM and Kingsley, RA and Gilmour, MW},
title = {Population structure and gene flux of Listeria monocytogenes ST121 reveal prophages as a candidate driver of adaptation and persistence in food production environments.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
doi = {10.1099/mgen.0.001397},
pmid = {40243587},
issn = {2057-5858},
mesh = {*Listeria monocytogenes/genetics/virology/classification/isolation & purification ; *Prophages/genetics ; Phylogeny ; *Food Microbiology ; Humans ; Genome, Bacterial ; United Kingdom ; Listeriosis/microbiology ; Adaptation, Physiological/genetics ; Whole Genome Sequencing ; Evolution, Molecular ; },
abstract = {Listeria monocytogenes is a bacterial pathogen found in an increasing number of food categories, potentially reflecting an expanding niche and food safety risk profile. In the UK, Listeria monocytogenes sequence type (ST) 121 is more frequently isolated from foods and food environments than from cases of clinical listeriosis, consistent with a relatively low pathogenicity. In this study, we determined the evolution associated with the environmental persistence of a Listeria monocytogenes clone by investigating clone-specific genome features in the context of the ST121 population structure from international sources. To enable unambiguous comparative genomic analysis of ST121 strains, we constructed 16 new high-quality genome assemblies from Listeria monocytogenes isolated from foods, food environments and human clinical sources in the UK from 1987 to 2019. Our dataset was supplemented with additional UK and international genomes from databases held by the Institut Pasteur and the UK Health Security Agency. Time-scaled phylogenetic reconstruction revealed that clade-specific microevolution correlated with key characteristics that may confer adaptations important for success in the environmental niche. For example, a prophage designated LP-13-6 unique to a clade is associated with multi-year persistence in a food production setting. This prophage, observed in a strain that persisted for over a decade, may encode mechanisms facilitating environmental persistence, including the exclusion of other bacteriophages. Pangenome analysis provided insights into other candidate genetic elements associated with persistence and biocide tolerance. The comparative genomic dataset compiled in this study includes an international collection of 482 genome sequences that serve as a valuable resource for future studies to explore conserved genes, regulatory regions, mutations and variations associated with particular traits, such as environmental persistence, pathogenicity or biocide tolerance.},
}

*Listeria monocytogenes/genetics/virology/classification/isolation & purification
*Prophages/genetics
Phylogeny
*Food Microbiology
Humans
Genome, Bacterial
United Kingdom
Listeriosis/microbiology
Adaptation, Physiological/genetics
Whole Genome Sequencing
Evolution, Molecular

@article {pmid40241821,
year = {2025},
author = {Terra, LA and Klepa, MS and Nogueira, MA and Hungria, M},
title = {Pangenome analysis indicates evolutionary origins and genetic diversity: emphasis on the role of nodulation in symbiotic Bradyrhizobium.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1539151},
pmid = {40241821},
issn = {1664-462X},
abstract = {The Bradyrhizobium genus is widely known for encompassing many species capable of forming nodules and establishing the biological nitrogen fixation process with several legumes, significantly contributing to agriculture and environmental sustainability. Despite its importance, questions about the evolution, pangenome, and symbiotic genes of Bradyrhizobium are still poorly understood. In this study, we analyzed the pangenome of a set of Bradyrhizobium symbiotic species using the Roary and GET_HOMOLOGUES tools in strains originated from the Northern and Southern Hemispheres. We also investigated the presence and correlation of the fix, nif, nod, Type III secretion system (T3SS) and their effector proteins, and T4SS genes, trying to find differences between clades, hosts, and biogeographic origin. Pangenome analysis of Bradyrhizobium species from the Northern and Southern Hemispheres provided valuable insights into their diversity, biogeography, origin, and co-evolution with their legume host plants. The genus possesses a relatively small core genome compared to the expanded accessory genome, a key feature that facilitates genetic exchange and acquisition of new genes, allowing adaptation to a variety of environments. Notably, the presence or absence of T3SS effector proteins varied significantly according to the geographic location, suggesting specific environmental adaptations, as well as a direct relationship with nodulation genes. Comparative analysis indicated that symbiotic Bradyrhizobium species originated in the Northern Hemisphere and present a greater diversity of orthologous groups than those from the Southern Hemisphere. These results contribute to our understanding of the evolutionary history of these symbiotic bacteria.},
}

@article {pmid40240877,
year = {2025},
author = {Li, W and Chu, C and Zhang, T and Sun, H and Wang, S and Liu, Z and Wang, Z and Li, H and Li, Y and Zhang, X and Geng, Z and Wang, Y and Li, Y and Zhang, H and Fan, W and Wang, Y and Xu, X and Cheng, L and Zhang, D and Xiong, Y and Li, H and Zhou, B and Guan, Q and Deng, CH and Han, Y and Ma, H and Han, Z},
title = {Pan-genome analysis reveals the evolution and diversity of Malus.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40240877},
issn = {1546-1718},
support = {CARS-27//Earmarked Fund for China Agriculture Research System/ ; 32172522//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32422077//National Natural Science Foundation of China (National Science Foundation of China)/ ; 2019M661344//China Postdoctoral Science Foundation/ ; },
abstract = {Malus Mill., a genus of temperate perennial trees with great agricultural and ecological value, has diversified through hybridization, polyploidy and environmental adaptation. Limited genomic resources for wild Malus species have hindered the understanding of their evolutionary history and genetic diversity. We sequenced and assembled 30 high-quality Malus genomes, representing 20 diploids and 10 polyploids across major evolutionary lineages and geographical regions. Phylogenomic analyses revealed ancient gene duplications and conversions, while six newly defined genome types, including an ancestral type shared by polyploid species, facilitated the detection of strong signals for extensive introgressions. The graph-based pan-genome captured shared and species-specific structural variations, facilitating the development of a molecular marker for apple scab resistance. Our pipeline for analyzing selective sweep identified a mutation in MdMYB5 having reduced cold and disease resistance during domestication. This study advances Malus genomics, uncovering genetic diversity and evolutionary insights while enhancing breeding for desirable traits.},
}

@article {pmid40240605,
year = {2025},
author = {Guo, D and Li, Y and Lu, H and Zhao, Y and Kurata, N and Wei, X and Wang, A and Wang, Y and Zhan, Q and Fan, D and Zhou, C and Lu, Y and Tian, Q and Weng, Q and Feng, Q and Huang, T and Zhang, L and Gu, Z and Wang, C and Wang, Z and Wang, Z and Huang, X and Zhao, Q and Han, B},
title = {A pangenome reference of wild and cultivated rice.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {40240605},
issn = {1476-4687},
abstract = {Oryza rufipogon, the wild progenitor of Asian cultivated rice Oryza sativa, is an important resource for rice breeding[1]. Here we present a wild-cultivated rice pangenome based on 145 chromosome-level assemblies, comprising 129 genetically diverse O. rufipogon accessions and 16 diverse varieties of O. sativa. This pangenome contains 3.87 Gb of sequences that are absent from the O. sativa ssp. japonica cv. Nipponbare reference genome. We captured alternate assemblies that include heterozygous information missing in the primary assemblies, and identified a total of 69,531 pan-genes, with 28,907 core genes and 13,728 wild-rice-specific genes. We observed a higher abundance and a significantly greater diversity of resistance-gene analogues in wild rice than in cultivars. Our analysis indicates that two cultivated subpopulations, intro-indica and basmati, were generated through gene flows among cultivars in South Asia. We also provide strong evidence to support the theory that the initial domestication of all Asian cultivated rice occurred only once. Furthermore, we captured 855,122 differentiated single-nucleotide polymorphisms and 13,853 differentiated presence-absence variations between indica and japonica, which could be traced to the divergence of their respective ancestors and the existence of a larger genetic bottleneck in japonica. This study provides reference resources for enhancing rice breeding, and enriches our understanding of the origins and domestication process of rice.},
}

@article {pmid40240601,
year = {2025},
author = {Sun, H and Tusso, S and Dent, CI and Goel, M and Wijfjes, RY and Baus, LC and Dong, X and Campoy, JA and Kurdadze, A and Walkemeier, B and Sänger, C and Huettel, B and Hutten, RCB and van Eck, HJ and Dehmer, KJ and Schneeberger, K},
title = {The phased pan-genome of tetraploid European potato.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {40240601},
issn = {1476-4687},
abstract = {Potatoes were first brought to Europe in the sixteenth century[1,2]. Two hundred years later, one of the species had become one of the most important food sources across the entire continent and, later, even the entire world[3]. However, its highly heterozygous, autotetraploid genome has complicated its improvement since then[4-7]. Here we present the pan-genome of European potatoes generated from phased genome assemblies of ten historical potato cultivars, which includes approximately 85% of all haplotypes segregating in Europe. Sequence diversity between the haplotypes was extremely high (for example, 20× higher than in humans), owing to numerous introgressions from wild potato species. By contrast, haplotype diversity was very low, in agreement with the population bottlenecks caused by domestication and transition to Europe. To illustrate a practical application of the pan-genome, we converted it into a haplotype graph and used it to generate phased, megabase-scale pseudo-genome assemblies of commercial potatoes (including the famous French fries potato 'Russet Burbank') using cost-efficient short reads only. In summary, we present a nearly complete pan-genome of autotetraploid European potato, we describe extraordinarily high sequence diversity in a domesticated crop, and we outline how this resource might be used to accelerate genomics-assisted breeding and research.},
}

@article {pmid40239363,
year = {2025},
author = {Wang, M and Jin, L and Wang, R and Wang, Q and Wang, S and Wu, X and Yao, C and Corander, J and Wang, H},
title = {KpnK48 clone driving hypervirulent carbapenem-resistant Escherichia coli epidemics: Insights into its evolutionary trajectory similar to Klebsiella pneumoniae.},
journal = {Drug resistance updates : reviews and commentaries in antimicrobial and anticancer chemotherapy},
volume = {81},
number = {},
pages = {101243},
doi = {10.1016/j.drup.2025.101243},
pmid = {40239363},
issn = {1532-2084},
abstract = {AIMS: Hypervirulent and carbapenem-resistant pathogens posed a significant and growing threat to global public health. This study focused on the rapid spread of a hypervirulent carbapenem-resistant E. coli (hv-CREC) subclone and its genomic resembles with hypervirulent carbapenem-resistant K. pneumoniae (hv-CRKP), driven by recombination impacting both chromosomal and plasmid gene content.

METHODS: A multicenter molecular epidemiological study was conducted on 653 CREC clinical isolates collected across China (2013-2022), integrated with public genomic data. Pangenome-wide and phylogeographical analyses were performed to uncover recombination events, define the epidemic clone, and trace its evolutionary history. Growth advantage and virulence were evaluated through competition assays and Galleria mellonella infection models.

RESULTS: Sequence types (ST) 167, ST410, ST617, and ST361 collectively accounted for 53.8 % (351/653) of the CREC isolates, with ST167 showing a sharp increase in prevalence after 2017. Among these, subclone named KpnK48 emerged as the primary driver of the increase in ST167 CREC prevalence. Traced to a European origin, KpnK48 rapidly expanded globally, particularly in China. The remarkable success of KpnK48 could plausibly be attributed to enhanced survival and virulence, driven by the acquisition of a ∼492 kb recombinant genomic region which mirrored the genomic architecture underlying the hv-CRKP ST11-K64 clone, reflecting a Klebsiella-like evolutionary path. Additionally, plasmid shift in KpnK48 clone from the prevalent NDM-IncX3 plasmid to Klebsiella-common NDM-IncF plasmid expanded its resistance spectrum and virulence gene repertoire, likely further amplifying its pathogenicity and success.

CONCLUSIONS: The KpnK48 subclone combined the features of hypervirulence and carbapenem resistance, bridging genomic traits of E. coli and K. pneumoniae, signifying a broader evolutionary trend with profound global health implications.},
}

@article {pmid40236780,
year = {2025},
author = {Zong, W and Chen, L and Zhang, D and Zhang, Y and Wang, J and Hou, X and Chai, J and An, Y and Tian, M and He, X and Song, C and He, J and Liu, X and Wang, L and D'Alessandro, E and Wang, L and Yin, Y and Li, M and Liu, D and Wang, J and Zhang, L},
title = {Two telomere-to-telomere pig genome assemblies and pan-genome analyses provide insights into genomic structural landscape and genetic adaptations.},
journal = {iMeta},
volume = {4},
number = {2},
pages = {e70013},
pmid = {40236780},
issn = {2770-596X},
abstract = {This study presented two high-precision telomere-to-telomere genome assemblies for Min and Rongchang pigs, including a detailed exploration of the telomeric and centromeric regions. By integrating pan-genome and multi-omics analyses, structural variations linked to genetic adaptation were identified, providing a valuable resource for advancing pig breeding and genetic improvement.},
}

@article {pmid40236772,
year = {2025},
author = {Wang, X and Zhou, P and Hu, X and Bai, Y and Zhang, C and Fu, Y and Huang, R and Suzhen, N and Song, X},
title = {T2T genome, pan-genome analysis, and heat stress response genes in Rhododendron species.},
journal = {iMeta},
volume = {4},
number = {2},
pages = {e70010},
pmid = {40236772},
issn = {2770-596X},
abstract = {This study reports the first high-quality telomere-to-telomere (T2T) Rhododendron liliiflorum genome with 11 chromosomes that are gap free. The 24 telomeres and all 13 centromeres detected in this genome, which reached the highest quality gold level. In addition, other three Rhododendron species were sequenced and assembled to the chromosomal level. Based on 15 Rhododendron genomes, we conducted a pan-genome analysis of genus Rhododendron. Combining the genome and whole transcriptome sequencing, we identified several key genes and miRNAs related to the heat stress, which were further verified by transgenic experiments. Our findings provide rich resources for comparative and functional genomics studies of Rhododendron species.},
}

@article {pmid40236729,
year = {2025},
author = {Yang, M and Kong, X and Zhou, C and Kuang, R and Wu, X and Liu, C and He, H and Xu, Z and Wei, Y},
title = {Genomic insights into the domestication and genetic basis of yield in papaya.},
journal = {Horticulture research},
volume = {12},
number = {5},
pages = {uhaf045},
pmid = {40236729},
issn = {2662-6810},
abstract = {Papaya (Carica papaya L.) is an important tropical and subtropical fruit crop, and understanding its genome is essential for breeding. In this study, we assembled a high-quality genome of 344.17 Mb for the newly cultivated papaya 'Zihui', which contains 22 250 protein-coding genes. By integrating 201 resequenced papaya genomes, we identified four distinct papaya groups and a 34 Mb genomic region with strong domestication selection signals. Within these regions, two key genes associated with papaya yield were discovered: Cp_zihui06549, encoding a leucine-rich receptor-like protein kinase, and Cp_zihui06768, encoding the accumulation of photosystem one 1 (APO1) protein. Heterologous expression of Cp_zihui06549 in tomato confirmed that the total number of fruits in transgenic lines more than doubled compared to wild-type plants, resulting in a significant yield increase. Furthermore, we constructed a pan-genome of papaya and obtained a 77.41 Mb nonreference sequence containing 1543 genes. Within this pan-genome, 2483 variable genes, we detected, including four genes annotated as the 'terpene synthase activity' Gene Ontology term, which were lost in cultivars during domestication. Finally, gene retention analyses were performed using gene presence and absence variation data and differentially expressed genes across various tissues and organs. This study provides valuable insights into the genes and loci associated with phenotypes and domestication processes, laying a solid foundation for future papaya breeding efforts.},
}

@article {pmid40236485,
year = {2025},
author = {Dione, N and Mlaga, KD and Liang, S and Jospin, G and Marfori, Z and Alvarado, N and Scarsella, E and Uttarwar, R and Ganz, HH},
title = {Comparative genomic and phenotypic description of Escherichia ruysiae: a newly identified member of the gut microbiome of the domestic dog.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1558802},
pmid = {40236485},
issn = {1664-302X},
abstract = {INTRODUCTION: Escherichia ruysiae is a newly identified species within the Escherichia genus, yet its presence in domestic animals remains largely unexamined. This study characterizes four isolates detected for the first time in the domestic dog (Canis lupus familiaris), focusing on their phenotypic and genomic features.

METHODS: We used culturomic methods to isolate four E. ruysiae isolates that were initially identified as Escherichia coli using MALDI-TOF mass spectrometry. Whole-genome sequencing confirmed that the isolates belonged to E. ruysiae, not E. coli. Phenotypic characterization included enzymatic activity assays and antimicrobial susceptibility testing. Comparative genomic analyses were performed on these four isolates, along with 14 additional E. ruysiae and representative genomes from the five other Escherichia species in order to assess genetic diversity and functional gene distribution.

RESULTS AND DISCUSSION: All strains exhibited similar enzymatic activities and resistance to clindamycin, erythromycin, and metronidazole. The pangenome analysis revealed that most missing gene orthologs are related to motility followed by metabolism, including synthetases, reductases, phosphatases, permeases, transferases, and epimerases, as well as structural genes like efflux pumps and transporters. Phylogroup typing using the ClermonTyping method identified two main groups within the E. ruysiae species, Clade III and IV. Typical virulence genes associated with E. coli are absent in these strains. The multiple approaches used in this study expand our understanding of the diverse aspects of the recently described species, E. ruysiae.},
}

@article {pmid40236475,
year = {2025},
author = {Zhu, X and Huang, Y and Shi, Y and Gao, X and Chen, D and Liu, C and Cao, S and Xue, X and Li, Y},
title = {Comparative genomic analysis of food-animal-derived and human-derived Clostridium perfringens isolates from markets in Shandong, China.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1543511},
pmid = {40236475},
issn = {1664-302X},
abstract = {Clostridium perfringens (C. perfringens) is a foodborne pathogen that poses a significant threat to both animal husbandry and public health. In this study, 27 C. perfringens strains were isolated from animal samples and animal-derived food products. Antibiotics resistances among the isolates were phenotypically and genotypically analyzed and Whole genome sequencing (WGS). In combination with the genomes of 141 human-derived C. perfringens strains from public databases, this study conducted comprehensive analyses of antibiotic resistance genes, virulence genes, multilocus sequence typing (MLST), prophage detection, and pan-genome analysis for a total of 168 strains of C. perfringens. Antibiotics resistances among the isolates were phenotypically and genotypically analyzed and found 24 of them (88.9%, 24/27) were identified as multidrug-resistant (MDR). WGS analysis revealed that 13 strains belonged to known sequence types (ST), and the remaining strains represented 10 new STs. By analysis in combination with data of 141 C. perfringens isolates from the database, it was implied that ST221, ST72 and ST370 were present in both animal-derived and human-derived C. perfringens. It is worth noting that 108 out of 168 strains of C. perfringens (64.3%, 108/168) were found to carry prophages, which were found more prevalent in human-derived C. perfringens isolates. Pan-genome and phylogenetic analysis of 168 C. perfringens strains indicated that C. perfringens possesses an open pan-genome with genetic diversity. This study provides genomic insights into C. perfringens from food animals and humans, shedding light on the importance for monitoring the C. perfringens in livestock in China for better public health.},
}

@article {pmid40235155,
year = {2025},
author = {Liang, YY and Liu, H and Lin, QQ and Shi, Y and Zhou, BF and Wang, JS and Chen, XY and Shen, Z and Qiao, LJ and Niu, JW and Ling, SJ and Luo, WJ and Zhao, W and Liu, JF and Kuang, YW and Ingvarsson, PK and Guo, YL and Wang, B},
title = {Pan-genome analysis reveals local adaptation to climate driven by introgression in oak species.},
journal = {Molecular biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/molbev/msaf088},
pmid = {40235155},
issn = {1537-1719},
abstract = {The genetic base of local adaptation has been extensively studied in natural populations. However, a comprehensive genome-wide perspective on the contribution of structural variants (SVs) and adaptive introgression to local adaptation remains limited. In this study, we performed de novo assembly and annotation of 22 representative accessions of Quercus variabilis, identifying a total of 543,372 SVs. These SVs play crucial roles in shaping genomic structure and influencing gene expression. By analysing range-wide genomic data, we identified both SNPs and SVs associated with local adaptation in Q. variabilis and Q. acutissima. Notably, SV-outliers exhibit selection signals that did not overlap with SNP-outliers, indicating that SNP-based analyses may not detect the same candidate genes associated with SV-outliers. Remarkably, 29-37% of candidate SNPs were located in a 250 kb region on chromosome 9, referred to as Chr9-ERF. This region contains eight duplicated ethylene-responsive factor (ERF) genes, which may have contributed to local adaptation of Q. variabilis and Q. acutissima. We also found that a considerable number of candidate SNPs were shared between Q. variabilis and Q. acutissima in the Chr9-ERF region, suggesting a pattern of repeated selection. We further demonstrated that advantageous variants in this region were introgressed from western populations of Q. acutissima into Q. variabilis, providing compelling evidence that introgression facilitates local adaptation. This study offers a valuable genomic resource for future studies on oak species and highlights the importance of pan-genome analysis in understating mechanism driving adaptation and evolution.},
}

