@article {pmid38619241,
year = {2024},
author = {Feng, Y and Arsenault, D and Louyakis, AS and Altman-Price, N and Gophna, U and Papke, RT and Gogarten, JP},
title = {Using the pan-genomic framework for the discovery of genomic islands in the haloarchaeon Halorubrum ezzemoulense.},
journal = {mBio},
volume = {},
number = {},
pages = {e0040824},
doi = {10.1128/mbio.00408-24},
pmid = {38619241},
issn = {2150-7511},
abstract = {In this study, we use pan-genomics to characterize the genomic variability of the widely dispersed halophilic archaeal species Halorubrum ezzemoulense (Hez). We include a multi-regional sampling of newly sequenced, high-quality draft genomes. The pan-genome graph of the species reveals 50 genomic islands that represent rare accessory genetic capabilities available to members. Most notably, we observe rearrangements that have led to the insertion/recombination/replacement of mutually exclusive genomic islands in equivalent genome positions ("homeocassettes"). These conflicting islands encode for similar functions, but homologs from islands located between the same core genes exhibit high divergence on the amino acid level, while the neighboring core genes are nearly identical. Both islands of a homeocassette often coexist in the same geographic location, suggesting that either island may be beyond the reach of selective sweeps and that these loci of divergence between Hez members are maintained and persist long term. This implies that subsections of the population have different niche preferences and rare metabolic capabilities. After an evaluation of the gene content in the homeocassettes, we speculate that these islands may play a role in the speciation, niche adaptability, and group selection dynamics in Hez. Though homeocassettes are first described in this study, similar replacements and divergence of genes on genomic islands have been previously reported in other Haloarchaea and distantly related Archaea, suggesting that homeocassettes may be a feature in a wide range of organisms outside of Hez.IMPORTANCEThis study catalogs the rare genes discovered in strains of the species Halorubrum ezzemoulense (Hez), an obligate halophilic archaeon, through the perspective of its pan-genome. These rare genes are often found to be arranged on islands that confer metabolic and transport functions and contain genes that have eluded previous studies. The discovery of divergent, but homologous islands occupying equivalent genome positions ("homeocassettes") in different genomes, reveals significant new information on genome evolution in Hez. Homeocassette pairs encode for similar functions, but their dissimilarity and distribution imply high rates of recombination, different specializations, and niche preferences in Hez. The coexistence of both islands of a homeocassette pair in multiple environments demonstrates that both islands are beyond the reach of selective sweeps and that these genome content differences between strains persist long term. The switch between islands through recombination under different environmental conditions may lead to a greater range of niche adaptability in Hez.},
}

@article {pmid38613721,
year = {2024},
author = {Zhang, H and Su, X and Zheng, X and Liu, M and Zhao, C and Liu, X and Ma, Z and Zhang, S and Zhang, W},
title = {vB_EcoM-P896 coliphage isolated from duck sewage can lyse both intestinal pathogenic Escherichia coli and extraintestinal pathogenic E. coli.},
journal = {International microbiology : the official journal of the Spanish Society for Microbiology},
volume = {},
number = {},
pages = {},
pmid = {38613721},
issn = {1618-1905},
support = {2022AH052192//Natural Science Foundation of Anhui Province/ ; 2022AH052192//Natural Science Foundation of Anhui Province/ ; 2022AH052192//Natural Science Foundation of Anhui Province/ ; gxgnfx2022135//The Project of Cultivating Outstanding Talents in Colleges/ ; gxgnfx2022135//The Project of Cultivating Outstanding Talents in Colleges/ ; gxgnfx2022135//The Project of Cultivating Outstanding Talents in Colleges/ ; KJ2021ZD0153//The Natural Science Research Project of Anhui Province/ ; KJ2021ZD0153//The Natural Science Research Project of Anhui Province/ ; KJ2021ZD0153//The Natural Science Research Project of Anhui Province/ ; wzykjtd202002//Wuhu Institute of Technology level science and technology team/ ; wzykjtd202002//Wuhu Institute of Technology level science and technology team/ ; wzykjtd202002//Wuhu Institute of Technology level science and technology team/ ; },
abstract = {Pathogenic Escherichia coli strains cause diseases in both humans and animals. The limiting factors to prevent as well as control infections from pathogenic E. coli strains are their pathotypes, serotypes, and drug resistance. Herein, a bacteriophage (vB_EcoM-P896) has been isolated from duck sewage. Furthermore, aside from targeting intestinal pathogenic E. coli strains like enteropathogenic E. coli, Shiga toxin-producing E. coli, entero-invasive E. coli, and enteroaggregative E. coli, vB_EcoM-P896 can cause lysis in extraintestinal pathogenic E. coli strains such as avian pathogenic E. coli. Stability analysis revealed that vB_EcoM-P896 was stable under the following conditions: temperature, 4℃-50℃; pH, 3-11. The sequencing of the vB_EcoM-P896 genome was conducted utilizing an HiSeq system (Illumina, San Diego, CA) and subjected to de novo assembling with the aid of Spades 3.11.1. The characteristics of the DNA genome were as follows: size, 170,656 bp; GC content, 40.4%; the number of putative coding regions, 294. Transmission electron microscopy analysis of morphology and genome analysis revealed that the phage vB_EcoM-P896 belonged to the order Caudovirales and the family Myoviridae. The pan-genome analysis of vB_EcoM-P896 was divided into two levels. The first level involved the analysis of 91 strains of muscle tail phages, which were mainly divided into 5 groups. The second level involved the analysis of 24 strains of myophage with high homology. Of the 1480 gene clusters, 23 were shared core genes. Neighbor-joining phylogenetic trees were constructed using the Poisson model with MEGA6.0 based on the conserved sequences of phage proteins, the amino acid sequence of the terminase large subunit, and tail fibrin. Further analysis revealed that vB_EcoM-P896 was a typical T4-like potent phage with potential clinical applications.},
}