@article {pmid40232949,
year = {2025},
author = {Iranzadeh, A and Alisoltani, A and Kiran, AM and Breiman, RF and Chaguza, C and Peno, C and Cornick, JE and Everett, DB and Mulder, N},
title = {Comparative pangenomics of Streptococcus pneumoniae from Malawi: uncovering genetic variability and pathogenicity.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
doi = {10.1099/mgen.0.001370},
pmid = {40232949},
issn = {2057-5858},
mesh = {*Streptococcus pneumoniae/genetics/pathogenicity/classification/isolation & purification ; Malawi/epidemiology ; Humans ; *Pneumococcal Infections/microbiology/epidemiology ; *Genetic Variation ; Serogroup ; Genome, Bacterial ; Phylogeny ; Genomics ; Virulence/genetics ; Child ; Bacterial Proteins/genetics ; Child, Preschool ; Female ; Bacteremia/microbiology ; },
abstract = {Streptococcus pneumoniae is a significant cause of bacterial infections, including pneumonia, meningitis and septicemia, primarily affecting children, the elderly and immunocompromised individuals. This study aimed to elucidate the serotype and lineage distribution and molecular mechanisms underlying pneumococcal invasiveness through a comprehensive pangenomic analysis of 1416 isolates from Malawi. Our analysis comprised 810 isolates from asymptomatic carriers and 606 isolates from patients with bacteraemia or meningitis. We identified 58 serotypes, with serotypes 1, 5 and 12F exhibiting significantly higher prevalence among patients. These serotypes likely exhibit reduced nasopharyngeal colonization and demonstrate rapid dissemination to sterile sites. Notably, these serotypes form a distinct lineage with distinct genomic characteristics, including the absence of V-type ATP synthase. The pangenome analysis revealed two highly conserved surface protein complexes, F-type ATP synthase and SecA1-SecY, which deserve further investigation as potential targets for novel therapeutic interventions.},
}

*Streptococcus pneumoniae/genetics/pathogenicity/classification/isolation & purification
Malawi/epidemiology
Humans
*Pneumococcal Infections/microbiology/epidemiology
*Genetic Variation
Serogroup
Genome, Bacterial
Phylogeny
Genomics
Virulence/genetics
Child
Bacterial Proteins/genetics
Child, Preschool
Female
Bacteremia/microbiology

@article {pmid40232097,
year = {2025},
author = {Kim, SS},
title = {Application of Comparative Genomics for the Development of PCR Primers for the Detection of Harmful or Beneficial Microorganisms in Food: Mini-Review.},
journal = {Foods (Basel, Switzerland)},
volume = {14},
number = {6},
pages = {},
pmid = {40232097},
issn = {2304-8158},
abstract = {Gene markers are widely utilized for detecting harmful and beneficial microorganisms in food products. Primer sequences targeting the 16S rRNA region, recognized as a conserved region, have been conventionally employed in PCR analyses. However, several studies have highlighted limitations and false-positive results associated with the use of these primer sequences. Consequently, pan-genome analysis, a comparative genomic approach, has been increasingly applied to design more selective gene markers. This mini-review explores the application of pan-genome analysis in developing PCR primers for the detection of harmful microorganisms, such as Salmonella, Cronobacter, Staphylococcus, and Listeria, as well as beneficial microorganisms like Lactobacillus. Additionally, the review discusses the applicability, advantages, limitations, and future directions of pan-genome analysis for primer design. A comparative overview of bioinformatics tools, recent trends, and verification methods is also provided, offering valuable insights for researchers interested in leveraging pan-genome analysis for advanced primer design.},
}

@article {pmid40228902,
year = {2025},
author = {Rausch, T and Marschall, T and Korbel, JO},
title = {The impact of long-read sequencing on human population-scale genomics.},
journal = {Genome research},
volume = {35},
number = {4},
pages = {593-598},
doi = {10.1101/gr.280120.124},
pmid = {40228902},
issn = {1549-5469},
mesh = {Humans ; *Genomics/methods ; *Genome, Human ; *High-Throughput Nucleotide Sequencing/methods ; *Sequence Analysis, DNA/methods ; Genomic Structural Variation ; DNA Methylation ; *Genetics, Population ; },
abstract = {Long-read sequencing technologies, particularly those from Pacific Biosciences and Oxford Nanopore Technologies, are revolutionizing genome research by providing high-resolution insights into complex and repetitive regions of the human genome that were previously inaccessible. These advances have been particularly enabling for the comprehensive detection of genomic structural variants (SVs), which is critical for linking genotype to phenotype in population-scale and rare disease studies, as well as in cancer. Recent developments in sequencing throughput and computational methods, such as pangenome graphs and haplotype-resolved assemblies, are paving the way for the future inclusion of long-read sequencing in clinical cohort studies and disease diagnostics. DNA methylation signals directly obtained from long reads enhance the utility of single-molecule long-read sequencing technologies by enabling molecular phenotypes to be interpreted, and by allowing the identification of the parent of origin of de novo mutations. Despite this recent progress, challenges remain in scaling long-read technologies to large populations due to cost, computational complexity, and the lack of tools to facilitate the efficient interpretation of SVs in graphs. This perspective provides a succinct review on the current state of long-read sequencing in genomics by highlighting its transformative potential and key hurdles, and emphasizing future opportunities for advancing the understanding of human genetic diversity and diseases through population-scale long-read analysis.},
}

Humans
*Genomics/methods
*Genome, Human
*High-Throughput Nucleotide Sequencing/methods
*Sequence Analysis, DNA/methods
Genomic Structural Variation
DNA Methylation
*Genetics, Population

@article {pmid40226526,
year = {2025},
author = {Ren, X and Liu, X and Che, Y and Yang, L and Mao, Y and Li, M and Sun, Z and Bai, X and Gao, H and Wang, Y and Wang, D},
title = {Serotype Distribution, Virulence, and Antibiotic Resistance Genomic Characterization of Group B Streptococcus - China, 1998-2024.},
journal = {China CDC weekly},
volume = {7},
number = {13},
pages = {413-421},
pmid = {40226526},
issn = {2096-7071},
abstract = {INTRODUCTION: Streptococcus agalactiae, or group B Streptococcus (GBS), can cause severe infections in humans, yet comprehensive genomic characterization from China remains limited. This study presents an extensive genomic analysis of GBS isolates collected in China from 1998 to 2024.

METHODS: GBS genomes were obtained from public databases and through de novo sequencing. Serotype confirmation was conducted via pan-genomic analysis, phylogenetic relationships were established using maximum-likelihood methodology, and virulence and antibiotic resistance genes were identified through the Virulence Factor Database and Comprehensive Antibiotic Resistance Database. Statistical analyses were performed using SPSS 26.0, primarily employing Fisher's exact tests.

RESULTS: Analysis of 747 GBS genomes revealed eight serotypes (Ia, Ib, II, III, IV, V, VI, VII) and nontypeable strains. Serotypes III, Ib, Ia, V, and II constituted 96.65% of all isolates. GBS prevalence remained low from 1998-2011 but increased substantially after 2012. Geographic distribution demonstrated significant regional heterogeneity. Phylogenetic analysis categorized the 747 genomes into five distinct lineages, with lineage 5 being predominant. Six virulence factor categories encompassing 56 virulence-associated genes were identified, with 33 genes present in nearly all genomes. Twenty-seven antibiotic resistance genes spanning nine drug classes were detected, particularly those conferring resistance to peptides and macrolide antibiotics, indicating widespread antimicrobial resistance mechanisms in GBS.

CONCLUSIONS: GBS infections in China exhibit serotype distributions similar to global patterns but with notable regional variations. This comprehensive genomic characterization provides critical insights for developing targeted prevention strategies and treatment approaches for GBS infections in China.},
}

@article {pmid40224327,
year = {2025},
author = {Nakandala, U and Furtado, A and Henry, RJ},
title = {Citrus genomes: past, present and future.},
journal = {Horticulture research},
volume = {12},
number = {5},
pages = {uhaf033},
pmid = {40224327},
issn = {2662-6810},
abstract = {Over the past decade, genome sequencing and assembly approaches have been greatly improved, resulting in the assembly of many genomes for citrus, including wild, domesticated, and citrus-related genomes. Improvements in technologies have led to assembled genomes with higher completeness, contiguity, quality, and accuracy that have greatly facilitated annotation and analysis. This review summarizes the evolution of the sequencing, assembly, and annotation technologies leading to citrus genomes over the past 11 years, a comprehensive evaluation of their quality, contiguity, and completeness, and the major findings and applications. Of the 50 genomes now available, 35 have been assembled to chromosome level and 15 to draft level, and 14 were haplotype-resolved assemblies. To date there have been four pangenome-wide studies for citrus. The very recent genomes assembled with long-read sequencing have achieved >99% and >98% assembly and annotation completeness (BUSCO), respectively. However, some early genomes are not of the same high quality as more recently sequenced genomes and would benefit from re-sequencing. A more comprehensive pangenome based upon a larger set of species and genotypes assembled at the haplotype level would allow genomics to deliver the maximum benefits for citrus improvement and research.},
}

@article {pmid40223124,
year = {2025},
author = {Azam, S and Sahu, A and Pandey, NK and Neupane, M and Van Tassell, CP and Rosen, BD and Gandham, RK and Rath, SN and Majumdar, SS},
title = {Constructing a draft Indian cattle pangenome using short-read sequencing.},
journal = {Communications biology},
volume = {8},
number = {1},
pages = {605},
pmid = {40223124},
issn = {2399-3642},
mesh = {Animals ; Cattle/genetics ; *Genome ; Polymorphism, Single Nucleotide ; *Genomics/methods ; Quantitative Trait Loci ; India ; Genetic Variation ; Sequence Analysis, DNA ; High-Throughput Nucleotide Sequencing ; },
abstract = {Indian desi cattle, known for their adaptability and phenotypic diversity, represent a valuable genetic resource. However, a single reference genome often fails to capture the full extent of their genetic variation. To address this, we construct a pangenome for desi cattle by identifying and characterizing non-reference novel sequences (NRNS). We sequence 68 genomes from seven breeds, generating 48.35 billion short reads. Using the PanGenome Analysis (PanGA) pipeline, we identify 13,065 NRNS (~41 Mbp), with substantial variation across the population. Most NRNS were unique to desi cattle, with minimal overlap (4.1%) with the Chinese indicine pangenome. Approximately 40% of NRNS exhibited ancestral origins within the Bos genus and were enriched in genic regions, suggesting functional roles. These sequences are linked to quantitative trait loci for traits such as milk production. The pangenome approach enhances read mapping accuracy, reduces spurious single nucleotide polymorphism calls, and uncovers novel genetic variants, offering a deeper understanding of desi cattle genomics.},
}

Animals
Cattle/genetics
*Genome
Polymorphism, Single Nucleotide
*Genomics/methods
Quantitative Trait Loci
India
Genetic Variation
Sequence Analysis, DNA
High-Throughput Nucleotide Sequencing

@article {pmid40219973,
year = {2025},
author = {Jiang, M and Qian, Q and Lu, M and Chen, M and Fan, Z and Shang, Y and Bu, C and Du, Z and Song, S and Zeng, J and Xiao, J},
title = {PlantPan: A comprehensive multi-species plant pan-genome database.},
journal = {The Plant journal : for cell and molecular biology},
volume = {122},
number = {1},
pages = {e70144},
doi = {10.1111/tpj.70144},
pmid = {40219973},
issn = {1365-313X},
support = {32170669//the National Natural Science Foundation of China/ ; XDA0450000//the Strategic Priority Research Program of the Chinese Academy of Sciences/ ; 2022098//the Youth Innovation Promotion Association of the Chinese Academy of Science/ ; },
mesh = {*Genome, Plant/genetics ; *Databases, Genetic ; *Plants/genetics ; Genetic Variation ; Multigene Family ; },
abstract = {The pan-genome represents the complete genomic diversity of specific species, serving as a valuable resource for studying species evolution, crop domestication, and guiding crop breeding and improvement. While there are several single-species-specific plant pan-genome databases, the availability of multi-species pan-genome databases is limited. Additionally, variations in methods and data types used for plant pan-genome analysis across different databases hinder the comparison and integration of pan-genome information from various projects at multi-species or single-species levels. To tackle this challenge, we introduce PlantPan, a comprehensive database housing the results of pan-genome analysis for 195 genomes from 11 plant species. PlantPan aims to provide extensive information, including gene-centric and sequence-centric pan-genome information, graph-based pan-genome, pan-genome openness profiles, gene functions and its variation characteristics, homologous genes, and gene clusters across different species. Statistically, PlantPan incorporates 9 163 011 genes, 694 191 gene clusters, 526 973 370 genome variations, and 1 616 089 non-redundant genome variation groups at the species level, 33 455,098 genome synteny, and 177 827 non-redundant genome synteny groups at the species level. Regarding functional genes, PlantPan contains 5 222 720 genes related to transcription factors, 395 247 literature-reported resistance genes, 455 748 predicted microbial/disease resistance genes, and 1 612 112 genes related to molecular pathways. In summary, PlantPan is a vital platform for advancing the application of pan-genomes in molecular breeding for crops and evolutionary research for plants.},
}

*Genome, Plant/genetics
*Databases, Genetic
*Plants/genetics
Genetic Variation
Multigene Family

@article {pmid40212029,
year = {2025},
author = {Frias-De-Diego, A and Jara, M and Lanzas, C},
title = {Influence of Sequencing Technology on Pangenome-Level Analysis and Detection of Antimicrobial Resistance Genes in ESKAPE Pathogens.},
journal = {Open forum infectious diseases},
volume = {12},
number = {4},
pages = {ofaf183},
pmid = {40212029},
issn = {2328-8957},
support = {R35 GM134934/GM/NIGMS NIH HHS/United States ; },
abstract = {As sequencing costs decrease, short-read and long-read technologies are indispensable tools for uncovering the genetic drivers behind bacterial pathogen resistance. This study explores the differences between the use of short-read (Illumina) and long-read (Oxford Nanopore Technologies [ONT]) sequencing in detecting antimicrobial resistance (AMR) genes in ESKAPE pathogens (ie, Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter cloacae). Utilizing a dataset of 1385 whole genome sequences and applying commonly used bioinformatic methods in bacterial genomics, we assessed the differences in genomic completeness, pangenome structure, and AMR gene and point mutation identification. Illumina presented higher genome completeness, while ONT identified a broader pangenome. Hybrid assembly outperformed both Illumina and ONT at identifying key AMR genetic determinants, presented results closer to Illumina's completeness, and revealed ONT-like pangenomic content. Notably, Illumina consistently detected more AMR-related point mutations than its counterparts. This highlights the importance of method selection based on research goals, particularly when using publicly available data ranging a wide timespan. Differences were also observed for specific gene classes and bacterial species, underscoring the need for a nuanced understanding of technology limitations. Overall, this study reveals the strengths and limitations of each approach, advocating for the use of Illumina for common AMR analysis, ONT for studying complex genomes and novel species, and hybrid assembly for a more comprehensive characterization, leveraging the benefits of both technologies.},
}

@article {pmid40210717,
year = {2025},
author = {Li, W},
title = {Solanum pan-genome highlights paralog diversification.},
journal = {Nature genetics},
volume = {57},
number = {4},
pages = {774},
doi = {10.1038/s41588-025-02178-2},
pmid = {40210717},
issn = {1546-1718},
}

@article {pmid40210439,
year = {2025},
author = {Smith, BJ and Zhao, C and Dubinkina, V and Jin, X and Zahavi, L and Shoer, S and Moltzau-Anderson, J and Segal, E and Pollard, KS},
title = {Accurate estimation of intraspecific microbial gene content variation in metagenomic data with MIDAS v3 and StrainPGC.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279543.124},
pmid = {40210439},
issn = {1549-5469},
abstract = {Metagenomics has greatly expanded our understanding of the human gut microbiome by revealing a vast diversity of bacterial species within and across individuals. Even within a single species, different strains can have highly divergent gene content, affecting traits such as antibiotic resistance, metabolism, and virulence. Methods that harness metagenomic data to resolve strain-level differences in functional potential are crucial for understanding the causes and consequences of this intraspecific diversity. The enormous size of pangenome references, strain mixing within samples, and inconsistent sequencing depth present challenges for existing tools that analyze samples one at a time. To address this gap, we updated the MIDAS pangenome profiler, now released as version 3, and developed StrainPGC, an approach to strain-specific gene content estimation that combines strain tracking and correlations across multiple samples. We validate our integrated analysis using a complex synthetic community of strains from the human gut and find that StrainPGC outperforms existing approaches. Analyzing a large, publicly available metagenome collection from inflammatory bowel disease patients and healthy controls, we catalog the functional repertoires of thousands of strains across hundreds of species, capturing extensive diversity missing from reference databases. Finally, we apply StrainPGC to metagenomes from a clinical trial of fecal microbiota transplantation for the treatment of ulcerative colitis. We identify two Escherichia coli strains, from two different donors, that are both frequently transmitted to patients but have notable differences in functional potential. StrainPGC and MIDAS v3 together enable precise, intraspecific pangenomic investigations using large collections of metagenomic data without microbial isolation or de novo assembly.},
}

@article {pmid40210437,
year = {2025},
author = {Quah, FX and Almeida, MV and Blumer, M and Yuan, CU and Fischer, B and See, K and Jackson, B and Zatha, R and Rusuwa, B and Turner, GF and Santos, ME and Svardal, H and Hemberg, M and Durbin, R and Miska, E},
title = {Lake Malawi cichlid pangenome graph reveals extensive structural variation driven by transposable elements.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279674.124},
pmid = {40210437},
issn = {1549-5469},
abstract = {Pangenome methods have the potential to uncover hitherto undiscovered sequences missing from established reference genomes, making them useful to study evolutionary and speciation processes in diverse organisms. The cichlid fishes of the East African Rift Lakes represent one of nature's most phenotypically diverse vertebrate radiations, but single-nucleotide polymorphism (SNP)-based studies have revealed little sequence difference, with 0.1%-0.25% pairwise divergence between Lake Malawi species. These were based on aligning short reads to a single linear reference genome and ignored the contribution of larger-scale structural variants (SVs). We constructed a pangenome graph that integrates six new and two existing long-read genome assemblies of Lake Malawi haplochromine cichlids. This graph intuitively represents complex and nested variation between the genomes and reveals that the SV landscape is dominated by large insertions, many exclusive to individual assemblies. The graph incorporates a substantial amount of extra sequence across seven species, the total size of which is 33.1% longer than that of a single cichlid genome. Approximately 4.73% to 9.86% of the assembly lengths are estimated as interspecies structural variation between cichlids, suggesting substantial genomic diversity underappreciated in SNP studies. Although coding regions remain highly conserved, our analysis uncovers a significant proportion of SV sequences as transposable element (TE) insertions, especially DNA, LINE, and LTR TEs. These findings underscore that the cichlid genome is shaped both by small-nucleotide mutations and large, TE-derived sequence alterations, both of which merit study to understand their interplay in cichlid evolution.},
}

@article {pmid40203032,
year = {2025},
author = {Timilsina, S and Iruegas-Bocardo, F and Jibrin, MO and Sharma, A and Subedi, A and Kaur, A and Minsavage, GV and Huguet-Tapia, JC and Klein-Gordon, J and Adhikari, P and Adhikari, TB and Cirvilleri, G and de la Barrera, LBT and Bernal, E and Creswell, TC and Doan, TTK and Coutinho, TA and Egel, DS and Félix-Gastélum, R and Francis, DM and Kebede, M and Ivey, ML and Louws, FJ and Luo, L and Maynard, ET and Miller, SA and Nguyen, NTT and Osdaghi, E and Quezado-Duval, AM and Roach, R and Rotondo, F and Ruhl, GE and Shutt, VM and Thummabenjapone, P and Trueman, C and Roberts, PD and Jones, JB and Vallad, GE and Goss, EM},
title = {Diversification of an emerging bacterial plant pathogen; insights into the global spread of Xanthomonas euvesicatoria pv. perforans.},
journal = {PLoS pathogens},
volume = {21},
number = {4},
pages = {e1013036},
doi = {10.1371/journal.ppat.1013036},
pmid = {40203032},
issn = {1553-7374},
abstract = {Emerging and re-emerging plant diseases continue to present multifarious threats to global food security. Considerable recent efforts are therefore being channeled towards understanding the nature of pathogen emergence, their spread and evolution. Xanthomonas euvesicatoria pv. perforans (Xep), one of the causal agents of bacterial spot of tomato, rapidly emerged and displaced other bacterial spot xanthomonads in many tomato production regions around the world. In less than three decades, it has become a dominant xanthomonad pathogen in tomato production systems across the world and presents a compelling example for understanding diversification of recently emerged bacterial plant pathogens. Although Xep has been continuously monitored in Florida since its discovery, the global population structure and evolution at the genome-scale is yet to be fully explored. The objectives of this work were to determine genetic diversity globally to ascertain if different tomato production regions contain genetically distinct Xep populations, to examine genetic relatedness of strains collected in tomato seed production areas in East Asia and other production regions, and to evaluate variation in type III secretion effectors, which are critical pathogenicity and virulence factors, in relationship to population structure. We used genome data from 270 strains from 13 countries for phylogenetic analysis and characterization of type III effector gene diversity among strains. Our results showed notable genetic diversity in the pathogen. We found genetically similar strains in distant tomato production regions, including seed production regions, and diversification over the past 100 years, which is consistent with intercontinental dissemination of the pathogen in hybrid tomato production chains. Evolution of the Xep pangenome, including the acquisition and loss of type III secreted effectors, is apparent within and among phylogenetic lineages. The apparent long-distance movement of the pathogen, together with variants that may not yet be widely distributed, poses risks of emergence of new variants in tomato production.},
}

@article {pmid40202301,
year = {2025},
author = {Mahillon, M and Debonneville, C and Groux, R and Roquis, D and Brodard, J and Faoro, F and Foissac, X and Schumpp, O and Dittmer, J},
title = {From insect endosymbiont to phloem colonizer: comparative genomics unveils the lifestyle transition of phytopathogenic Arsenophonus strains.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0149624},
doi = {10.1128/msystems.01496-24},
pmid = {40202301},
issn = {2379-5077},
abstract = {UNLABELLED: Bacteria infecting the plant phloem represent a growing threat worldwide. While these organisms often resist in vitro culture, they multiply both in plant sieve elements and hemipteran vectors. Such cross-kingdom parasitic lifestyle has emerged in diverse taxa via distinct ecological routes. In the genus Arsenophonus, the phloem pathogens "Candidatus Arsenophonus phytopathogenicus" (Ap) and "Ca. Phlomobacter fragariae" (Pf) have evolved from insect endosymbionts, but the genetic mechanisms underlying this transition have not been explored. To fill this gap, we obtained the genomes of both strains from insect host metagenomes. The resulting assemblies are highly similar in size and functional repertoire, rich in viral sequences, and closely resemble the genomes of several facultative endosymbiotic Arsenophonus strains of sap-sucking hemipterans. However, a phylogenomic analysis demonstrated distinct origins, as Ap belongs to the "Triatominarum" clade, whereas Pf represents a distant species. We identified a set of orthologs encoded only by Ap and Pf in the genus, including hydrolytic enzymes likely targeting plant substrates. In particular, both bacteria encode putative plant cell wall-degrading enzymes and cysteine peptidases related to xylellain, a papain-like peptidase from Xylella fastidiosa, for which close homologs are found in diverse Pseudomonadota infecting the plant vasculature. In silico predictions and gene expression analyses further support a role during phloem colonization for several of the shared orthologs. We conclude that the double emergence of phytopathogenicity in Arsenophonus may have been mediated by a few horizontal gene transfer events, involving genes acquired from other Pseudomonadota, including phytopathogens.

IMPORTANCE: We investigate the genetic mechanisms of a transition in bacterial lifestyle. We focus on two phloem pathogens belonging to the genus Arsenophonus: "Candidatus Arsenophonus phytopathogenicus" and "Ca. Phlomobacter fragariae." Both bacteria cause economically significant pathologies, and they have likely emerged among facultative insect endosymbionts. Our genomic analyses show that both strains are highly similar to other strains of the genus associated with sap-sucking hemipterans, suggesting a recent lifestyle shift. Importantly, although the phytopathogenic Arsenophonus strains belong to distant clades, they share a small set of orthologs unique in the genus pangenome. We provide evidence that several of these genes produce hydrolytic enzymes that are secreted and may target plant substrates. The acquisition and exchange of these genes may thus have played a pivotal role in the lifestyle transition of the phytopathogenic Arsenophonus strains.},
}

@article {pmid40198110,
year = {2025},
author = {Chowdhury, G and Hoshiko, Y and Okuno, M and Kitahara, K and Albert, MJ and Miyoshi, SI and Ogura, Y and Dutta, S and Ramamurthy, T and Mukhopadhyay, AK},
title = {Whole-genome-based characterization of Escherichia albertii strains isolated from paediatric diarrhoeal cases in Kolkata, India.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
pmid = {40198110},
issn = {2057-5858},
mesh = {Humans ; *Diarrhea/microbiology ; Phylogeny ; India ; Virulence Factors/genetics ; *Escherichia/genetics/isolation & purification/drug effects/classification/pathogenicity ; *Genome, Bacterial ; Whole Genome Sequencing ; Feces/microbiology ; Microbial Sensitivity Tests ; Child, Preschool ; Infant ; Child ; Anti-Bacterial Agents/pharmacology ; Male ; Female ; Drug Resistance, Bacterial/genetics ; Bacterial Toxins/genetics ; },
abstract = {Escherichia albertii is a Gram-negative facultative anaerobic bacterium that causes diarrhoea in humans. This study shows the isolation of E. albertii from hospitalized paediatric diarrhoeal cases and genome-based characteristics with putative virulence factors and antimicrobial resistance. E. albertii isolates were identified by species-specific PCR, targeting the gene encoding cytolethal distending toxin (Ea-cdt). The genome of E. albertii was sequenced to identify (i) genes encoding virulence factors (ii) antibiotic resistance-encoding genes, including the mobile genetic elements and (iii) core gene-based phylogenetic relationships and pan-genome features. A total of 10 (1.2%) E. albertii isolates were isolated from 854 faecal samples, of which 6 (60%) were found as the sole pathogen and the remaining 4 (40%) were identified along with other pathogens, such as enteroaggregative Escherichia coli, rotavirus and adenovirus. Patients from whom E. albertii was isolated presented cholera-like diarrhoea, i.e. with watery stool (60%) with moderate dehydration (100%), fever (20%) and abdominal pain (20%). The antimicrobial susceptibility testing of E. albertii showed that most of the isolates were susceptible or reduced susceptible to most of the antibiotics except resistance to erythromycin (80%), tetracycline (50%), nalidixic acid (40%), ampicillin (40%), doxycycline (30%) and ceftriaxone (20%). In the whole-genome sequence, E. albertii isolates revealed several virulence-encoding genes, namely the intimin (eae, E. coli attaching and effacing), the cytolethal distending toxin type II subunit A (cdt-IIA), adhesion (paa, porcine attaching- and effacing-associated), non-LEE (locus of enterocyte effacement) encoded effector A (nleA) and antimicrobial resistance genes (ARGs) conferring resistance to tetracycline (tetA, tetR), sulphonamides (sul2), fluoroquinolones (qnrS) and beta-lactamases (bla CTX-M, blaTEM). The SNP-based phylogenetic analysis of 647 whole genomes of E. albertii isolates from the National Center for Biotechnology Information databases did not reveal any comparable clustering pattern based on the biological source and place of isolation. The genome of some of the E. albertii was closely related to those of the isolates from China and the United Kingdom. The PFGE patterns revealed that most of the E. albertii isolates were distinct clones. This study reports on the extensive genome analysis of diarrhoea-associated E. albertii harbouring multiple virulence and ARGs.},
}

Humans
*Diarrhea/microbiology
Phylogeny
India
Virulence Factors/genetics
*Escherichia/genetics/isolation & purification/drug effects/classification/pathogenicity
*Genome, Bacterial
Whole Genome Sequencing
Feces/microbiology
Microbial Sensitivity Tests
Child, Preschool
Infant
Child
Anti-Bacterial Agents/pharmacology
Male
Female
Drug Resistance, Bacterial/genetics
Bacterial Toxins/genetics

@article {pmid40197242,
year = {2025},
author = {Kong, PF and Yan, YH and Duan, YT and Fang, YT and Dou, Y and Xu, YH and Xu, DZ},
title = {Comparative genomic analysis of Helicobacter pylori isolates from gastric cancer and gastritis in China.},
journal = {BMC cancer},
volume = {25},
number = {1},
pages = {628},
pmid = {40197242},
issn = {1471-2407},
support = {81972213//National Natural Science Foundation of China/ ; },
mesh = {*Stomach Neoplasms/microbiology ; Humans ; *Helicobacter pylori/genetics/isolation & purification/pathogenicity ; *Gastritis/microbiology ; China/epidemiology ; *Helicobacter Infections/microbiology ; *Genome, Bacterial ; Genomics/methods ; Phylogeny ; Virulence Factors/genetics ; Whole Genome Sequencing ; Male ; Female ; Bacterial Proteins/genetics ; Middle Aged ; },
abstract = {BACKGROUND: This study aimed to explore and compare the genomic characteristics and pathogenicity of Helicobacter pylori (H. pylori) strains derived from the gastric cancer (GC) and gastritis in the Chinese population.

METHODS: We performed whole genome sequencing on 12 H. pylori strains obtained from GC and gastritis patients in China. Additionally, we retrieved sequencing data for 20 H. pylori strains from various regions worldwide from public databases to serve as reference genomes. An evolutionary tree was constructed based on comparative genomics, and we analyzed the differences in virulence factors (VFs) and gene functions.

RESULTS: In the GC strains, we identified 1,544 to 1,640 coding genes, with a total length ranging from 1,549,790 to 1,605,249 bp. In the gastritis strains, we found 1,552 to 1,668 coding genes, with a total length spanning from 1,552,426 to 1,665,981 bp. The average length of coding genes was approximately 1,594 (90.91%) for GC strains and 1,589 (90.81%) for gastritis strains. We observed a high degree of consistency in the VFs predicted for both cohorts; however, there was a significant difference in their cagA status. Clustering analysis showed significant core single nucleotide polymorphisms (SNPs) differences between GC and gastritis strains, but no major differences in homologous proteins or gene islands. Subsequent pan-genomic and Average Nucleotide Identity (ANI) analyses indicated high homology among GC, gastritis, and other reference H. pylori strains. Furthermore, gene function annotation results showed substantial similarity in gene functions between the H. pylori strains from GC and gastritis patients, with specific functions primarily concentrated in metabolic processes, transcription, and DNA repair.

CONCLUSIONS: H. pylori strains derived from GC and gastritis patients exhibit differences in virulence factors and SNPs, yet they demonstrate high genomic homology across other levels in the Chinese population.},
}

*Stomach Neoplasms/microbiology
Humans
*Helicobacter pylori/genetics/isolation & purification/pathogenicity
*Gastritis/microbiology
China/epidemiology
*Helicobacter Infections/microbiology
*Genome, Bacterial
Genomics/methods
Phylogeny
Virulence Factors/genetics
Whole Genome Sequencing
Male
Female
Bacterial Proteins/genetics
Middle Aged

@article {pmid40193344,
year = {2025},
author = {Javadzadeh, S and Adamson, A and Park, J and Jo, SY and Ding, YC and Bakhtiari, M and Bansal, V and Neuhausen, SL and Bafna, V},
title = {Analysis of targeted and whole genome sequencing of PacBio HiFi reads for a comprehensive genotyping of gene-proximal and phenotype-associated Variable Number Tandem Repeats.},
journal = {PLoS computational biology},
volume = {21},
number = {4},
pages = {e1012885},
pmid = {40193344},
issn = {1553-7358},
mesh = {*Minisatellite Repeats/genetics ; Humans ; Phenotype ; *Whole Genome Sequencing/methods ; Genotype ; *Genotyping Techniques/methods ; *Genome, Human/genetics ; *High-Throughput Nucleotide Sequencing/methods ; *Sequence Analysis, DNA/methods ; Computational Biology ; },
abstract = {Variable Number Tandem repeats (VNTRs) refer to repeating motifs of size greater than five bp. VNTRs are an important source of genetic variation, and have been associated with multiple Mendelian and complex phenotypes. However, the highly repetitive structures require reads to span the region for accurate genotyping. Pacific Biosciences HiFi sequencing spans large regions and is highly accurate but relatively expensive. Therefore, targeted sequencing approaches coupled with long-read sequencing have been proposed to improve efficiency and throughput. In this paper, we systematically explored the trade-off between targeted and whole genome HiFi sequencing for genotyping VNTRs. We curated a set of 10 , 787 gene-proximal (G-)VNTRs, and 48 phenotype-associated (P-)VNTRs of interest. Illumina reads only spanned 46% of the G-VNTRs and 71% of P-VNTRs, motivating the use of HiFi sequencing. We performed targeted sequencing with hybridization by designing custom probes for 9,999 VNTRs and sequenced 8 samples using HiFi and Illumina sequencing, followed by adVNTR genotyping. We compared these results against HiFi whole genome sequencing (WGS) data from 28 samples in the Human Pangenome Reference Consortium (HPRC). With the targeted approach only 4,091 (41%) G-VNTRs and only 4 (8%) of P-VNTRs were spanned with at least 15 reads. A smaller subset of 3,579 (36%) G-VNTRs had higher median coverage of at least 63 spanning reads. The spanning behavior was consistent across all 8 samples. Among 5,638 VNTRs with low-coverage (< 15), 67% were located within GC-rich regions (> 60%). In contrast, the 40X WGS HiFi dataset spanned 98% of all VNTRs and 49 (98%) of P-VNTRs with at least 15 spanning reads, albeit with lower coverage. Spanning reads were sufficient for accurate genotyping in both cases. Our findings demonstrate that targeted sequencing provides consistently high coverage for a small subset of low-GC VNTRs, but WGS is more effective for broad and sufficient sampling of a large number of VNTRs.},
}

*Minisatellite Repeats/genetics
Humans
Phenotype
*Whole Genome Sequencing/methods
Genotype
*Genotyping Techniques/methods
*Genome, Human/genetics
*High-Throughput Nucleotide Sequencing/methods
*Sequence Analysis, DNA/methods
Computational Biology

@article {pmid40192321,
year = {2025},
author = {Zhang, S and Huang, Y and Nachawati, R and Huber, P and Walther, G and Gregor, L and Vilotijević, I and Stallforth, P},
title = {Pangenome Analysis of the Plant Pathogen Pseudomonas syringae Reveals Unique Natural Products for Niche Adaptation.},
journal = {Angewandte Chemie (International ed. in English)},
volume = {},
number = {},
pages = {e202503679},
doi = {10.1002/anie.202503679},
pmid = {40192321},
issn = {1521-3773},
abstract = {Pseudomonas syringae is a soil-dwelling bacterium that exhibits remarkable niche adaptability and it is known for its devastating impact as a plant pathogen. This bacterium has an outstanding capability to produce a wide array of biologically active natural products. P. syringae coexists with amoebal predators and fungal strains, which drives the production of secondary metabolites for predator evasion in addition to niche adaptation. In this study, we conducted a broad pangenomic analysis of 18 taxonomically distinct P. syringae strains leading to the identification of 231 biosynthetic gene clusters (BGCs). Among these, nonribosomal peptide synthetases (NRPSs) were particularly abundant, indicating their potential significance within this ecological context. We discovered and elucidated the structures of two novel classes of bioactive compounds, the syrilipamides and chlorosecimides. Furthermore, a bioinformatic analysis enabled the identification of an undescribed halogenase, SecA, essential for the chlorination of secimide A. We observed that syrilipamides and secimides and in particular mixtures thereof exhibit amoebicidal activities. Additionally, secimides showed selective antifungal activity. These findings provide valuable insights into the ecological roles of P. syringae natural products and highlight their potential for biotechnological applications and therapeutic development.},
}

@article {pmid40189201,
year = {2025},
author = {Cheng, H and Kong, L and Zhu, K and Zhao, H and Li, X and Zhang, Y and Ning, W and Jiang, M and Song, B and Cheng, S},
title = {Structural variation-based and gene-based pangenome construction reveals untapped diversity of hexaploid wheat.},
journal = {Journal of genetics and genomics = Yi chuan xue bao},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jgg.2025.03.015},
pmid = {40189201},
issn = {1673-8527},
abstract = {Increasing number of structural variations (SVs) have been identified as causative mutations for diverse agronomic traits. However, the systematic exploration of SVs quantity, distribution and contribution in wheat was lacking. Here, we report high-quality gene-based and SV-based pangenomes comprising 22 hexaploid wheat assemblies showing a wide range of chromosome size, gene number, and TE component, which indicates their representativeness of wheat genetic diversity. Pan-gene analyses uncover 140,261 distinct gene families, of which only 23.2% are shared in all accessions. Moreover, we built a ∼16.15 Gb graph pangenome containing 695,897 bubbles, intersecting 5,132 genes and 230,307 cis-regulatory regions. Pairwise genome comparisons identified ∼1,978,221 non-redundant SVs and 497 SV hotspots. Notably, the density of bubbles as well as SVs show remarkable aggregation in centromeres, which probably play an important role in chromosome plasticity and stability. As for functional SVs exploration, we identify 2,769 SVs with absolute relative frequency differences exceeding 0.7 between spring and winter growth habit groups. Additionally, several reported functional genes in wheat display complex structural graphs, for example PPD-A1, VRT-A2, and TaNAAT2-A. These findings deepen our understanding of wheat genetic diversity, providing valuable graphical pangenome and variation resources to improve the efficiency of genome-wide association mapping in wheat.},
}

@article {pmid40188140,
year = {2025},
author = {Yang, C and Zheng, YX and Gu, HY and Chen, H and Li, W and Li, F and Bi, YW and Chen, J and Wang, FK and Sun, QQ and Meng, HB and Wu, ZH and Yu, S and Gu, J and Cheng, Y},
title = {Genomic characteristics, virulence potential, antimicrobial resistance profiles, and phylogenetic insights into Nocardia cyriacigeorgica.},
journal = {Annals of clinical microbiology and antimicrobials},
volume = {24},
number = {1},
pages = {22},
pmid = {40188140},
issn = {1476-0711},
support = {No.20211116//Hebei Medical Science Research Project/ ; No.H2022505004//Hebei Natural Science Foundation/ ; No.31200142//National Natural Science Foundation of China/ ; },
mesh = {*Nocardia/genetics/pathogenicity/drug effects/classification/isolation & purification ; *Phylogeny ; Humans ; *Nocardia Infections/microbiology ; *Genome, Bacterial ; Virulence Factors/genetics ; Anti-Bacterial Agents/pharmacology ; Virulence/genetics ; *Drug Resistance, Bacterial/genetics ; Whole Genome Sequencing ; Genomics ; Microbial Sensitivity Tests ; },
abstract = {BACKGROUND: Nocardia cyriacigeorgica, an opportunistic pathogen, is increasingly implicated in human infections. This pathogen predominantly causes pulmonary infections, leading to acute, subacute, or chronic necrotizing suppurative lesions, in severe cases, may progress to disseminated infections. Effective clinical diagnosis, prevention, and treatment strategies require a thorough understanding of its biological characteristics and pathogenic mechanisms. However, despite the rising incidence of nocardial diseases, research on the pathogenicity of N. cyriacigeorgica remains limited, primarily focusing on case reports and epidemiological studies. This study aimed to provide a comprehensive analysis of the genomic features, phylogenetic relationships, antimicrobial resistance profiles, and candidate virulence factors of N. cyriacigeorgica strains to inform future investigations into its pathogenesis.

METHODS: Whole-genome sequencing was conducted on five N. cyriacigeorgica strains isolated from patients with pulmonary infection at our hospital. This analysis utilized a combination of second-generation Illumina HiSeq and third-generation PacBio sequencing technologies. Additionally, publicly available genomic data from 58 strains in the National Center Biotechnology Information database were integrated, resulting in a dataset of 63 genomes. These genomes were subjected to comparative genomic analyses, including phylogenetic reconstruction, pan-genome evaluation, and gene distribution assessments.

RESULTS: Phylogenetic analysis identified five major clades within N. cyriacigeorgica. ANI analysis further subdivided clade B into five distinct subgroups. Pan-genome analysis revealed clade-specific orthogroups in the distribution of genes assigned to Clusters of Orthologous Groups, with clade A containing the highest number of clade-specific gene families. Comparative genomic analysis uncovered several potential pathogenic genes implicated in host cell invasion, phagosomal maturation arrest, and intracellular survival within macrophages, which were conserved across all analyzed strains. Notable differences in the distribution of enterobactin-encoding genes were observed among the clades. The mce3C gene also displayed variable distributions across clades; however, no correlation was established between its presence and strain source. Among the 63 strains, 27 were found to harbor both mce3C and mce4F genes, which were categorized into five distinct patterns. Furthermore, antibiotic resistance genes, including VanSO, VanRO, erm(O)-Irm, srmB, ermH, bcl, bla1, and cmIR, demonstrated clade-specific distribution patterns. Notably, the genes erm(O)-Irm, srmB, and ermH were associated with the isolation origin of the strains.

CONCLUSIONS: This study provides a comprehensive evaluation of the genomic characteristics, potential virulence factors, antimicrobial resistance genes, and phylogenetic relationships of N. cyriacigeorgica. The findings offer valuable insights into the mechanisms underlying intracellular survival, replication within macrophages, and pathogen-host interactions in N. cyriacigeorgica infections. These results establish a foundation for future research into the pathogenesis and clinical management of N. cyriacigeorgica.},
}

*Nocardia/genetics/pathogenicity/drug effects/classification/isolation & purification
*Phylogeny
Humans
*Nocardia Infections/microbiology
*Genome, Bacterial
Virulence Factors/genetics
Anti-Bacterial Agents/pharmacology
Virulence/genetics
*Drug Resistance, Bacterial/genetics
Whole Genome Sequencing
Genomics
Microbial Sensitivity Tests

@article {pmid40186911,
year = {2025},
author = {Du, Q and Li, R},
title = {Super pan-genome-wide analysis of Hordeum WOX genes and identification of key members conferring salt stress tolerance.},
journal = {Plant physiology and biochemistry : PPB},
volume = {223},
number = {},
pages = {109874},
doi = {10.1016/j.plaphy.2025.109874},
pmid = {40186911},
issn = {1873-2690},
abstract = {The WUSCHEL-related homeobox (WOX) is a transcription factor family specific to plants, playing a key role in the initiation and maintenance of meristematic tissue, organ formation and response to abiotic stress. Here we identified 14-15 WOX genes in four Hordeum species, conducted their phylogenetic tree, determined their chromosome locations and gene structures, and analyzed their collinearity and cis-acting elements in promoters. Presence Absence Variation (PAV) analysis revealed that certain WOX genes in the four Hordeum species were lost and expanded. Duplication analysis discovered five types of duplications contributing to the formation of WOX genes, with dispersed duplication (DSD) being the main type in four Hordeum species. WOXs belonging to DSD exhibited a high number of long terminal repeat retrotransposons (LTR-RTs), indicating the potential role of LTR-RTs in the formation of WOX genes of the DSD type. Evaluation of Ka/Ks values showed that all WOX genes have undergone purification selection, with varying degrees among different clades of WOX genes. Furthermore, through pan-transcriptome analysis and quantitative experiments, we identified a common gene clade and the WOX13 co-expression networks responding to saline stress. Survival ratio statistics of Arabidopsis thaliana complementation lines under salt treatment suggested that HvWOX13 may play a crucial role in regulating salt tolerance. These findings provide new insights into evolutionary studies of WOX gene family and offer valuable gene resources for breeding crops with enhanced salt stress resistance.},
}

@article {pmid40181465,
year = {2025},
author = {Feng, X and Liu, Y and Xu, S and Ma, J and Yuan, H and Wang, H and Hu, J and Jin, S and Liu, S and Zhong, J and Ma, T and Tu, Y},
title = {Functional analysis of Parabacteroides distasonis F4: a novel probiotic strain linked to calf growth and rumen fermentation.},
journal = {Journal of animal science and biotechnology},
volume = {16},
number = {1},
pages = {50},
pmid = {40181465},
issn = {1674-9782},
abstract = {BACKGROUND: Rumen microorganisms are key regulators of ruminant growth and production performance. Identifying probiotic candidates through microbial culturomics presents a promising strategy for improving ruminant production performance. Our previous study identified significant differences in rumen microbial communities of Holstein calves with varying average daily gain (ADG). This study aims to identify a target strain based on the findings from multi-omics analysis and literature review, isolating and evaluating the target microbial strains from both the rumen and hindgut contents for their probiotic potential.