@article {pmid38613617,
year = {2024},
author = {Aziz, T and Hangyu, H and Naveed, M and Shabbir, MA and Sarwar, A and Nasbeeb, J and Zhennai, Y and Alharbi, M},
title = {Genotypic Profiling, Functional Analysis, Cholesterol-Lowering Ability, and Angiotensin I-Converting Enzyme (ACE) Inhibitory Activity of Probiotic Lactiplantibacillus plantarum K25 via Different Approaches.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {38613617},
issn = {1867-1314},
support = {2017YFE0131800//National Natural Science Foundation of China/ ; },
abstract = {Due to its alleged health advantages, several uses in biotechnology and food safety, the well-known probiotic strain Lactiplantibacillus plantarum K25 has drawn interest. This in-depth investigation explores the genetic diversity, makeup, and security characteristics of the microbial genome of L. plantarum K25, providing insightful knowledge about its genotypic profile and functional characteristics. Utilizing cutting-edge bioinformatics techniques like comparative genomics, pan-genomics, and genotypic profiling was carried out to reveal the strain's multidimensional potential in various fields. The results not only add to our understanding of the genetic makeup of L. plantarum K25 but also show off its acceptability in various fields, notably in biotechnology and food safety. The explanation of evolutionary links, which highlights L. plantarum K25's aptitude as a probiotic, is one notable finding from this research. Its safety profile, which is emphasized by the absence of genes linked to antibiotic resistance, is crucial and supports its status as a promising probiotic option.},
}

@article {pmid38612691,
year = {2024},
author = {Chen, L and Chen, K and Xi, X and Du, X and Zou, X and Ma, Y and Song, Y and Luo, C and Weining, S},
title = {The Evolution, Expression Patterns, and Domestication Selection Analysis of the Annexin Gene Family in the Barley Pan-Genome.},
journal = {International journal of molecular sciences},
volume = {25},
number = {7},
pages = {},
doi = {10.3390/ijms25073883},
pmid = {38612691},
issn = {1422-0067},
abstract = {Plant annexins constitute a conserved protein family that plays crucial roles in regulating plant growth and development, as well as in responses to both biotic and abiotic stresses. In this study, a total of 144 annexin genes were identified in the barley pan-genome, comprising 12 reference genomes, including cultivated barley, landraces, and wild barley. Their chromosomal locations, physical-chemical characteristics, gene structures, conserved domains, and subcellular localizations were systematically analyzed to reveal the certain differences between wild and cultivated populations. Through a cis-acting element analysis, co-expression network, and large-scale transcriptome analysis, their involvement in growth, development, and responses to various stressors was highlighted. It is worth noting that HvMOREXann5 is only expressed in pistils and anthers, indicating its crucial role in reproductive development. Based on the resequencing data from 282 barley accessions worldwide, genetic variations in thefamily were investigated, and the results showed that 5 out of the 12 identified HvMOREXanns were affected by selection pressure. Genetic diversity and haplotype frequency showed notable reductions between wild and domesticated barley, suggesting that a genetic bottleneck occurred on the annexin family during the barley domestication process. Finally, qRT-PCR analysis confirmed the up-regulation of HvMOREXann7 under drought stress, along with significant differences between wild accessions and varieties. This study provides some insights into the genome organization and genetic characteristics of the annexin gene family in barley at the pan-genome level, which will contribute to better understanding its evolution and function in barley and other crops.},
}