RESULTS: Parabacteroides distasonis, a strain closely associated with ADG, was successfully isolated from calf rumen content cultured with Fastidious Anaerobe Agar (FAA) medium and named Parabacteroides distasonis F4. Whole-genome sequencing and pan-genome analysis showed that P. distasonis F4 possesses a core functional potential for carbohydrate and amino acid metabolism, with the ability to produce propionate, acetate, and lactate. The results of targeted and untargeted metabolomics further validated the organic acid production and metabolic pathways of P. distasonis F4. An in vitro simulated rumen fermentation test showed that supplementation with P. distasonis F4 significantly altered rumen microbial community structure and increased the molar proportions of propionate and butyrate in the rumen. Furthermore, an in vivo study demonstrated that dietary supplementation with P. distasonis F4 significantly increased the ADG of pre-weaning calves.

CONCLUSIONS: This study represents the first isolation of P. distasonis F4 from rumen, highlighting its potential as a probiotic strain for improving rumen development and growth performance in ruminants.},
}

@article {pmid40180959,
year = {2025},
author = {Yang, L and He, W and Zhu, Y and Lv, Y and Li, Y and Zhang, Q and Liu, Y and Zhang, Z and Wang, T and Wei, H and Cao, X and Cui, Y and Zhang, B and Chen, W and He, H and Wang, X and Chen, D and Liu, C and Shi, C and Liu, X and Xu, Q and Yuan, Q and Yu, X and Qian, H and Li, X and Zhang, B and Zhang, H and Leng, Y and Zhang, Z and Dai, X and Guo, M and Jia, J and Qian, Q and Shang, L},
title = {GWAS meta-analysis using a graph-based pan-genome enhanced gene mining efficiency for agronomic traits in rice.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {3171},
pmid = {40180959},
issn = {2041-1723},
support = {32188102 and 32372148//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
mesh = {*Oryza/genetics ; *Genome-Wide Association Study/methods ; *Quantitative Trait Loci/genetics ; *Genome, Plant ; Polymorphism, Single Nucleotide ; Phenotype ; Data Mining/methods ; },
abstract = {Genome-wide association studies (GWASs) encounter limitations from population structure and sample size, restricting their efficacy. Though meta-analysis mitigates these issues, its application in rice research remains limited. Here, we report a large-scale meta-analysis of six independent GWAS experiments in rice to mine genes for key agronomic traits. By integrating a rice pan-genome graph to identify structural variants, we obtained 6,604,898 SNP and 42,879 PAV variants for the six panels (7765 accessions). Meta-analysis significantly improved quantitative trait loci (QTLs) detection and hidden heritability by up to 43 and 37.88%, respectively. Among 156 QTLs identified for six agronomic traits, 116 were exclusively detected through meta-analysis, highlighting its superior resolution. Two novel QTLs governing grain width and length were functionally validated through CRISPR/Cas9, confirming their candidate genes. Our findings underscore the utility and potential advantages of this pan-genome-based meta-GWAS approach, providing a scalable model for efficiently gene mining from diverse rice germplasms.},
}

*Oryza/genetics
*Genome-Wide Association Study/methods
*Quantitative Trait Loci/genetics
*Genome, Plant
Polymorphism, Single Nucleotide
Phenotype
Data Mining/methods

@article {pmid40178590,
year = {2025},
author = {Yildiz, G and Zanini, SF and Weber, S and Kopalli, V and Kox, T and Abbadi, A and Snowdon, RJ and Golicz, AA},
title = {Graphical pangenomics-enabled characterization of structural variant impact on gene expression in Brassica napus.},
journal = {TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik},
volume = {138},
number = {4},
pages = {91},
pmid = {40178590},
issn = {1432-2242},
support = {Sofja Kovalevskaja Award//Alexander von Humboldt-Stiftung/ ; 031B0187//Bundesministerium für Bildung und Forschung/ ; LOEWE Start Professorship//Hessisches Ministerium für Wissenschaft und Kunst/ ; },
mesh = {*Brassica napus/genetics ; *Quantitative Trait Loci ; *Gene Expression Regulation, Plant ; DNA Transposable Elements ; Genotype ; *Genome, Plant ; *Genomic Structural Variation ; Gene Expression Profiling ; },
abstract = {Pangenome graphs enable population-scale genotyping and improve expression analysis, revealing that structural variations (SVs), particularly transposable elements (TEs), significantly contribute to gene expression variation in winter oilseed rape. Structural variations (SVs) impact important traits, from yield to flowering behaviour and stress responses. Pangenome graphs capture population-level diversity, including SVs, within a single data structure and provide a robust framework for downstream applications. They have the potential to serve as unbiased references for SV genotyping, pan-transcriptomic analyses, and association studies, offering significant advantages over single reference genomes. However, their full potential for expression quantitative trait locus (eQTL) analysis is yet to be explored. We combined long and short-read whole genome sequencing data with expression profiling of Brassica napus (oilseed rape) to assess the impact of SVs on gene expression regulation and explored the utility of pangenome graphs for eQTL analysis. Over 90,000 SVs were discovered from 57 long-read datasets. Pangenome graph as reference was evaluated and used for SV genotyping with short reads and transcript expression quantification. Using SVs genotyped from the graph and 100 expression datasets, we identified 267 gene proximal (cis) SV-eQTLs. Over 70% of eQTL-SVs had similarity to transposable elements (TEs), especially Helitrons. The highest proportion of cis-eQTL-SVs were found in promoter regions. About a third of transcripts whose expression was associated with SVs, had no associated SNPs, suggesting that including SVs allows capturing of relationship which would be missed in SNP-only analyses. This study demonstrated that pangenome graphs provide a unifying framework for eQTL analysis by allowing population-scale SV genotyping and gene expression quantification. We also showed that SVs make an appreciable contribution to gene expression variation in winter oilseed rape.},
}

*Brassica napus/genetics
*Quantitative Trait Loci
*Gene Expression Regulation, Plant
DNA Transposable Elements
Genotype
*Genome, Plant
*Genomic Structural Variation
Gene Expression Profiling

@article {pmid40177483,
year = {2025},
author = {Sousa, EG and Campos, GM and Viana, MVC and Gomes, GC and Rodrigues, DLN and Aburjaile, FF and Fonseca, BB and de Araújo, MRB and da Costa, MM and Guedon, E and Brenig, B and Soares, S and Azevedo, V},
title = {The research on the identification, taxonomy, and comparative genomics analysis of nine Bacillus velezensis strains significantly contributes to microbiology, genetics, bioinformatics, and biotechnology.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1544934},
pmid = {40177483},
issn = {1664-302X},
abstract = {INTRODUCTION: Next-generation sequencing (NGS) has played a pivotal role in the advancement of taxonomics, allowing for the accurate identification, differentiation, and reclassification of several bacteria species. Bacillus velezensis is a Gram-positive, facultatively aerobic, spore-forming bacterium known for its antimicrobial and antifungal properties. Strains of this species are highly relevant in agriculture, biotechnology, the food industry, and biomedicine.

METHODS: In this study, we characterized the genomes of nine Bacillus strains isolated from soil in the state of Bahia (Brazil) using NGS with Illumina platform. Identification was performed by Average Nucleotide Identity (ANI) and digital DNA-DNA hybridization (dDDH) analyses, which revealed a match between the genomic information of the isolates and B. velezensis NRRL B-41580, with a variation of 89.3% to 91.8% by dDDH in TYGS and 95% to 98.04% by ANI in GTDBtk.

RESULTS AND DISCUSSION: Two strains, BAC144 and BAC1273, exhibited high similarity to B. amyloliquefaciens subsp. plantarum FZB42. However, the latter strain was subsequently reclassified as B. velezensis. The division pattern observed during identification was confirmed in the phylogenomic analysis, where BAC144 and BAC1273 clustered with Bacillus amyloliquefaciens subsp. plantarum, while the other strains clustered with B. velezensis NRRL B-41580, forming a clade with high genetic similarity, with a bootstrap value of 100%. Furthermore, a synteny analysis demonstrated greater conservation among the strains from this study compared to the reference strain, with the formation of distinct collinear groups. The pangenome analysis revealed an open pangenome, highlighting the genetic diversity within the species. Based on this analysis, a functional annotation was performed to compare exclusive gene repertoires across groups, uncovering distinct adaptations and functional profiles. The identification of bacterial strains belonging to this species is of great importance due to their high applicability. The strains identified in this study underscore the need for more robust taxonomic technologies to accurately classify prokaryotes, which are subject to constant evolutionary changes, requiring the reclassification of several species within the genus Bacillus, many of which are heterotypic synonyms of B. velezensis like Bacillus oryzicola, B. amyloliquefaciens subsp. plantarum and Bacillus methylotrophicus.},
}

@article {pmid40177478,
year = {2025},
author = {Feng, S and Ramachandran, P and Blaustein, RA and Pradhan, AK},
title = {Bioinformatics combined with machine learning unravels differences among environmental, seafood, and clinical isolates of Vibrio parahaemolyticus.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1549260},
pmid = {40177478},
issn = {1664-302X},
abstract = {Vibrio parahaemolyticus is the leading cause of illnesses and outbreaks linked to seafood consumption across the globe. Understanding how this pathogen may be adapted to persist along the farm-to-table supply chain has applications for addressing food safety. This study utilized machine learning to develop robust models classifying genomic diversity of V. parahaemolyticus that was isolated from environmental (n = 176), seafood (n = 975), and clinical (n = 865) sample origins. We constructed a pangenome of the respective genome assemblies and employed random forest algorithm to develop predictive models to identify gene clusters encoding metabolism, virulence, and antibiotic resistance that were associated with isolate source type. Comparison of genomes of all seafood-clinical isolates showed high balanced accuracy (≥0.80) and Area Under the Receiver Operating Characteristics curve (≥0.87) for all of these functional features. Major virulence factors including tdh, trh, type III secretion system-related genes, and four alpha-hemolysin genes (hlyA, hlyB, hlyC, and hlyD) were identified as important differentiating factors in our seafood-clinical virulence model, underscoring the need for further investigation. Significant patterns for AMR genes differing among seafood and clinical samples were revealed from our model and genes conferring to tetracycline, elfamycin, and multidrug (phenicol antibiotic, diaminopyrimidine antibiotic, and fluoroquinolone antibiotic) resistance were identified as the top three key variables. These findings provide crucial insights into the development of effective surveillance and management strategies to address the public health threats associated with V. parahaemolyticus.},
}

@article {pmid40176926,
year = {2025},
author = {van Westerhoven, AC and Fokkens, L and Wissink, K and Kema, GHJ and Rep, M and Seidl, MF},
title = {Reference-free identification and pangenome analysis of accessory chromosomes in a major fungal plant pathogen.},
journal = {NAR genomics and bioinformatics},
volume = {7},
number = {2},
pages = {lqaf034},
doi = {10.1093/nargab/lqaf034},
pmid = {40176926},
issn = {2631-9268},
mesh = {*Fusarium/genetics/pathogenicity ; *Chromosomes, Fungal/genetics ; *Genome, Fungal ; Plant Diseases/microbiology ; Evolution, Molecular ; },
abstract = {Accessory chromosomes, found in some but not all individuals of a species, play an important role in pathogenicity and host specificity in fungal plant pathogens. However, their variability complicates reference-based analysis, especially when these chromosomes are missing in the reference genome. Pangenome variation graphs offer a reference-free alternative for studying these chromosomes. Here, we constructed a pangenome variation graph for 73 diverse Fusarium oxysporum genomes, a major fungal plant pathogen with a compartmentalized genome that includes conserved core as well as variable accessory chromosomes. To obtain insights into accessory chromosome dynamics, we first constructed a chromosome similarity network using all-vs-all similarity mapping. We identified eleven core chromosomes conserved across all strains and a substantial number of highly variable accessory chromosomes. Some of these accessory chromosomes are host-specific and likely play a role in determining host range. Using a k-mer based approach, we further identified the presence of these accessory chromosomes in all available (581) F. oxysporum assemblies and corroborated the occurrence of host-specific accessory chromosomes. To further analyze the evolution of chromosomes in F. oxysporum, we constructed a pangenome variation graph per group of homologous chromosomes. This reveals that accessory chromosomes are composed of different stretches of accessory regions, and possibly rearrangements between accessory regions gave rise to these mosaic accessory chromosomes. Furthermore, we show that accessory chromosomes are likely horizontally transferred in natural populations. Our findings demonstrate that a pangenome variation graph is a powerful approach to elucidate the evolutionary dynamics of accessory chromosomes in F. oxysporum, which is not only a useful resource for Fusarium but also provides a framework for similar analyses in other species containing accessory chromosomes.},
}

*Fusarium/genetics/pathogenicity
*Chromosomes, Fungal/genetics
*Genome, Fungal
Plant Diseases/microbiology
Evolution, Molecular

@article {pmid40173044,
year = {2025},
author = {Zhang, Z and Ni, Z and Li, T and Ning, M and Gao, C and Hu, J and Han, M and Yang, J and Wu, F and Chen, L and Lu, L and Wu, Z and Ai, H and Huang, Y},
title = {Nine high-quality Anas genomes provide new insights into Anas evolution and domestication.},
journal = {Cell reports},
volume = {44},
number = {4},
pages = {115477},
doi = {10.1016/j.celrep.2025.115477},
pmid = {40173044},
issn = {2211-1247},
abstract = {Evolutionary studies of wild and domestic organisms have yielded fascinating discoveries, while the species diversity and the domestication of ducks remain unclear. Here, we assembled eight chromosome-level Anas genomes, combined with the Pekin duck genome, to investigate Anas evolution and domestication. We found that, compared to autosomes, the Z chromosome was less affected by introgression and exhibited relatively stable local phylogenies. From the Z chromosome perspective, we proposed that the speciation of Anas platyrhynchos and Anas zonorhyncha was accompanied by continuous female-biased gene flow and remodeled duck domestication history. Moreover, we constructed an Anas pan-genome and identified several differentiated structural variations (SVs) between domestic and wild ducks. These SVs likely regulate their neighboring genes (i.e., GHR and FER), which represented the promising "domestication genes." Furthermore, a long terminal repeat (LTR) retrotransposon burst was found to have accelerated duck domestication, specifically contributing to functional shifts of the notable MITF and IGF2BP1 genes. These findings presented a live example for understanding animal evolutionary processes.},
}

@article {pmid40172189,
year = {2025},
author = {Deng, Z and Yang, W and Lin, T and Wang, Y and Hua, X and Jiang, X and Chen, J and Liu, D and Ye, Z and Zhang, Y and Lynch, M and Long, H and Pan, J},
title = {Multidimensional insights into the biodiversity of Streptomyces in soils of China: a pilot study.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0169224},
doi = {10.1128/spectrum.01692-24},
pmid = {40172189},
issn = {2165-0497},
abstract = {UNLABELLED: Streptomyces, a diverse group of filamentous bacteria found predominantly in soil, play a crucial role in nutrient cycling and produce many valuable secondary metabolites for the pharmaceutical industry. In this pilot study, we collected 19 soil samples from 14 provinces in China to preliminarily investigate the biodiversity and genetic structure of Streptomyces in soils of China from different dimensions, using recently developed cost-efficient amplicon and whole-genome library preparation methods. Amplicon analysis showed that Actinobacteria were among the most abundant bacteria, with 0.3% of amplicon sequence variants (ASVs) belonging to Streptomyces. Meanwhile, we successfully isolated 136 Streptomyces natural strains and assembled their genomes, including 26 previously unreported species, underscoring the need for further exploration of soil Streptomyces in China. Population genetics analysis revealed that homologous recombination may primarily drive the extensive genetic diversity observed in Streptomyces, as well as a complex population structure. Complementing this, pan-genome analysis shed light on gene diversity within Streptomyces and led to the discovery of rare genes, further emphasizing the vast genetic diversity of this genus. Additionally, multiple metabolic gene clusters were found in these Streptomyces strains, as well as some potentially unique or uncommon ones were found. These findings not only highlight the biological and metabolic diversity of Streptomyces but also provide a technical framework for future studies on the global biodiversity and evolution of this genus.

IMPORTANCE: Streptomyces, a prominent group of Actinobacteria, holds significant importance in ecosystems and biotechnology due to their diverse array of metabolic products. However, research on the biodiversity of soil Streptomyces across extensive geographical scales in China has been limited, and their genetic diversity has rarely been evaluated using modern population genetics principles. This pilot study successfully addresses these gaps by conducting a preliminary exploration on the biodiversity of Streptomyces in Chinese soils from multiple perspectives, providing valuable insights for a deeper understanding of their biodiversity and a novel technical framework for future large-scale explorations of its diversity.},
}

@article {pmid40169664,
year = {2025},
author = {Han, H and Lee, HH and Kim, MG and Shin, YS and Chung, JS and Kim, J},
title = {Genome assembly resources of genitourinary cancers for chromosomal aberration at the single nucleotide level.},
journal = {Scientific data},
volume = {12},
number = {1},
pages = {550},
pmid = {40169664},
issn = {2052-4463},
support = {RS-2023-00247499//National Research Foundation of Korea (NRF)/ ; 2022R1I1A1A0107306512//National Research Foundation of Korea (NRF)/ ; HI22C118600//Korea Health Industry Development Institute (KHIDI)/ ; },
mesh = {Humans ; *Chromosome Aberrations ; *Genome, Human ; Cell Line, Tumor ; Male ; Urogenital Neoplasms/genetics ; Prostatic Neoplasms/genetics ; Kidney Neoplasms/genetics ; },
abstract = {Traditionally, the evolutionary perspective of cancer has been understood as gradual alterations in passenger/driver genes that lead to branching phylogeny. However, in cases of prostate adenocarcinoma and kidney renal cell carcinoma, macroevolutionary landmarks like chromoplexy and chromothripsis are frequently observed. Unfortunately, short-read sequencing techniques often miss these significant macroevolutionary changes, which involve multiple translocations and deletions at the chromosomal level. To resolve such genomic dark matters, we provided high-fidelity long-read sequencing data (78-92 Gb of ~Q30 reads) of six genitourinary tumour cell lines (one benign kidney tumour and two kidney and three prostate cancers). Based on these data, we obtained 12 high-quality, partially phased genome assemblies (Contig N50 1.85-29.01 Mb; longest contig 2.02-171.62 Mb), graph-based pan-genome variant sets (11.57 M variants including 60 K structural variants), and 5-methylcytosine sites (14.68%-27.05% of the CpG sites). We also identified several severe chromosome aberration events, which would result from chromosome break and fusion events. Our cancer genome assemblies will provide unprecedented resolution to understand cancer genome instability and chromosomal aberration.},
}

Humans
*Chromosome Aberrations
*Genome, Human
Cell Line, Tumor
Male
Urogenital Neoplasms/genetics
Prostatic Neoplasms/genetics
Kidney Neoplasms/genetics

@article {pmid40168336,
year = {2025},
author = {Brangsch, H and Marcordes, S and Busch, A and Weber, M and Wolf, SA and Semmler, T and Höper, D and Calvelage, S and Linde, J and Barth, SA},
title = {Comparative genomics of Mycobacterium avium subsp. hominissuis strains within a group of captive lowland tapirs.},
journal = {PloS one},
volume = {20},
number = {4},
pages = {e0320499},
pmid = {40168336},
issn = {1932-6203},
mesh = {Animals ; *Perissodactyla/microbiology ; *Polymorphism, Single Nucleotide ; *Mycobacterium avium/genetics/isolation & purification/classification ; *Genomics/methods ; Genome, Bacterial ; Phylogeny ; Multilocus Sequence Typing ; Whole Genome Sequencing ; },
abstract = {Within a group of three captive lowland tapirs (Tapirus terrestris) suffering from clinically apparent mycobacteriosis, non-tuberculous Mycobacterium avium subsp. hominissuis (MAH) strains were isolated from the animals and the tapir's enclosure. Based on MIRU-VNTR findings, which identified two closely related INMV profiles (124 and 246), a micro-evolutionary event was assumed, and four available MAH strains were submitted to whole genome sequencing (short- and long-read technologies). Surprisingly, the differences based on single nucleotide polymorphisms (SNPs) were exceptionally high between the four strains, i.e., between 841 and 11,166 bases, due to a strong impact of homologous recombination. Thus, an ad hoc core genome multilocus sequence typing (cgMLST) scheme was created and pangenome analysis was conducted for determining the genomic similarity between the strains. The INMV246 isolate obtained from sputum on the enclosure floor and one INMV124 isolate of tapir #2 showed the highest congruence, suggesting that both originated from a shared source. The other two INMV124 isolates were genomically distinct from these strains. Nevertheless, in all four strains two plasmids were detected, which were highly conserved between the strains. The study showed that the genomic variability between MAH strains isolated from the same site within a short period of time can be exceptionally high and the influence of homologous recombination needs to be considered when determining MAH strain relationships, particularly via SNP analyses.},
}

Animals
*Perissodactyla/microbiology
*Polymorphism, Single Nucleotide
*Mycobacterium avium/genetics/isolation & purification/classification
*Genomics/methods
Genome, Bacterial
Phylogeny
Multilocus Sequence Typing
Whole Genome Sequencing

@article {pmid40162720,
year = {2025},
author = {Liu, H and Zhou, H and Ye, H and Li, M and Ma, J and Xi, R and He, X and Zhao, P},
title = {Integrated multi-omics analyses provide new insights into genomic variation landscape and regulatory network candidate genes associated with walnut endocarp.},
journal = {The Plant journal : for cell and molecular biology},
volume = {122},
number = {1},
pages = {e70113},
doi = {10.1111/tpj.70113},
pmid = {40162720},
issn = {1365-313X},
support = {32070372//National Natural Science Foundation of China/ ; 32200295//National Natural Science Foundation of China/ ; 32370386//National Natural Science Foundation of China/ ; 2019K-06//Shaanxi Academy of Science Research Funding Project/ ; 2023K-49//Shaanxi Academy of Science Research Funding Project/ ; 2023k-26//Shaanxi Academy of Science Research Funding Project/ ; SXLK2023-02-20//Shaanxi Forestry Science and Technology Innovation Key Project/ ; Y23Z619F17//Qinling Hundred Talents Project of Shaanxi Academy of Science/ ; 2023-JC-JQ-22//Science Foundation for Distinguished Young Scholars of Shaanxi Province/ ; 22JHZ005//Basic Research Project of Shaanxi Academy of Fundamental Science/ ; 23JHQ029//Basic Research Project of Shaanxi Academy of Fundamental Science/ ; 23JHZ009//Basic Research Project of Shaanxi Academy of Fundamental Science/ ; 2024NC-YBXM-064//Shaanxi Key Research and Development Program/ ; },
mesh = {*Juglans/genetics/growth & development ; *Gene Regulatory Networks ; *Genome-Wide Association Study ; Genome, Plant/genetics ; Genetic Variation ; Gene Expression Regulation, Plant ; Genomics ; DNA Methylation ; Plant Proteins/genetics/metabolism ; Lignin/metabolism/genetics ; Metabolomics ; Nuts/genetics/growth & development ; Transcriptome ; Multiomics ; },
abstract = {Persian walnut (Juglans regia) is an economically important nut oil tree; the fruit has a hard endocarp/shell to protect seeds, thus playing a key role in its evolution, and the shell thickness is an important trait for walnut breeding. However, the genomic landscape and the gene regulatory networks associated with walnut shell development remain to be systematically elucidated. Here, we report a high-quality genome assembly of the walnut cultivar 'Xiangling' and construct a graphic structure pan-genome of eight Juglans species to reveal the genetic variations at the genome level. We re-sequence 285 accessions to characterize the genomic variation landscape. Through genome-wide association studies (GWAS), we identified 19 loci associated with more than 268 loci that underwent selection during walnut domestication and improvement. Multi-omics analyses, including transcriptomics, metabolomics, DNA methylation, and spatial transcriptomics across eleven developmental stages, revealed several candidate genes related to secondary cell biosynthesis and lignin accumulation. This integrated multi-omics approach revealed several candidate genes associated with secondary cell biosynthesis and lignin accumulation, such as UGP, MYB308, MYB83, NAC043, NAC073, CCoAOMT1, CCoAOMT7, CHS2, CESA7, LAC7, COBL4, and IRX12. Overexpression of JrUGP and JrMYB308 in Arabidopsis thaliana confirmed their roles in lignin biosynthesis and cell wall thickening. Consequently, our comprehensive multi-omics findings offer novel insights into walnut genetic variation and network regulation of endocarp development and shell thickness, which enable further genome-informed breeding strategies for walnut cultivar improvement.},
}

*Juglans/genetics/growth & development
*Gene Regulatory Networks
*Genome-Wide Association Study
Genome, Plant/genetics
Genetic Variation
Gene Expression Regulation, Plant
Genomics
DNA Methylation
Plant Proteins/genetics/metabolism
Lignin/metabolism/genetics
Metabolomics
Nuts/genetics/growth & development
Transcriptome
Multiomics

@article {pmid40153053,
year = {2025},
author = {Kiraz, D and Özcan, A},
title = {Comparative genome analysis of 15 Streptococcus thermophilus strains isolated from Turkish traditional yogurt.},
journal = {Antonie van Leeuwenhoek},
volume = {118},
number = {4},
pages = {64},
pmid = {40153053},
issn = {1572-9699},
mesh = {*Yogurt/microbiology ; *Streptococcus thermophilus/genetics/classification/isolation & purification ; *Genome, Bacterial ; *Phylogeny ; Turkey ; Fermentation ; Whole Genome Sequencing ; Food Microbiology ; Genomics ; },
abstract = {Streptococcus thermophilus plays a pivotal role in yogurt fermentation, yet strains from traditional fermented products remain largely unexplored compared to their industrial counterparts. This study aimed to characterize the genomic diversity and functional potential of 15 S. thermophilus strains isolated from Turkish traditional yogurts, and to compare them with industrial strains. Through whole-genome sequencing and advanced bioinformatics analyses, we revealed distinct phylogenetic patterns and genetic features that differentiate these traditional strains from industrial isolates. The genomes (1.68-1.86 Mb) exhibited high genetic homogeneity (ANI > 98.69%) while maintaining significant functional diversity. Pan-genome analysis identified 1160 core genes and 5694 accessory genes, highlighting substantial genomic plasticity that enables niche adaptation. Our analysis uncovered several distinctive features: (1) unique phylogenetic clustering patterns based on both housekeeping genes and whole-genome SNPs, suggesting geographical isolation effects; (2) an extensive repertoire of carbohydrate-active enzymes (CAZymes), comprising 111 Glycoside Hydrolases, 227 Glycosyl Transferases, and 44 Carbohydrate Esterases and 13 Carbohydrate-Binding Modules, demonstrating sophisticated carbohydrate metabolism adaptation significantly enriched compared to industrial strains; (3) widespread GABA biosynthesis pathways in 8 strains, including complete gadB gene, indicating potential health-promoting properties; (4) multiple genomic islands containing genes for galactose utilization and stress response, suggesting specific adaptation to traditional fermentation environments; (5) diverse exopolysaccharide biosynthesis and bacteriocin gene clusters; and (6) widespread CRISPR-Cas systems with variable spacer content. Notably, we identified vanY glycopeptide resistance genes across all strains, with two strains additionally harboring vanT. These results reveal the genetic mechanisms behind S. thermophilus adaptation to traditional yogurt environments, offering valuable insights for developing starter cultures and preserving the unique qualities and potential health benefits of traditional dairy products.},
}

*Yogurt/microbiology
*Streptococcus thermophilus/genetics/classification/isolation & purification
*Genome, Bacterial
*Phylogeny
Turkey
Fermentation
Whole Genome Sequencing
Food Microbiology
Genomics

@article {pmid40149406,
year = {2025},
author = {Panzenhagen, P and Shah, DH and Rodrigues, DDP and Conte Junior, CA},
title = {Worldwide Population Dynamics of Salmonella Saintpaul: Outbreaks, Epidemiology, and Genome Structure.},
journal = {Genes},
volume = {16},
number = {3},
pages = {},
pmid = {40149406},
issn = {2073-4425},
mesh = {Humans ; *Disease Outbreaks ; *Phylogeny ; *Genome, Bacterial ; *Salmonella Infections/microbiology/epidemiology ; Brazil/epidemiology ; Whole Genome Sequencing ; Salmonella/genetics/pathogenicity ; Multilocus Sequence Typing ; Genome-Wide Association Study ; Population Dynamics ; Virulence/genetics ; },
abstract = {BACKGROUND/OBJECTIVES: Salmonella Saintpaul (SSa) is increasingly linked to foodborne outbreaks in Brazil and globally. Despite its rising public health significance, its epidemiology, genomic diversity, and pathogenic potential remain underexplored. This study addresses these gaps through a comprehensive global analysis of SSa population dynamics, outbreak patterns, and genetic structures, along with an in-depth phenotypic and genomic characterization of strain PP_BR059, isolated from a hospitalized patient in Ceará, Brazil.

METHODS: We analyzed 1,953 publicly available SSa genomes using core-genome multi-locus sequence typing (cgMLST), antimicrobial resistance (AMR) profiling, pan-genome analysis, and phylogenetic inference. A genome-wide association study (GWAS) identified genetic determinants of virulence and AMR. The invasiveness and intracellular survival of PP_BR059 were assessed using in vitro macrophage infection assays, while whole-genome sequencing (WGS) provided genetic insights.

RESULTS: Phylogenetic analysis identified 49 sequence types (STs), with ST-50 (787 genomes) and ST-27 (634 genomes) being most prevalent. ST-50 included all clinical strains from South America, including PP_BR059. AMR analysis showed 60% of SSa genomes were pan-susceptible, while ST-27 had the highest proportion of AMR strains. GWAS revealed distinct evolutionary lineages within ST-50 and ST-27. PP_BR059 exhibited lower macrophage invasion (3.82%) but significantly higher intracellular survival at 2 h (68.72%) and 20 h (25.68%) post-infection. WGS confirmed a pan-susceptible AMR profile and plasmid absence.

CONCLUSIONS: This study highlights SSa's global dissemination, evolutionary trends, and pathogenic variability, emphasizing the need for molecular surveillance to inform public health interventions.},
}

Humans
*Disease Outbreaks
*Phylogeny
*Genome, Bacterial
*Salmonella Infections/microbiology/epidemiology
Brazil/epidemiology
Whole Genome Sequencing
Salmonella/genetics/pathogenicity
Multilocus Sequence Typing
Genome-Wide Association Study
Population Dynamics
Virulence/genetics

@article {pmid40143297,
year = {2025},
author = {Troshin, K and Sykilinda, N and Shuraleva, S and Tokmakova, A and Tkachenko, N and Kurochkina, L and Miroshnikov, K and Suzina, N and Brzhozovskaya, E and Petrova, K and Toshchakov, S and Evseev, P},
title = {Pseudomonas Phage Lydia and the Evolution of the Mesyanzhinovviridae Family.},
journal = {Viruses},
volume = {17},
number = {3},
pages = {},
pmid = {40143297},
issn = {1999-4915},
support = {state assignment//Kurchatov Institute/ ; },
mesh = {*Pseudomonas Phages/genetics/classification ; *Phylogeny ; *Genome, Viral ; *Host Specificity ; *Pseudomonas aeruginosa/virology/genetics ; *Evolution, Molecular ; Siphoviridae/genetics/classification/isolation & purification ; DNA, Viral/genetics ; Computational Biology/methods ; Viral Proteins/genetics ; Genomics ; },
abstract = {Phage Lydia, a newly isolated siphovirus infecting Pseudomonas aeruginosa, was characterized with respect to its basic kinetic properties and subjected to comparative bioinformatic analysis with related phages. The phage exhibited a restricted host range, with lytic activity observed against 7 of 30 tested isolates. The genome of phage Lydia consists of a 61,986 bp dsDNA molecule and contains 89 predicted genes. Bioinformatic analysis suggests the presence of a DNA modification system, but no apparent genes associated with lysogeny or antibiotic resistance were identified. Taxonomic classification places Lydia within the Mesyanzhinovviridae family, Rabinowitzvirinae subfamily, and Yuavirus genus, with the closest relation to Pseudomonas virus M6. Comprehensive bioinformatic studies, including structural modelling and analysis of phage proteins, as well as comparative taxonomic, phylogenomic, and pangenomic analyses of the Mesyanzhinovviridae family, revealed relationships between proteins of Mesyanzhinovviridae phages, proteins from other phage groups, encapsulins, and a gene transfer agent (GTA) particle from Rhodobacter capsulatus. These analyses uncovered patterns of evolutionary history within the family, characterized by genetic exchange events alongside the maintenance of a common genomic architecture, leading to the emergence of new groups within the family.},
}

*Pseudomonas Phages/genetics/classification
*Phylogeny
*Genome, Viral
*Host Specificity
*Pseudomonas aeruginosa/virology/genetics
*Evolution, Molecular
Siphoviridae/genetics/classification/isolation & purification
DNA, Viral/genetics
Computational Biology/methods
Viral Proteins/genetics
Genomics

@article {pmid40141723,
year = {2025},
author = {Romanenko, L and Bystritskaya, E and Otstavnykh, N and Kurilenko, V and Velansky, P and Isaeva, M},
title = {Phenotypic and Genomic Characterization of Oceanisphaera submarina sp. nov. Isolated from the Sea of Japan Bottom Sediments.},
journal = {Life (Basel, Switzerland)},
volume = {15},
number = {3},
pages = {},
pmid = {40141723},
issn = {2075-1729},
support = {15.BRK.21.0004 (Contract No. 075-15-2021-1052/9)//the Ministry of Science and Higher Education, Russian Federation/ ; },
abstract = {A Gram-negative aerobic, motile bacterium KMM 10153[T] was isolated from bottom sediment sampled from the Sea of Japan at a depth of 256 m, Russia. Strain KMM 10153[T] grew in 0-12% NaCl at temperatures ranging from 4 to 42 °C and produced brown diffusible pigments. Based on the 16S rRNA gene and whole genome sequences analyses, novel bacterium KMM 10153[T] was affiliated with the genus Oceanisphaera (phylum Pseudomonadota) showing the highest 16S rRNA gene sequence similarities of 98.94% to Oceanisphaera arctica KCTC 23013[T], 98.15% to Oceanisphaera donghaensis BL1[T], and similarity values of <98% to other validly described Oceanisphaera species. The pairwise Average Nucleotide Identity (ANI) and Average Amino Acid Identity (AAI) values between the novel strain KMM 10153[T] and the three closest type strains Oceanishaera arctica KCTC 23013[T], Oceanisphaera litoralis DSM 15406[T] and Oceanisphaera sediminis JCM 17329[T] were 89.4%, 89.1%, 87.41%, and 90.7%, 89.8%, 89.7%, respectively. The values of digital DNA-DNA hybridization (dDDH) were below 39.3%. The size of the KMM 10153[T] draft genome was 3,558,569 bp, and the GC content was 57.5%. The genome of KMM 10153[T] harbors 343 unique genes with the most abundant functional classes consisting of transcription, mobilome, amino acid metabolism, and transport. Strain KMM 10153[T] contained Q-8 as the predominant ubiquinone and C16:1ω7c, C16:0, and C18:1ω7c as the major fatty acids. The polar lipids were phosphatidylethanolamine, phosphatidylglycerol, diphosphatidylglycerol, and phosphatidic acid. Based on the distinctive phenotypic characteristics and the results of phylogenetic and genomic analyses, the marine bacterium KMM 10153[T] could be classified as a novel Oceanisphaera submarina sp. nov. The type strain of the species is strain KMM 10153[T] (=KCTC 8836[T]).},
}

@article {pmid40141677,
year = {2025},
author = {Nedashkovskaya, O and Baldaev, S and Ivaschenko, A and Bystritskaya, E and Zhukova, N and Eremeev, V and Kukhlevskiy, A and Kurilenko, V and Isaeva, M},
title = {Description and Comparative Genomics of Algirhabdus cladophorae gen. nov., sp. nov., a Novel Aerobic Anoxygenic Phototrophic Bacterial Epibiont Associated with the Green Alga Cladophora stimpsonii.},
journal = {Life (Basel, Switzerland)},
volume = {15},
number = {3},
pages = {},
pmid = {40141677},
issn = {2075-1729},
support = {15.BRK.21.0004 (Contract No. 075-15-2021-1052/9)//Ministry of Science and Higher Education, Russian Federation/ ; },
abstract = {A novel, strictly aerobic, non-motile, and pink-pigmented bacterium, designated 7Alg 153[T], was isolated from the Pacific green alga Cladophora stimpsonii. Strain 7Alg 153[T] was able to grow at 4-32 °C in the presence of 1.5-4% NaCl and hydrolyze L-tyrosine, gelatin, aesculin, Tweens 20, 40, and 80 and urea, as well as produce catalase, oxidase, and nitrate reductase. The novel strain 7Alg 153[T] showed the highest similarity of 96.75% with Pseudaestuariivita rosea H15[T], followed by Thalassobius litorarius MME-075[T] (96.60%), Thalassobius mangrovi GS-10[T] (96.53%), Tritonibacter litoralis SM1979[T] (96.45%), and Marivita cryptomonadis CL-SK44[T] (96.38%), indicating that it belongs to the family Roseobacteraceae, the order Rhodobacteales, the class Alphaproteobacteria, and the phylum Pseudomonadota. The respiratory ubiquinone was Q-10. The main polar lipids were phosphatidylethanolamine, phosphatidylglycerol, diphosphatidylglycerol, phosphatidylcholine, two unidentified aminolipids, and one unidentified lipid. The predominant cellular fatty acids (>5%) were C18:1 ω7c, C16:0, C18:0, and 11-methyl C18:1 ω7c. The 7Alg 153[T] genome is composed of a single circular chromosome of 3,786,800 bp and two circular plasmids of 53,157 bp and 37,459 bp, respectively. Pan-genome analysis showed that the 7Alg 153[T] genome contains 33 genus-specific clusters spanning 92 genes. The COG20-annotated singletons were more often related to signal transduction mechanisms, cell membrane biogenesis, transcription, and transport, and the metabolism of amino acids. The complete photosynthetic gene cluster (PGC) for aerobic anoxygenic photosynthesis (AAP) was found on a 53 kb plasmid. Based on the phylogenetic evidence and phenotypic and chemotaxonomic characteristics, the novel isolate represents a novel genus and species within the family Roseobacteraceae, for which the name Algirhabdus cladophorae gen. nov., sp. nov. is proposed. The type strain is 7Alg 153[T] (=KCTC 72606[T] = KMM 6494[T]).},
}

@article {pmid40140905,
year = {2025},
author = {Miao, J and Wang, Q and Zhang, Z and Wang, Q and Pan, Y and Wang, Z},
title = {Pangenome graph mitigates heterozygosity overestimation from mapping bias: a case study in Chinese indigenous pigs.},
journal = {BMC biology},
volume = {23},
number = {1},
pages = {89},
pmid = {40140905},
issn = {1741-7007},
mesh = {Animals ; *Heterozygote ; *Genome ; Polymorphism, Single Nucleotide ; China ; Sus scrofa/genetics ; Swine/genetics ; Chromosome Mapping/methods ; East Asian People ; },
abstract = {BACKGROUND: Breeds genetically distant from the reference genome often show considerable differences in DNA fragments, making it difficult to achieve accurate mappings. The genetic differences between pig reference genome (Sscrofa11.1) and Chinese indigenous pigs may lead to mapping bias and affect subsequent analyses.

RESULTS: Our analysis revealed that pangenome exhibited superior mapping accuracy to the Sscrofa11.1, reducing false-positive mappings by 1.4% and erroneous mappings by 0.8%. Furthermore, the pangenome yielded more accurate genotypes of SNP (F1: 0.9660 vs. 0.9607) and INDEL (F1: 0.9226 vs. 0.9222) compared to Sscrofa11.1. In real sequencing data, the inconsistent SNPs called from the pangenome exhibited lower genome heterozygosity compared to those identified by the Sscrofa11.1, including observed heterozygosity and nucleotide diversity. The same reduction of heterozygosity overestimation was also found in the chicken pangenome.

CONCLUSIONS: This study quantifies the mapping bias of Sscrofa11.1 in Chinese indigenous pigs, demonstrating that mapping bias can lead to an overestimation of heterozygosity in Chinese indigenous pig breeds. The adoption of a pig pangenome mitigates this bias and provides a more accurate representation of genetic diversity in these populations.},
}

Animals
*Heterozygote
*Genome
Polymorphism, Single Nucleotide
China
Sus scrofa/genetics
Swine/genetics
Chromosome Mapping/methods
East Asian People

@article {pmid40140737,
year = {2025},
author = {Tahir Ul Qamar, M and Fatima, K and Rao, MJ and Tang, Q and Sadaqat, M and Ding, B and Chen, LL and Zhu, XT},
title = {Comparative genomics profiling of Citrus species reveals the diversity and disease responsiveness of the GLP pangenes family.},
journal = {BMC plant biology},
volume = {25},
number = {1},
pages = {388},
pmid = {40140737},
issn = {1471-2229},
mesh = {*Citrus/genetics ; *Multigene Family ; *Genome, Plant ; Genomics ; Plant Diseases/genetics/microbiology ; Plant Proteins/genetics/metabolism ; Genetic Variation ; Phylogeny ; Genes, Plant ; Gene Expression Regulation, Plant ; Disease Resistance/genetics ; },
abstract = {Citrus is an important nutritional fruit globally; however, its yield is affected by various stresses. This study presents the draft pangenome of Citrus, developed using 11 species to examine their genetic diversity and identify members of the germin-like proteins (GLPs) gene family involved in disease responsiveness. The developed sequence-based pangenome contains 954 Mb sequence and 74,755 genes. The comparative genomics analysis revealed the presence-absence variations (PAVs) among the Citrus genomes and species-specific protein-coding genes. Gene-based pangenome analysis revealed 4,936 new genes missing in the reference genome and highlighted the core and shell genes with putative functions in stress regulation. The pangenome-wide identification of GLP gene family members indicated the intraspecies diversity among the members across 11 genomes by analyzing their gene structure, motifs, and chromosomal distribution patterns. The synteny and evolutionary constraints analyses of Citrus GLPs provide detailed evidence of their evolutionary conservation and divergence. Further, the interaction, functional enrichment, and promoter analysis revealed their involvement in abiotic-, biotic-stress, signaling, and development-related pathways. The expression patterns of C. sinensis GLPs were studied in Huanglongbing (HLB) and Citrus canker disease. Several genes including CsGLPs1-2 and CsGLPs8-4 showed changes in expression patterns under both disease conditions. The qRT-PCR analysis revealed that these two genes were highly expressed in leaves infected with HLB disease across seven HLB-tolerant and susceptible citrus species. This Citrus pangenome and pangenes family study offers a comprehensive resource and new insights into the structural and functional diversity, identifying candidate genes that are important for future research to understand the stress-responsive mechanisms in Citrus.},
}

*Citrus/genetics
*Multigene Family
*Genome, Plant
Genomics
Plant Diseases/genetics/microbiology
Plant Proteins/genetics/metabolism
Genetic Variation
Phylogeny
Genes, Plant
Gene Expression Regulation, Plant
Disease Resistance/genetics

@article {pmid40139668,
year = {2025},
author = {Zheng, Z and Lv, J and Niu, Z and Zhang, J and Zhu, M and Hu, H and Sun, W and Ma, J and Li, Y and Wu, Y and Wang, D and Mu, W and Xu, R and Jiang, Y and Lu, Z and Liu, J and Yang, Y},
title = {Genetic insights into developmental variations of spiny bracts among hazels through the pangenome construction.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.14568},
pmid = {40139668},
issn = {1467-7652},
support = {2021 + 02//Young Talent Development Project of State Key Laboratory of Herbage Improvement and Grassland Agroecosystems/ ; BP0719040//International Collaboration 111 Program/ ; 22ZD6NA007//Key Science & Technology Project of Gansu Province/ ; lzujbky-2022-ey07//Fundamental Research Funds for the Central Universities/ ; 31900201//National Natural Science Foundation of China/ ; 32170219//National Natural Science Foundation of China/ ; },
}

@article {pmid40137238,
year = {2025},
author = {Cheng, G and An, X and Dai, Y and Li, C and Li, Y},
title = {Genomic Insights into Cobweb Disease Resistance in Agaricus bisporus: A Comparative Analysis of Resistant and Susceptible Strains.},
journal = {Journal of fungi (Basel, Switzerland)},
volume = {11},
number = {3},
pages = {},
pmid = {40137238},
issn = {2309-608X},
support = {CARS-20//Ministry of Agriculture and Rural Affairs of the People's Republic of China/ ; U20A2046//National Natural Science Foundation of China/ ; Tiānchí Yīngcái//Science&Technology Department of Xinjiang Uygur Autonomous Region/ ; 20230101272JC//Jilin Provincial Department of Science and Technology/ ; },
abstract = {Agaricus bisporus, a globally cultivated edible fungus, faces significant challenges from fungal diseases like cobweb disease caused by Cladobotryum mycophilum, which severely impacts yield. This study aimed to explore the genetic basis of disease resistance in A. bisporus by comparing the genomes of a susceptible strain (AB7) and a resistant strain (AB58). Whole-genome sequencing of AB7 was performed using PacBio Sequel SMRT technology, and comparative genomic analyses were conducted alongside AB58 and other fungal hosts of C. mycophilum. Comparative genomic analyses revealed distinct resistance features in AB58, including enriched regulatory elements, specific deletions in AB7 affecting carbohydrate-active enzymes (CAZymes), and unique cytochrome P450 (CYP) profiles. Notably, AB58 harbored more cytochrome P450 genes related to fatty acid metabolism and unique NI-siderophore synthetase genes, contributing to its enhanced environmental adaptability and disease resistance. Pan-genome analysis highlighted significant genetic diversity, with strain-specific genes enriched in pathways like aflatoxin biosynthesis and ether lipid metabolism, suggesting distinct evolutionary adaptations. These findings provide valuable insights into the genetic basis underlying disease resistance in A. bisporus, offering a foundation for future breeding strategies to improve fungal crop resilience.},
}

@article {pmid40135051,
year = {2025},
author = {Bello, A and Ning, S and Zhang, Q and Ni, W and Hu, S},
title = {Genomic analysis of multidrug-resistant Escherichia coli isolated from dairy cows in Shihezi city, Xinjiang, China.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1527546},
pmid = {40135051},
issn = {1664-302X},
abstract = {INTRODUCTION: Dairy farming plays a vital role in agriculture and nutrition; however, the emergence of antimicrobial resistance (AMR) among bacterial pathogens poses significant risks to public health and animal welfare. Multidrug-resistant (MDR) Escherichia coli strains are of particular concern due to their potential for zoonotic transmission and resistance to multiple antibiotics. In this study, we investigated the prevalence of AMR and analyzed the genomes of two MDR E. coli isolated from dairy cows in Shihezi City.

METHODS: Fecal samples were collected from dairy cows, and E. coli strains were isolated. Antibiotic susceptibility testing was conducted using the Kirby-Bauer disk diffusion method against 14 antibiotics. Two MDR isolates (E.coli_30 and E.coli_45) were selected for whole-genome sequencing and comparative genomic analysis. The Comprehensive Antibiotic Resistance Database (CARD) was used to identify AMR genes, and virulence factors were analyzed. Phylogenetic analysis was performed to determine the evolutionary relationships of the isolates, and a pangenome analysis of 50 E. coli strains was conducted to assess genetic diversity. The presence of mobile genetic elements (MGEs), including insertion sequences (IS) and transposons, was also examined.

RESULTS: Among the E. coli isolates, 22.9% exhibited MDR, with high resistance to imipenem and ciprofloxacin, while gentamicin and tetracycline remained the most effective antibiotics. Genomic analysis revealed key AMR genes, including mphA, qnrS1, and bla CTX-M-55 (the latter found only in E.coli_45), conferring resistance to macrolides, quinolones, and beta-lactams, respectively. Virulence genes encoding type III secretion systems (TTSS) and adhesion factors were identified, indicating pathogenic potential. Phylogenetic analysis showed that E.coli_30 and E.coli_45 originated from distinct ancestral lineages. The presence of two extended-spectrum β-lactamase (ESBL) genes in E.coli_45 was noticeable, so we studied their global and national distribution using evolutionary analysis. We found that they are endemic in E. coli, Salmonella enterica, and Klebsiella pneumoniae. Pangenome analysis revealed significant genetic diversity among E. coli strains, with unique genes related to metabolism and stress response. This indicates the bacteria's adaptation to various environments. MGEs were identified as key contributors to genetic variability and adaptation.

DISCUSSION: This study highlights the growing threat of MDR E. coli in dairy farms, emphasizing the critical role of MGEs in the spread of resistance genes. The genetic diversity observed suggests strong adaptive capabilities, justifying the need for continuous AMR surveillance in livestock. Effective monitoring and mitigation strategies are essential to prevent the dissemination of MDR bacteria, thereby protecting both animal and public health.},
}

@article {pmid40133961,
year = {2025},
author = {Innamorati, KA and Earl, JP and Barrera, SC and Ehrlich, RL and Aiyeku, J and Gordon, A and Powell, E and Retchless, AC and Ahmed, A and Sen, B and Balashov, S and Mell, JC and Hillier, SL and Ehrlich, GD},
title = {Metronidazole response profiles of Gardnerella species are congruent with phylogenetic and comparative genomic analyses.},
journal = {Genome medicine},
volume = {17},
number = {1},
pages = {28},
pmid = {40133961},
issn = {1756-994X},
mesh = {*Metronidazole/pharmacology ; *Phylogeny ; Humans ; *Microbial Sensitivity Tests ; *Drug Resistance, Bacterial/genetics ; *Genome, Bacterial ; Genomics/methods ; Anti-Bacterial Agents/pharmacology ; Female ; Vaginosis, Bacterial/microbiology/drug therapy ; Gardnerella vaginalis/genetics/drug effects ; Whole Genome Sequencing ; Gardnerella/genetics/drug effects ; Clindamycin/pharmacology ; },
abstract = {BACKGROUND: Bacterial vaginosis (BV) affects 20-50% of reproductive-age female patients annually, arising when opportunistic pathogens outcompete healthy vaginal flora. Many patients fail to resolve symptoms with a course of metronidazole, the current first-line treatment for BV. Our study was designed to identify genomic variation associated with metronidazole resistance among strains of Gardnerella vaginalis spp. (GV), a genus of biogenic-amine-producing bacteria closely associated with BV pathogenesis, for the development of a companion molecular diagnostic.

METHODS: Whole-genome sequencing and comparative genomic metrics, including average nucleotide identity and GC content, were performed on a diverse set of 129 GV genomes to generate data for detailed taxonomic analyses. Pangenomic analyses were employed to construct a phylogenetic tree and cluster highly related strains within genospecies. G. vaginalis spp. clinical isolates within our collection were subjected to plate-based minimum inhibitory concentration (MIC) testing of metronidazole (n = 60) and clindamycin (n = 63). DECIPHER and MAFFT were used to identify genospecies-specific primers associated with antibiotic-resistance phenotypes. PCR-based analyses with these primers were used to confirm their specificity for the relevant genospecies.

RESULTS: Eleven distinct genospecies based on standard ANI criteria were identified among the GV strains in our collection. Metronidazole MIC testing revealed six genospecies within a closely related phylogenetic clade contained only highly metronidazole-resistant strains (MIC ≥ 32 µg/mL) and suggested at least two mechanisms of metronidazole resistance within the eleven GV genospecies. All strains within the six highly metronidazole-resistant genospecies displayed susceptibility to clinically relevant clindamycin concentrations (MIC ≤ 2 µg/mL). A PCR-based molecular diagnostic assay was developed to distinguish between members of the metronidazole-resistant and mixed-response genospecies, which should be useful for determining the clade membership of various GV strains and could assist in the selection of appropriate antibiotic therapies for BV cases.

CONCLUSIONS: This study provides comparative genomic and phylogenetic evidence for eleven distinct genospecies within the genus Gardnerella vaginalis spp., and identifies genospecies-specific responses to metronidazole, the first-line treatment for BV. A companion molecular diagnostic assay was developed that is capable of identifying essentially all highly metronidazole-resistant strains that phylogenetically cluster together within the GV genospecies, which is informative for antibiotic treatment options.},
}

*Metronidazole/pharmacology
*Phylogeny
Humans
*Microbial Sensitivity Tests
*Drug Resistance, Bacterial/genetics
*Genome, Bacterial
Genomics/methods
Anti-Bacterial Agents/pharmacology
Female
Vaginosis, Bacterial/microbiology/drug therapy
Gardnerella vaginalis/genetics/drug effects
Whole Genome Sequencing
Gardnerella/genetics/drug effects
Clindamycin/pharmacology

@article {pmid40133370,
year = {2025},
author = {Wan, L and Deng, C and Liu, B and Su, S and Zhang, Z and Jiang, Y and Zou, B and Liu, J and Du, Z and Zhang, Y and Chen, P and Xiao, W},
title = {Telomere-to-telomere genome assemblies of three silkworm strains with long-term pupal characteristics.},
journal = {Scientific data},
volume = {12},
number = {1},
pages = {501},
pmid = {40133370},
issn = {2052-4463},
mesh = {Animals ; *Bombyx/genetics ; *Genome, Insect ; *Telomere/genetics ; *Pupa/genetics ; },
abstract = {The domesticated silkworm (Bombyx mori) is both economically significant and a valuable model organism. However, challenges persist in silk production, particularly in preserving silkworm cocoons. The wild silkworm (Bombyx mandarina), a close relative, with long-term pupal characteristics, could address storage and industrial silk production issues. We conducted interspecies hybridization between domestic and wild silkworms, successfully introducing the long-pupal period trait into the domestic silkworm through genomic integration. Here, we presented the telomere-to-telomere genome assemblies of three silkworm strains (KA, L, and M) with long-term pupal characteristics. The genome assembly sizes ranged from 453.82 Mb to 461.92 Mb, with high contig N50 values and completeness. We predicted over 14,000 protein-coding genes and identified strain-specific fragments. This research enriches the domestic silkworm pan-genome project and provides a foundation for further genetic studies. By introducing the trait, we have for the first time reported a phenomenon of genomic introgression between domestic and wild silkworm, and have also opened up a new avenue for silkworm breeding.},
}

Animals
*Bombyx/genetics
*Genome, Insect
*Telomere/genetics
*Pupa/genetics

@article {pmid40131635,
year = {2025},
author = {Silva, UCM and da Silva, DRC and Cuadros-Orellana, S and Moreira, LM and Leite, LR and Medeiros, JD and Felestrino, EB and Caneschi, WL and Almeida, NF and Silva, RS and Oliveira-Paiva, CA and Dos Santos, VL},
title = {Genomic and phenotypic insights into Serratia interaction with plants from an ecological perspective.},
journal = {Brazilian journal of microbiology : [publication of the Brazilian Society for Microbiology]},
volume = {},
number = {},
pages = {},
pmid = {40131635},
issn = {1678-4405},
support = {N° 477349/2013-7//CNPq/ ; N° APQ-01819-13//Fapemig/ ; },
abstract = {We investigated the plant growth-promoting potential of two endophytic strains of Serratia marcescens, namely SmCNPMS2112 and SmUFMG85, which were isolated from the roots of the same maize (Zea mays) plant. The strains were evaluated in vitro for their ability to produce siderophores and indoleacetic acid, form biofilm, solubilize iron phosphate (Fe-P) and Araxá rock phosphate (RP), mineralize phytate, and for their ability to adhere and colonize host roots. Additionally, their plant growth-promoting potential was tested in vivo under greenhouse conditions using millet grown in soil under two fertilization schemes (triple superphosphate, TSP, or commercial rock phosphate, cRP). Both strains improved at least five physiological traits of millet or P content in soil. In order to elucidate the genetic basis of the plant growth-promoting ability of these strains, their genomes were compared. While both genomes exhibited a similar overall functional profile, each strain had unique features. SmCNPMS2112 contained genes related to arsenic and aromatic hydrocarbons degradation, whereas SmUFMG85 harbored genes related to rhamnolipid biosynthesis and chromium bioremediation. Also, we observe a unique repertoire of genes related to plant growth-promotion (PGP) in the SmUFMG85 genome, including oxalate decarboxylase (OxdC), associated with the catabolism of oxalic acid, and aerobactin siderophore (lucD) in the genome of SmCNPMS2112. The alkaline phosphatase was observed on two strains, but acid phosphatase was exclusive to SmUFMG85. Eighteen secondary metabolic gene clusters, such as those involved in the biosynthesis of macrolides and bacillomycin, among others, occur in both strains. Moreover, both genomes contained prophages, suggesting that viral-mediated horizontal gene transfer may be a key mechanism driving genomic variability in the endophytic environment. Indeed, the most genes unique and accessory of SmUFMG85 and SmCNPMS2112 were localized in genomic islands, highlighting genome plasticity and its underlying drivers. To investigate the ecological distribution of plant-interaction traits in the genus Serratia, the genomes of SmUFMG85 and SmCNPMS2112 strains were compared with those of other 19 Serratia strains of different species, which were isolated from different environments. We observe that many features for PGP are present in all genomes, regardless of niche, for instance: formation of flagella, fimbriae and pili, chemotaxis, biosynthesis of siderophores, indole-3-acetic acid (IAA) and volatile organic (VOC) and inorganic (VIC) compounds, such as acetoin and HCN. Also, all the analyzed genomes show an antimicrobial resistance repertoire of genes that confer resistance to several antibiotics belonging to the groups of aminoglycosides and quinolones, for instance. Also, from a niche partitioning perspective, secretion system preference and the ability to produce exopolysaccharides involved in biofilm formation are among the features that vary the most among strains, and most likely influence niche adaptation in Serratia spp., even though only the latter seems to be a feature specifically associated with virulence in the analyzed strains. Our results show that populations of bacteria sharing the same niche can present significant physiological and genomic differences, and reveal the intraspecific metabolic plasticity that underlie plant-bacteria interactions. Also, this study reveals the potential of two Serratia marcescens strains as bioinoculants in agriculture. Considering that Serratia spp. are regarded as low risk biological agents, despite the fact that they can be associated with human disease, we suggest that strain biosafety be evaluated using a combination of genome and phenotypic analyses, as presented herein.},
}

@article {pmid40130174,
year = {2025},
author = {Bixler, BJ and Royer, CJ and Petit Iii, RA and Moller, AG and Sefton, S and Thomas, S and Tunali, A and Collins, LF and Farley, MM and Satola, SW and Read, TD},
title = {Comparative genomic analysis of emerging non-typeable Haemophilus influenzae (NTHi) causing emerging septic arthritis in Atlanta.},
journal = {PeerJ},
volume = {13},
number = {},
pages = {e19081},
pmid = {40130174},
issn = {2167-8359},
mesh = {*Haemophilus influenzae/genetics/pathogenicity ; Humans ; *Haemophilus Infections/microbiology ; *Arthritis, Infectious/microbiology ; Georgia/epidemiology ; Genome, Bacterial/genetics ; Genomics ; Virulence Factors/genetics ; Whole Genome Sequencing ; Polymorphism, Single Nucleotide ; Multilocus Sequence Typing ; },
abstract = {BACKGROUND: Haemophilus influenzae is a Gram-negative bacterium that can exist as a commensal organism or cause a range of diseases, from ear infections to invasive conditions like meningitis. While encapsulated H. influenzae strains have historically been linked to severe diseases, non-typeable Haemophilus influenzae (NTHi) strains, lacking an intact capsule locus, have emerged as the leading cause of invasive H. influenzae infections, particularly following the widespread use of the H. influenzae serotype b (Hib) vaccine.

METHODS: In response to a significant increase in invasive NTHi infections among persons living with HIV in metropolitan Atlanta during 2017-2018, we conducted a comparative genomic analysis of two predominant NTHi clones, C1 and C2, identified during this period. These clones correspond to multilocus sequence types ST164 and ST1714, respectively. We analyzed the genomic characteristics of C1 and C2 using whole genome sequencing data and compared them to a broader pangenome of H. influenzae strains to identify potential virulence factors and genetic adaptations.

RESULTS: Both C1 and C2 isolates were highly related within their clusters, with C1 showing a maximum of 132 SNPs and C2 showing 149 SNPs within their respective core genomes. Genomic analysis revealed significant deletions in known virulence genes, surprisingly suggesting possible attenuation of virulence. No unique accessory genes were identified that distinguished C1 and C2 from other H. influenzae strains, although both clusters exhibited a consistent loss of the pxpB gene (encoding 5-oxoprolinase subunit), replaced by a mobile cassette containing genes potentially involved in sugar metabolism. All C1 and C2 isolates showed potential enrichment in accessory genes associated with systemic infections.

CONCLUSIONS: Our study suggests that while C1 and C2 clones possess some genetic markers potentially linked to systemic infections, there are no definitive unique genetic factors that distinguish these clones as more virulent than other H. influenzae strains. The expansion of these clones in a vulnerable population may reflect both chance introduction and potential adaptations to the host environment. Further research is needed to understand the implications of these genetic findings on the clinical management and prevention of invasive NTHi infections.},
}

*Haemophilus influenzae/genetics/pathogenicity
Humans
*Haemophilus Infections/microbiology
*Arthritis, Infectious/microbiology
Georgia/epidemiology
Genome, Bacterial/genetics
Genomics
Virulence Factors/genetics
Whole Genome Sequencing
Polymorphism, Single Nucleotide
Multilocus Sequence Typing

@article {pmid40128563,
year = {2025},
author = {Stoltze, U and Junk, SV and Byrjalsen, A and Cavé, H and Cazzaniga, G and Elitzur, S and Fronkova, E and Hjalgrim, LL and Kuiper, RP and Lundgren, L and Mescher, M and Mikkelsen, T and Pastorczak, A and Strullu, M and Trka, J and Wadt, K and Izraeli, S and Borkhardt, A and Schmiegelow, K},
title = {Overt and covert genetic causes of pediatric acute lymphoblastic leukemia.},
journal = {Leukemia},
volume = {},
number = {},
pages = {},
pmid = {40128563},
issn = {1476-5551},
support = {2023-001063//Børnecancerfonden (Danish Childhood Cancer Foundation)/ ; 2020-5769//Børnecancerfonden (Danish Childhood Cancer Foundation)/ ; R-257-A14720//Kræftens Bekæmpelse (Danish Cancer Society)/ ; 2023-29175//Associazione Italiana per la Ricerca sul Cancro (Italian Association for Cancer Research)/ ; },
abstract = {Pediatric acute lymphoblastic leukemia (pALL) is the most common childhood malignancy, yet its etiology remains incompletely understood. However, over the course of three waves of germline genetic research, several non-environmental causes have been identified. Beginning with trisomy 21, seven overt cancer predisposition syndromes (CPSs)-characterized by broad clinical phenotypes that include an elevated risk of pALL-were first described. More recently, newly described CPSs conferring high risk of pALL are increasingly covert, with six exhibiting only minimal or no non-cancer features. These 13 CPSs now represent the principal known hereditary causes of pALL, and human pangenomic data indicates a strong negative selection against mutations in the genes associated with these conditions. Collectively they affect approximately 1 in 450 newborns, of which just a minority will develop the disease. As evidenced by tailored leukemia care protocols for children with trisomy 21, there is growing recognition that CPSs warrant specialized diagnostic, therapeutic, and long-term management strategies. In this review, we investigate the evidence that the 12 other CPSs associated with high risk of pALL may also see benefits from specialized care - even if these needs are often incompletely mapped or addressed in the clinic. Given the rarity of each syndrome, collaborative international research and shared data initiatives will be crucial for advancing knowledge and improving outcomes for these patients.},
}

@article {pmid40124499,
year = {2025},
author = {Li, L and Wu, Z and Guarracino, A and Villani, F and Kong, D and Mancieri, A and Zhang, A and Saba, L and Chen, H and Brozka, H and Vales, K and Senko, AN and Kempermann, G and Stuchlik, A and Pravenec, M and Lechner, J and Prins, P and Mathur, R and Lu, L and Yang, K and Peng, J and Williams, RW and Wang, X},
title = {Genetic modulation of protein expression in rat brain.},
journal = {iScience},
volume = {28},
number = {3},
pages = {112079},
pmid = {40124499},
issn = {2589-0042},
abstract = {Genetic variations in protein expression are implicated in a broad spectrum of common diseases and complex traits but remain less explored compared to mRNA and classical phenotypes. This study systematically analyzed brain proteomes in a rat family using tandem mass tag (TMT)-based quantitative mass spectrometry. We quantified 8,119 proteins across two parental strains (SHR/Olalpcv and BN-Lx/Cub) and 29 HXB/BXH recombinant inbred (RI) strains, identifying 597 proteins with differential expression and 464 proteins linked to cis-acting quantitative trait loci (pQTLs). Proteogenomics identified 95 variant peptides, and sex-specific analyses revealed both shared and distinct cis-pQTLs. We improved the ability to pinpoint candidate genes underlying pQTLs by utilizing the rat pangenome and explored the connections between pQTLs in rats and human disorders. Collectively, this study highlights the value of large proteo-genetic datasets in elucidating protein modulation in the brain and its links to complex central nervous system (CNS) traits.},
}

@article {pmid40121180,
year = {2025},
author = {Bigey, F and Menatong Tene, X and Wessner, M and Devillers, H and Pradal, M and Cruaud, C and Aury, JM and Neuvéglise, C},
title = {Insights into the genomic and phenotypic diversity of Monosporozyma unispora strains isolated from anthropic environments.},
journal = {FEMS yeast research},
volume = {},
number = {},
pages = {},
doi = {10.1093/femsyr/foaf016},
pmid = {40121180},
issn = {1567-1364},
abstract = {Food microorganisms have been employed for centuries for the processing of fermented foods, leading to adapted populations with phenotypic traits of interest. The yeast Monosporozyma unispora (formerly Kazachstania unispora) has been identified in a wide range of fermented foods and beverages. Here, we studied the genetic and phenotypic diversity of a collection of 53 strains primarily derived from cheese, kefir, and sourdough. The 12.7 Mb genome of the type strain CLIB 234T was sequenced and assembled into near-complete chromosomes and annotated at the structural and functional levels, with 5639 coding sequences predicted. Comparison of the pangenome and core genome revealed minimal differences. From the complete yeast collection, we gathered genetic data (diversity, phylogeny, population structure) and phenotypic data (growth capacity on solid media). Population genomic analyses revealed low level of nucleotide diversity and strong population structure, with the presence of two major clades corresponding to ecological origins (cheese and kefir vs. plant derivatives). A high prevalence of extensive loss of heterozygosity and a slow linkage disequilibrium decay suggested a predominantly clonal mode of reproduction. Phenotypic analyses revealed growth variation under stress conditions, including high salinity and low pH, but no definitive link between phenotypic traits and environmental adaptation was established.},
}

@article {pmid40120273,
year = {2025},
author = {Chen, J and Yu, Q and Zhang, T and Ma, Y and Xiao, M and Zhang, C and Ge, Y},
title = {Quorum sensing luxI/R genes enhances cadmium detoxification in Aeromonas by up-regulating EPS production and cadmium resistance genes.},
journal = {Journal of hazardous materials},
volume = {491},
number = {},
pages = {137959},
doi = {10.1016/j.jhazmat.2025.137959},
pmid = {40120273},
issn = {1873-3336},
abstract = {The increasing cadmium (Cd) contamination in the environment poses a serious threat to ecosystem health and human safety. This study investigated the roles of quorum sensing (QS) genes luxI/R, key components of the QS system, in the Cd accumulation and detoxification in Aeromonas. Pan-genome analysis showed that luxI/R and Cd resistance genes were highly conserved in Aeromonas species. Strains of luxI/R knockout, complementation and overexpression were constructed via homologous recombination. The luxI/R deletion significantly reduced Cd removal by up to 32 %, decreased extracellular protein (18-36 %) and polysaccharide (19-33 %) contents, whereas luxI/R overexpression enhanced Cd removal capacity by 11 %. Transcriptomic and metabolomic analyses further revealed coordinated changes. In the ΔluxI/R strain, genes involved in assimilatory sulfate reduction and arginine biosynthesis were downregulated, accompanied by reduced levels of glycerophospholipid, vitamin, and cytochrome P450-related metabolites. In contrast, luxI/R overexpression upregulated arginine synthesis (2.0-3.5 fold) and sulfate assimilation (1.4-2.4 fold) genes, with corresponding increases of metabolites. Together these findings demonstrate that luxI/R genes may play a crucial role in regulation of EPS production and Cd resistance gene expression, thus enhancing our understanding of microbial Cd detoxification mechanisms.},
}

@article {pmid40118394,
year = {2025},
author = {Cuecas, A and Delgado, JA and González, JM},
title = {Inferring inter-phylum gene transfer events from unique genes detected in Parageobacillus thermoglucosidasius.},
journal = {Molecular phylogenetics and evolution},
volume = {},
number = {},
pages = {108329},
doi = {10.1016/j.ympev.2025.108329},
pmid = {40118394},
issn = {1095-9513},
abstract = {A pan-genome includes the complete pool of genes of a species including those recently acquired. The new additions of genetic material to a genome are frequently linked to horizontal gene transfer (HGT) processes and can confer adaptive advantages improving the recipient functional response and growth. Previous studies have reported that Parageobacillus have frequent DNA exchange mainly with other members of the phylum Bacillota sharing similar environments. Nevertheless, the occurrence of transfer events between phylogenetically distant microorganisms is scarcely known. In this work, based on the pan-genome of Parageobacillus thermoglucosidasius, we detected a number of unique genes within the species which were used to carry out BLAST searches to find out similar genes in distant bacteria taxa. We aimed to infer potential inter-phylum HGT events. Results suggested genetic exchanges among different phyla. Among them Actinomycetota, Pseudomonadota and the Bacteroidota/Chlorobiota group were the dominant observed phyla. Those HGT events frequently involved ATP binding cassette transporters, enzymes of the C metabolism and transcriptional regulators. Based on the frequency of these genes within specific phyla, directional HGT events could be proposed. A dominant origin of the suggested HGT events could be within the Bacillota. This exploratory analysis indicates that Bacillota are frequent exporters of DNA both within the phylum and to phylogenetically distant groups. Long-distance HGT can assist to better understand microbial evolution, the relevance of HGT processes within the prokaryotes and the genomic plasticity of microorganisms.},
}

@article {pmid40113550,
year = {2025},
author = {Thudi, M and Mascher, M and Jayakodi, M},
title = {Pangenome charts the genomic path for wheat improvement.},
journal = {Trends in plant science},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tplants.2025.03.002},
pmid = {40113550},
issn = {1878-4372},
abstract = {A wheat pangenome of 17 Chinese cultivars, recently developed by Jiao et al., reveals structural variants (SVs) shaped by cultural, dietary, and environmental changes. This resource provides access to East Asian wheat genetic diversity and supports genome-driven efforts to advance wheat improvement and adaptation to changing agricultural demands.},
}

@article {pmid40113404,
year = {2025},
author = {Wu, XM and Li, ZP and Huang, J and Wang, YH and Lu, X and Kan, B and Zhao, JL},
title = {[Pangenome analysis on plasmids carried by hypervirulent Klebsiella pneumoniae].},
journal = {Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi},
volume = {46},
number = {3},
pages = {506-513},
doi = {10.3760/cma.j.cn112338-20241026-00663},
pmid = {40113404},
issn = {0254-6450},
support = {2022YFC2303900//National Key Research and Development Program of China/ ; },
mesh = {*Klebsiella pneumoniae/genetics/pathogenicity/drug effects ; *Plasmids/genetics ; Virulence/genetics ; *Genome, Bacterial ; Replicon ; Virulence Factors/genetics ; Genetic Variation ; Anti-Bacterial Agents/pharmacology ; },
abstract = {Objective: To analyze the pangenome, pan drug resistance genes, pan virulence genes, pan replicons, and others of the plasmids carried by hypervirulent Klebsiella pneumoniae (hvKP) in the world and their evolutionary trends over time, and provide evidence for more comprehensive understanding of the evolution of genetic diversity, drug resistance genes, and virulence genes of the plasmids. Methods: From the National Center for Biotechnology Information database, a total 1 738 plasmids were screened from 524 strains with completed genome sequences in 2 136 strains of hvKP carrying plasmids. Through pangenome, pan drug resistance gene, and pan-virulence gene composition and functional analyses, the curves of pangenome size and new gene size against plasmid isolation time were established, revealing the diversity of the plasmid pangenome and its evolutionary patterns. Results: The homologous genes, homologous drug resistance genes, homologous virulence genes, and replicons of the plasmids carried by hvKP comprised of 12 906, 149, 107 and 89 types, respectively. The fitting curves for the number of new genes, new drug resistance genes and new replicons increased with the increase of plasmids in an open state, while the curve for novel virulence genes was in a closed state. A obvious increase in new drug resistance genes was observed during 2018-2019. Among the newly added drug resistance genes during 2021-2023, beside those conferring aminoglycoside resistance, they were mainly new subtypes conferring carbapenem resistance. Conclusions: The pangenome of plasmids carried by hvKP exhibited high diversity, with the plasmid pan genes, pan drug resistance genes, and pan replicon types gradually expanding, while the pan virulence genes remains stable. The increase in novel drug resistance genes in specific years and the emergence of new carbapenem-resistant gene subtypes during 2021-2023 suggested the need for strengthened drug resistance surveillance and prevention efforts, with particular attention to carbapenem resistance.},
}

*Klebsiella pneumoniae/genetics/pathogenicity/drug effects
*Plasmids/genetics
Virulence/genetics
*Genome, Bacterial
Replicon
Virulence Factors/genetics
Genetic Variation
Anti-Bacterial Agents/pharmacology

@article {pmid40113263,
year = {2025},
author = {Groza, C and Ge, B and Cheung, WA and Pastinen, T and Bourque, G},
title = {Expanded methylome and quantitative trait loci detection by long-read profiling of personal DNA.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279240.124},
pmid = {40113263},
issn = {1549-5469},
abstract = {Structural variants (SVs) are omnipresent in human DNA, yet their genotype and methylation statuses are rarely characterized due to previous limitations in genome assembly and detection of modified nucleotides. Also, the extent to which SVs act as methylation quantitative trait loci (SV-mQTLs) is largely unknown. Here, we generated a pangenome graph summarizing SVs in 782 de novo assemblies obtained from Genomic Answers for Kids, capturing 14.6 million CpG dinucleotides that are absent from the CHM13v2 reference (SV-CpGs), thus expanding their number by 43.6%. Using 435 methylomes, we genotyped 4.06 million SV-CpGs, of which 3.93 million (96.8%) are methylated at least once. Nonrepeat sequences contribute 1.59 × 10[6] novel SV-CpGs, followed by centromeric satellites (6.57 × 10[5]), simple repeats (5.40 × 10[5]), Alu elements (5.07 × 10[5]), satellites (2.17 × 10[5]), LINE-1s (1.83 × 10[5]), and SVA (SINE-VNTR-Alu) elements (1.50 × 10[5]). Centromeric satellites, simple repeats, and SVAs are overrepresented in SV-CpGs versus reference CpGs. Similarly, methylation levels in SV-CpGs are more variable than in reference CpGs. To explore if SVs are potentially causal for functional variation, we measured SV-mQTLs. This revealed over 230,464 methylation bins where the methylation is associated with common SVs within 100 kbp. Finally, we identified 65,659 methylation bins (28.5%) where the leading QTL variant is an SV. In conclusion, we demonstrate that graph pangenomes provide full SV structures, the associated methylation variation, and reveal tens of thousands of SV-mQTLs, underscoring the importance of assembly based analyses of human traits.},
}

@article {pmid40113261,
year = {2025},
author = {Li, Q and Keskus, AG and Wagner, J and Izydorczyk, MB and Timp, W and Sedlazeck, FJ and Klein, AP and Zook, JM and Kolmogorov, M and Schatz, MC},
title = {Unraveling the hidden complexity of cancer through long-read sequencing.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.280041.124},
pmid = {40113261},
issn = {1549-5469},
abstract = {Cancer is fundamentally a disease of the genome, characterized by extensive genomic, transcriptomic, and epigenomic alterations. Most current studies predominantly use short-read sequencing, gene panels, or microarrays to explore these alterations; however, these technologies can systematically miss or misrepresent certain types of alterations, especially structural variants, complex rearrangements, and alterations within repetitive regions. Long-read sequencing is rapidly emerging as a transformative technology for cancer research by providing a comprehensive view across the genome, transcriptome, and epigenome, including the ability to detect alterations that previous technologies have overlooked. In this review, we explore the current applications of long-read sequencing for both germline and somatic cancer analysis. We provide an overview of the computational methodologies tailored to long-read data and highlight key discoveries and resources within cancer genomics that were previously inaccessible with prior technologies. We also address future opportunities and persistent challenges, including the experimental and computational requirements needed to scale to larger sample sizes, the hurdles in sequencing and analyzing complex cancer genomes, and opportunities for leveraging machine learning and artificial intelligence technologies for cancer informatics. We further discuss how the telomere-to-telomere genome and the emerging human pangenome could enhance the resolution of cancer genome analysis, potentially revolutionizing early detection and disease monitoring in patients. Finally, we outline strategies for transitioning long-read sequencing from research applications to routine clinical practice.},
}

@article {pmid40111256,
year = {2025},
author = {Roberts, MD and Davis, O and Josephs, EB and Williamson, RJ},
title = {K-mer-based Approaches to Bridging Pangenomics and Population Genetics.},
journal = {Molecular biology and evolution},
volume = {42},
number = {3},
pages = {},
doi = {10.1093/molbev/msaf047},
pmid = {40111256},
issn = {1537-1719},
support = {GM142829/NH/NIH HHS/United States ; IOS-1934384//National Science Foundation/ ; T32-GM110523/GM/NIGMS NIH HHS/United States ; },
mesh = {*Genetics, Population/methods ; *Genetic Variation ; *Genomics/methods ; Humans ; },
abstract = {Many commonly studied species now have more than one chromosome-scale genome assembly, revealing a large amount of genetic diversity previously missed by approaches that map short reads to a single reference. However, many species still lack multiple reference genomes and correctly aligning references to build pangenomes can be challenging for many species, limiting our ability to study this missing genomic variation in population genetics. Here, we argue that k-mers are a very useful but underutilized tool for bridging the reference-focused paradigms of population genetics with the reference-free paradigms of pangenomics. We review current literature on the uses of k-mers for performing three core components of most population genetics analyses: identifying, measuring, and explaining patterns of genetic variation. We also demonstrate how different k-mer-based measures of genetic variation behave in population genetic simulations according to the choice of k, depth of sequencing coverage, and degree of data compression. Overall, we find that k-mer-based measures of genetic diversity scale consistently with pairwise nucleotide diversity (π) up to values of about π=0.025 (R2=0.97) for neutrally evolving populations. For populations with even more variation, using shorter k-mers will maintain the scalability up to at least π=0.1. Furthermore, in our simulated populations, k-mer dissimilarity values can be reliably approximated from counting bloom filters, highlighting a potential avenue to decreasing the memory burden of k-mer-based genomic dissimilarity analyses. For future studies, there is a great opportunity to further develop methods to identifying selected loci using k-mers.},
}

*Genetics, Population/methods
*Genetic Variation
*Genomics/methods
Humans

@article {pmid40108696,
year = {2025},
author = {Yu, X and Qu, M and Wu, P and Zhou, M and Lai, E and Liu, H and Guo, S and Li, S and Yao, X and Gao, L},
title = {Correction: Super pan-genome reveals extensive genomic variations associated with phenotypic divergence in Actinidia.},
journal = {Molecular horticulture},
volume = {5},
number = {1},
pages = {31},
pmid = {40108696},
issn = {2730-9401},
}

@article {pmid40105318,
year = {2025},
author = {Choudoir, MJ and Narayanan, A and Rodriguez-Ramos, D and Simoes, R and Efroni, A and Sondrini, A and DeAngelis, KM},
title = {Pangenomes suggest ecological-evolutionary responses to experimental soil warming.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0005925},
doi = {10.1128/msphere.00059-25},
pmid = {40105318},
issn = {2379-5042},
abstract = {Below-ground carbon transformations that contribute to healthy soils represent a natural climate change mitigation, but newly acquired traits adaptive to climate stress may alter microbial feedback mechanisms. To better define microbial evolutionary responses to long-term climate warming, we study microorganisms from an ongoing in situ soil warming experiment where, for over three decades, temperate forest soils are continuously heated at 5°C above ambient. We hypothesize that across generations of chronic warming, genomic signatures within diverse bacterial lineages reflect adaptations related to growth and carbon utilization. From our bacterial culture collection isolated from experimental heated and control plots, we sequenced genomes representing dominant taxa sensitive to warming, including lineages of Actinobacteria, Alphaproteobacteria, and Betaproteobacteria. We investigated genomic attributes and functional gene content to identify signatures of adaptation. Comparative pangenomics revealed accessory gene clusters related to central metabolism, competition, and carbon substrate degradation, with few functional annotations explicitly associated with long-term warming. Trends in functional gene patterns suggest genomes from heated plots were relatively enriched in central carbohydrate and nitrogen metabolism pathways, while genomes from control plots were relatively enriched in amino acid and fatty acid metabolism pathways. We observed that genomes from heated plots had less codon bias, suggesting potential adaptive traits related to growth or growth efficiency. Codon usage bias varied for organisms with similar 16S rrn operon copy number, suggesting that these organisms experience different selective pressures on growth efficiency. Our work suggests the emergence of lineage-specific trends as well as common ecological-evolutionary microbial responses to climate change.IMPORTANCEAnthropogenic climate change threatens soil ecosystem health in part by altering below-ground carbon cycling carried out by microbes. Microbial evolutionary responses are often overshadowed by community-level ecological responses, but adaptive responses represent potential changes in traits and functional potential that may alter ecosystem function. We predict that microbes are adapting to climate change stressors like soil warming. To test this, we analyzed the genomes of bacteria from a soil warming experiment where soil plots have been experimentally heated 5°C above ambient for over 30 years. While genomic attributes were unchanged by long-term warming, we observed trends in functional gene content related to carbon and nitrogen usage and genomic indicators of growth efficiency. These responses may represent new parameters in how soil ecosystems feedback to the climate system.},
}

@article {pmid40104030,
year = {2025},
author = {Gayathri, M and Sharanya, R and Renukadevi, P and Malathi, VG and Ghosh, A and Nallusamy, S and Varanavasiappan, S and Nakkeeran, S and Alkahtani, S},
title = {Genomic configuration of Bacillus subtilis (NMB01) unveils its antiviral activity against Orthotospovirus arachinecrosis infecting tomato.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1517157},
pmid = {40104030},
issn = {1664-462X},
abstract = {Orthotospovirus arachinecrosis (groundnut bud necrosis virus, GBNV) infecting tomato is a devastating viral pathogen responsible for severe yield losses of up to 100%. Considering the significance of the plant growth-promoting bacteria to induce innate immunity, attempts were made to evaluate the antiviral efficacy of Bacillus subtilis NMB01 against GBNV in cowpea and tomato. Foliar application of B. subtilis NMB01 at 1.5% onto the leaves of cowpea and tomato followed by challenge inoculation with GBNV significantly reduced the incidence of GBNV from 80% to 90% in response to the untreated inoculated control. Hence, we had a quest to understand if any genes were contributing toward the suppression of GBNV in assay hosts. To unveil the secrecy, whole-genome sequencing of B. subtilis NMB01 was carried out. The genome sequence of NMB01 revealed the presence of secondary metabolite biosynthetic gene clusters, including non-ribosomal peptide synthetases (NRPSs) and polyketide synthases (PKSs) which also encoded bacteriocins and antimicrobial peptides. The pan-genome analysis identified 1,640 core genes, 4,885 dispensable genes, and 60 unique genes, including MAMP genes that induce host immune responses. Comparative genome and proteome analysis with other genomes of B. subtilis strains in a public domain through OrthoVenn analysis revealed the presence of 4,241 proteins, 3,695 clusters, and 655 singletons in our study isolate. Furthermore, the NMB01-treated tomato plants increased the levels of defense-related genes (MAPKK1, WRKY33, PR1, PAL, and NPR1), enhancing immune system priming against GBNV infection. These findings suggest that B. subtilis NMB01 can be used as a promising biological control agent for managing plant viral disease sustainably.},
}

@article {pmid40102251,
year = {2025},
author = {Vedrine, E and Bessenay, L and Philipponnet, C and Dancer, M and Bertholet-Thomas, A},
title = {Granulomatous nephropathy: have you thought about genetics?.},
journal = {Pediatric nephrology (Berlin, Germany)},
volume = {},
number = {},
pages = {},
pmid = {40102251},
issn = {1432-198X},
abstract = {We report here the case of a 16-year-old girl with chronic kidney disease, where biopsy revealed tubulointerstitial nephropathy with granulomas. Initial treatments included immunosuppressive therapy unless genetic testing with exome sequencing identified nephronophthisis due to a homozygous deletion of the NPHP1 gene, marking a unique instance of granulomatous nephropathy related to nephronophthisis. With severe kidney damage, her function has not recovered, necessitating peritoneal dialysis and transplantation. This case highlights the need to consider nephronophthisis in inflammatory interstitial and granulomatous nephropathy, especially when it appears severe and early in life. In addition, it underscores the importance of genetic testing for accurate diagnosis and management in pediatric nephropathies.},
}

@article {pmid40100768,
year = {2025},
author = {Chen, YW and Su, YC and Chen, WY and Wu, JH and Chen, JW and Su, SL and Chen, CS and Tsai, PF and Ko, WC and Chen, PL},
title = {Comprehensive Genomic Analysis of Antimicrobial Resistance in Aeromonas dhakensis.},
journal = {Microbial drug resistance (Larchmont, N.Y.)},
volume = {},
number = {},
pages = {},
doi = {10.1089/mdr.2024.0212},
pmid = {40100768},
issn = {1931-8448},
abstract = {Aeromonas dhakensis is prevalent in aquatic environments in Taiwan and known for its notable antimicrobial resistance. However, comprehensive pan-genomic studies for this species in Taiwan are limited. This study analyzed 28 clinical A. dhakensis isolates using single-molecule real-time sequencing technology, coupled with diverse databases, to elucidate the whole genomes. The focus was on phylogenetic relatedness, antimicrobial resistance genes, and mobile genetic elements. Genomic analysis and multilocus sequence typing were utilized to identify A. dhakensis strains of heterogeneous origins. The detection of various β-lactamase genes (blacphA, blaimiH, blaAQU, blaOXA, blaTEM-1, blaTRU-1, and blaVEB) in clinical A. dhakensis isolates raises concern, especially considering the use of carbapenems and third-generation cephalosporins in patients with severe infections. Notably, most A. dhakensis strains carry chromosome-encoded β-lactamases, including AmpC, metallo-β-lactamase, and oxacillinase, and were susceptible to cefepime in drug susceptibility tests. A. dhakensis strains were also susceptible to aminoglycosides, fluoroquinolones, tigecycline, and trimethoprim/sulfamethoxazole. Three of the 28 A. dhakensis isolates carried plasmids containing an array of drug resistance genes, suggesting this species is likely a recipient or donor of drug resistance genes through horizontal gene transfer. Our findings provide valuable insights into the antimicrobial resistance of A. dhakensis, highlighting the medical implications of its β-lactamase diversity and its potential role in the horizontal gene transfer of drug resistance genes.},
}

@article {pmid40098156,
year = {2025},
author = {Liu, R and Hu, C and Gao, D and Li, M and Yuan, X and Chen, L and Shu, Q and Wang, Z and Yang, X and Dai, Z and Yu, H and Yang, F and Zheng, A and Lv, M and Garg, V and Jiao, C and Zhang, H and Hou, W and Teng, C and Zhou, X and Du, C and Xiang, C and Xu, D and Tang, Y and Chitikineni, A and Duan, Y and Maalouf, F and Agrawal, SK and Wei, L and Zhao, N and Barmukh, R and Li, X and Wang, D and Ding, H and Liu, Y and Chen, X and Varshney, RK and He, Y and Zong, X and Yang, T},
title = {A special short-wing petal faba genome and genetic dissection of floral and yield-related traits accelerate breeding and improvement of faba bean.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {62},
pmid = {40098156},
issn = {1474-760X},
support = {2021YFD1200105//National Key R&D Program of China/ ; 32272134//National Natural Science Foundation of China/ ; 32241042//National Natural Science Foundation of China/ ; 32360466//Reginal Science Foundation of National Natural Science Foundation of China/ ; SCCXTD-2020-20//Project of Sichuan Beans and Cereals Innovation Team of China Agriculture Research System/ ; 2021YFYZ0022//The Sichuan Provincial Science and Technology Support Breeding Project during the 14th 5-Year Plan/ ; CARS-08//China Agriculture Research System of MOF and MARA- Food Legumes/ ; CARS-08//China Agriculture Research System of MOF and MARA- Food Legumes/ ; CARS-08//China Agriculture Research System of MOF and MARA- Food Legumes/ ; CARS-08//China Agriculture Research System of MOF and MARA- Food Legumes/ ; CARS-08//China Agriculture Research System of MOF and MARA- Food Legumes/ ; JBGS[2021]003, JBGS[2021]056//The "JBGS" Project of Seed Industry Revitalization in Jiangsu Province/ ; UMU UMU2403-009RTX//Achieving improved genetic gain for yield in chickpea, faba bean, and lentil using genetic diversity project in Australia/ ; 202202AE090003//The Science and Technology Project of Yunnan Province/ ; 2130135//The Crop Germplasm Resources Protection/ ; 2130135//The Crop Germplasm Resources Protection/ ; ASTIP//Agricultural Science and Technology Innovation Program in CAAS/ ; ASTIP//Agricultural Science and Technology Innovation Program in CAAS/ ; },
mesh = {*Vicia faba/genetics ; *Genome, Plant ; *Plant Breeding ; *Flowers/genetics ; *Quantitative Trait Loci ; *Genome-Wide Association Study ; Genetic Variation ; Phenotype ; },
abstract = {BACKGROUND: A comprehensive study of the genome and genetics of superior germplasms is fundamental for crop improvement. As a widely adapted protein crop with high yield potential, the improvement in breeding and development of the seeds industry of faba bean have been greatly hindered by its giant genome size and high outcrossing rate.

RESULTS: To fully explore the genomic diversity and genetic basis of important agronomic traits, we first generate a de novo genome assembly and perform annotation of a special short-wing petal faba bean germplasm (VF8137) exhibiting a low outcrossing rate. Comparative genome and pan-genome analyses reveal the genome evolution characteristics and unique pan-genes among the three different faba bean genomes. In addition, the genome diversity of 558 accessions of faba bean germplasm reveals three distinct genetic groups and remarkable genetic differences between the southern and northern germplasms. Genome-wide association analysis identifies several candidate genes associated with adaptation- and yield-related traits. We also identify one candidate gene related to short-wing petals by combining quantitative trait locus mapping and bulked segregant analysis. We further elucidate its function through multiple lines of evidence from functional annotation, sequence variation, expression differences, and protein structure variation.

CONCLUSIONS: Our study provides new insights into the genome evolution of Leguminosae and the genomic diversity of faba bean. It offers valuable genomic and genetic resources for breeding and improvement of faba bean.},
}

*Vicia faba/genetics
*Genome, Plant
*Plant Breeding
*Flowers/genetics
*Quantitative Trait Loci
*Genome-Wide Association Study
Genetic Variation
Phenotype

@article {pmid40097267,
year = {2025},
author = {Olbrich, J and Büchler, T and Ohlebusch, E},
title = {Generating Multiple Alignments on a Pangenomic Scale.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btaf104},
pmid = {40097267},
issn = {1367-4811},
abstract = {MOTIVATION: Since novel long read sequencing technologies allow for de novo assembly of many individuals of a species, high-quality assemblies are becoming widely available. For example, the recently published draft human pangenome reference was based on assemblies composed of contigs. There is an urgent need for a software-tool that is able to generate a multiple alignment of genomes of the same species because current multiple sequence alignment programs cannot deal with such a volume of data.

RESULTS: We show that the combination of a well-known anchor-based method with the technique of prefix-free parsing yields an approach that is able to generate multiple alignments on a pangenomic scale, provided that large-scale structural variants are rare. Furthermore, experiments with real world data show that our software tool PANAMA (PANgenomic Anchor-based Multiple Alignment) significantly outperforms current state-of-the art programs.

AVAILABILITY: Source code is available at: https://gitlab.com/qwerzuiop/panama, archived at swh  :  1: dir: e90c9f664995acca9063245cabdd97549cf39694.},
}

@article {pmid40094775,
year = {2025},
author = {Pedrozo, R and Osakina, A and Huang, Y and Nicolli, CP and Wang, L and Jia, Y},
title = {Status on Genetic Resistance to Rice Blast Disease in the Post-Genomic Era.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {5},
pages = {},
pmid = {40094775},
issn = {2223-7747},
support = {445546//USDA Agriculture Research Service (ARS)/ ; },
abstract = {Rice blast, caused by Magnaporthe oryzae, is a major threat to global rice production, necessitating the development of resistant cultivars through genetic improvement. Breakthroughs in rice genomics, including the complete genome sequencing of japonica and indica subspecies and the availability of various sequence-based molecular markers, have greatly advanced the genetic analysis of blast resistance. To date, approximately 122 blast-resistance genes have been identified, with 39 of these genes cloned and molecularly characterized. The application of these findings in marker-assisted selection (MAS) has significantly improved rice breeding, allowing for the efficient integration of multiple resistance genes into elite cultivars, enhancing both the durability and spectrum of resistance. Pangenomic studies, along with AI-driven tools like AlphaFold2, RoseTTAFold, and AlphaFold3, have further accelerated the identification and functional characterization of resistance genes, expediting the breeding process. Future rice blast disease management will depend on leveraging these advanced genomic and computational technologies. Emphasis should be placed on enhancing computational tools for the large-scale screening of resistance genes and utilizing gene editing technologies such as CRISPR-Cas9 for functional validation and targeted resistance enhancement and deployment. These approaches will be crucial for advancing rice blast resistance, ensuring food security, and promoting agricultural sustainability.},
}

@article {pmid40092765,
year = {2025},
author = {Pacce, VD and Guimarães, AM and Kremer, FS and Ferreira, GN and Vedova-Costa, JMD and Dos Santos, AC and Dellagostin, OA and Soccol, CR and Thomaz-Soccol, V},
title = {Integrated Bioinformatics Analysis for Target Identification and Evaluation of Recombinant Protein as an Antigen for Intradermal Skin Test in Bovine Tuberculosis Diagnosis.},
journal = {ACS omega},
volume = {10},
number = {9},
pages = {9187-9196},
pmid = {40092765},
issn = {2470-1343},
abstract = {Bovine tuberculosis (bTB) is a respiratory disease caused by Mycobacterium bovis, posing a significant threat to animal health and the livestock industry. Current control strategies for bTB rely on diagnostic tests and slaughter policies. However, the limitations of existing diagnostic methods, which depend on PPD antigens, necessitate the exploration of alternative antigens to enhance the accuracy and reliability of bTB diagnosis. This study aimed to identify, produce, and evaluate novel antigens for use in the intradermal skin test for bTB diagnosis. A pangenome analysis of four Mycobacterium species identified 12 unique genes specific to M. bovis SP38. Further integrated bioinformatic analysis revealed 224 genomic islands associated with virulence and pathogenesis. Among these, a highly antigenic protein, termed HP28, was selected for in vivo testing. The recombinant HP28 protein (rHP28) was expressed in E. coli and assessed for its ability to induce intradermal skin reactions in guinea pigs. The rHP28 protein elicited a skin reaction of 6.6 mm at 72 h post-injection, whereas negative controls showed no reaction. This study presents a pipeline for the selection of antigens using integrated bioinformatic analysis to identify diagnostic targets that can effectively distinguish between sensitized and non-sensitized animals, offering a promising approach for improving bTB diagnostics.},
}

@article {pmid40092526,
year = {2025},
author = {Zytnicki, M},
title = {Assessing genome conservation on pangenome graphs with PanSel.},
journal = {Bioinformatics advances},
volume = {5},
number = {1},
pages = {vbaf018},
pmid = {40092526},
issn = {2635-0041},
abstract = {MOTIVATION: With more and more telomere-to-telomere genomes assembled, pangenomes make it possible to capture the genomic diversity of a species. Because they introduce less biases, pangenomes, represented as graphs, tend to supplant the usual linear representation of a reference genome, augmented with variations. However, this major change requires new tools adapted to this data structure. Among the numerous questions that can be addressed to a pangenome graph is the search for conserved or divergent genes.

RESULTS: In this article, we present a new tool, named PanSel, which computes a conservation score for each segment of the genome, and finds genomic regions that are significantly conserved, or divergent. PanSel can be used on prokaryotes and eukaryotes, with a sequence identity not less than 98%.

PanSel, written in C++11 with no dependency, is available at https://github.com/mzytnicki/pansel.},
}

@article {pmid40089923,
year = {2025},
author = {Mukhopadhya, I and Martin, JC and Shaw, S and Gutierrez-Torrejon, M and Boteva, N and McKinley, AJ and Gratz, SW and Scott, KP},
title = {Novel insights into carbohydrate utilisation, antimicrobial resistance, and sporulation potential in Roseburia intestinalis isolates across diverse geographical locations.},
journal = {Gut microbes},
volume = {17},
number = {1},
pages = {2473516},
doi = {10.1080/19490976.2025.2473516},
pmid = {40089923},
issn = {1949-0984},
mesh = {Humans ; *Carbohydrate Metabolism ; *Spores, Bacterial/genetics/growth & development/metabolism ; *Gastrointestinal Microbiome ; Anti-Bacterial Agents/pharmacology ; Genome, Bacterial ; Drug Resistance, Bacterial ; Phylogeny ; },
abstract = {Roseburia intestinalis is one of the most abundant and important butyrate-producing human gut anaerobic bacteria that plays an important role in maintaining health and is a potential next-generation probiotic. We investigated the pangenome of 16 distinct strains, isolated over several decades, identifying local and time-specific adaptations. More than 50% of the genes in each individual strain were assigned to the core genome, and 77% of the cloud genes were unique to individual strains, revealing the high level of genome conservation. Co-carriage of the same enzymes involved in carbohydrate binding and degradation in all strains highlighted major pathways in carbohydrate utilization and reveal the importance of xylan, starch and mannose as key growth substrates. A single strain had adapted to use rhamnose as a sole growth substrate, the first time this has been reported. The ubiquitous presence of motility and sporulation gene clusters demonstrates the importance of these phenotypes for gut survival and acquisition of this bacterium. More than half the strains contained functional, potentially transferable, tetracycline resistance genes. This study advances our understanding of the importance of R. intestinalis within the gut ecosystem by elucidating conserved metabolic characteristics among different strains, isolated from different locations. This information will help to devise dietary strategies to increase the abundance of this species providing health benefits.},
}

Humans
*Carbohydrate Metabolism
*Spores, Bacterial/genetics/growth & development/metabolism
*Gastrointestinal Microbiome
Anti-Bacterial Agents/pharmacology
Genome, Bacterial
Drug Resistance, Bacterial
Phylogeny

@article {pmid40087830,
year = {2025},
author = {Simon, V and Trouillon, J and Attrée, I and Elsen, S},
title = {Functional and Pangenomic Exploration of Roc Two-Component Regulatory Systems Identifies Novel Players Across Pseudomonas Species.},
journal = {Molecular microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1111/mmi.15357},
pmid = {40087830},
issn = {1365-2958},
support = {//CNRS, the CEA and the Grenoble Alpes University/ ; //French Ministry of Education and Research/ ; ANR-17-EURE-0003//University Grenoble Alpes Graduate School/ ; },
abstract = {The opportunistic pathogen Pseudomonas aeruginosa relies on a large collection of two-component regulatory systems (TCSs) to sense and adapt to changing environments. Among them, the Roc (regulation of cup) system is a one-of-a-kind network of branched TCSs, composed of two histidine kinases (HKs-RocS1 and RocS2) interacting with three response regulators (RRs-RocA1, RocR, and RocA2), which regulate virulence, antibiotic resistance, and biofilm formation. Based on extensive work on the Roc system, previous data suggested the existence of other key regulators yet to be discovered. In this work, we identified PA4080, renamed RocA3, as a fourth RR that is activated by RocS1 and RocS2 and that positively controls the expression of the cupB operon. Comparative genomic analysis of the locus identified a gene-rocR3-adjacent to rocA3 in a subpopulation of strains that encodes a protein with structural and functional similarity to the c-di-GMP phosphodiesterase RocR. Furthermore, we identified a fourth branch of the Roc system consisting of the PA2583 HK, renamed RocS4, and the Hpt protein HptA. Using a bacterial two-hybrid system, we showed that RocS4 interacts with HptA, which in turn interacts with RocA1, RocA2, and RocR3. Finally, we mapped the pangenomic RRs repertoire, establishing a comprehensive view of the plasticity of such regulators among clades of the species. Overall, our work provides a comprehensive inter-species definition of the Roc system, nearly doubling the number of proteins known to be involved in this interconnected network of TCSs controlling pathogenicity in Pseudomonas species.},
}

@article {pmid40083908,
year = {2025},
author = {Kumari, K and Sinha, A and Sharma, PK and Singh, RP},
title = {In-depth genome and comparative genome analysis of a metal-resistant environmental isolate Pseudomonas aeruginosa S-8.},
journal = {Frontiers in cellular and infection microbiology},
volume = {15},
number = {},
pages = {1511507},
pmid = {40083908},
issn = {2235-2988},
mesh = {*Pseudomonas aeruginosa/genetics/isolation & purification/metabolism/drug effects ; *Genome, Bacterial/genetics ; *Soil Microbiology ; *Phylogeny ; *RNA, Ribosomal, 16S/genetics ; Genomics ; Base Composition ; India ; Multigene Family ; Drug Resistance, Bacterial/genetics ; Metals/metabolism ; Secondary Metabolism ; Sequence Analysis, DNA ; },
abstract = {The present study aimed to identify the mechanisms underlying the survival of an environmental bacterium originally isolated from the waste-contaminated soil of Jhiri, Ranchi, India. Based on 16S rRNA, ANI (average nucleotide identity), and BLAST Ring Image Generator (BRIG) analysis, the isolated strain was identified as Pseudomonas aeruginosa. The present study extends the characterization of this bacterium through genomic and comparative genomic analysis to understand the genomic features pertaining to survival in stressed environments. The sequencing of the bacterium at Illumina HiSeq platform revealed that it possessed a 6.8 Mb circular chromosome with 65.9% GC content and 63 RNAs sequence. The genome also harbored several genes associated to plant growth promotion i.e. phytohormone and siderophore production, phosphate solubilization, motility, and biofilm formation, etc. The genomic analysis with online tools unraveled the various genes belonging to the bacterial secretion system, antibiotic resistance, virulence, and efflux pumps, etc. The presence of biosynthetic gene clusters (BCGs) indicated that large numbers of genes were associated to non-ribosomal synthesized peptide synthetase, polyketide synthetase, and other secondary metabolite production. Additionally, its genomes encode various CAZymes such as glycoside hydrolases and other genes associated with lignocellulose breakdown, suggesting that strain S-8 have strong biomass degradation potential. Furthermore, pan-genome analysis based on a comparison of whole genomes showed that core genome represented the largest part of the gene pools. Therefore, genome and comparative genome analysis of Pseudomonas strains is valuable for understanding the mechanism of resistance to metal stress, genome evolution, HGT events, and therefore, opens a new perspective to exploit a newly isolated bacterium for biotechnological applications.},
}

*Pseudomonas aeruginosa/genetics/isolation & purification/metabolism/drug effects
*Genome, Bacterial/genetics
*Soil Microbiology
*Phylogeny
*RNA, Ribosomal, 16S/genetics
Genomics
Base Composition
India
Multigene Family
Drug Resistance, Bacterial/genetics
Metals/metabolism
Secondary Metabolism
Sequence Analysis, DNA

@article {pmid40083414,
year = {2025},
author = {Shi, G and Dai, Y and Zhou, D and Chen, M and Zhang, J and Bi, Y and Liu, S and Wu, Q},
title = {An alignment- and reference-free strategy using k-mer present pattern for population genomic analyses.},
journal = {Mycology},
volume = {16},
number = {1},
pages = {309-323},
pmid = {40083414},
issn = {2150-1203},
abstract = {Pangenomes are replacing single reference genomes to capture all variants within a species or clade, but their analysis predominantly leverages graph-based methods that require multiple high-quality genomes and computationally intensive multiple-genome alignments. K-mer decomposition is an alternative to graph-based pangenomes. However, how to directly use k-mers for the population genetic analyses is unknown. Here, we developed a novel strategy that uses the variants of k-mer count in the genome for population analyses. To test the effectivity of this method, we compared it directly to the SNP-based method on the analysis of population structure and genetic diversity of 267 Saccharomyces cerevisiae strains within two simulated datasets and a real sequence dataset. The population structure identified with k-mers recapitulates that obtained using SNPs, indicating the effectiveness of k-mer-based approach, and higher genetic diversity within real dataset supported k-mers contained more genetic variants. Based on k-mer frequency, we found not only SNP but also some insertion/deletion and horizontal gene transfer (HGT) fragments related to the adaptive evolution of S. cerevisiae. Our study creates a framework for the alignment- and reference-free (ARF) method in population genetic analyses, which will be more pronounced in the species with no complete genome or highly diverged species.},
}