@article {pmid38608279,
year = {2024},
author = {Wong, B and Ferguson, JM and Do, JY and Gamaarachchi, H and Deveson, IW},
title = {Streamlining remote nanopore data access with slow5curl.},
journal = {GigaScience},
volume = {13},
number = {},
pages = {},
doi = {10.1093/gigascience/giae016},
pmid = {38608279},
issn = {2047-217X},
support = {MRF1173594//Australian Medical Research Futures Fund/ ; DE230100178//Australian Research Council/ ; },
abstract = {BACKGROUND: As adoption of nanopore sequencing technology continues to advance, the need to maintain large volumes of raw current signal data for reanalysis with updated algorithms is a growing challenge. Here we introduce slow5curl, a software package designed to streamline nanopore data sharing, accessibility, and reanalysis.

RESULTS: Slow5curl allows a user to fetch a specified read or group of reads from a raw nanopore dataset stored on a remote server, such as a public data repository, without downloading the entire file. Slow5curl uses an index to quickly fetch specific reads from a large dataset in SLOW5/BLOW5 format and highly parallelized data access requests to maximize download speeds. Using all public nanopore data from the Human Pangenome Reference Consortium (>22 TB), we demonstrate how slow5curl can be used to quickly fetch and reanalyze raw signal reads corresponding to a set of target genes from each individual in large cohort dataset (n = 91), minimizing the time, egress costs, and local storage requirements for their reanalysis.

CONCLUSIONS: We provide slow5curl as a free, open-source package that will reduce frictions in data sharing for the nanopore community: https://github.com/BonsonW/slow5curl.},
}

@article {pmid38607544,
year = {2024},
author = {Wang, J and Hu, H and Jiang, X and Zhang, S and Yang, W and Dong, J and Yang, T and Ma, Y and Zhou, L and Chen, J and Nie, S and Liu, C and Ning, Y and Zhu, X and Liu, B and Yang, J and Zhao, J},
title = {Pangenome-Wide Association Study and Transcriptome Analysis Reveal a Novel QTL and Candidate Genes Controlling both Panicle and Leaf Blast Resistance in Rice.},
journal = {Rice (New York, N.Y.)},
volume = {17},
number = {1},
pages = {27},
pmid = {38607544},
issn = {1939-8425},
support = {2020A1515111025//the GuangDong Basic and Applied Basic Research Foundation/ ; 2022NPY00005//Seed industry revitalization project of special fund for rural revitalization strategy in Guangdong Province/ ; 32161143009//the National Natural Science Foundation of China/ ; G2022030024L//the National Project/ ; 2023B1212060042//Guangdong Key Laboratory of New Technology in Rice Breeding/ ; 2023KJ106//the Innovation Team Project of Guangdong Modern Agricultural Industrial System/ ; },
abstract = {Cultivating rice varieties with robust blast resistance is the most effective and economical way to manage the rice blast disease. However, rice blast disease comprises leaf and panicle blast, which are different in terms of resistance mechanisms. While many blast resistant rice cultivars were bred using genes conferring resistance to only leaf or panicle blast, mining durable and effective quantitative trait loci (QTLs) for both panicle and leaf blast resistance is of paramount importance. In this study, we conducted a pangenome-wide association study (panGWAS) on 9 blast resistance related phenotypes using 414 international diverse rice accessions from an international rice panel. This approach led to the identification of 74 QTLs associated with rice blast resistance. One notable locus, qPBR1, validated in a F4:5 population and fine-mapped in a Heterogeneous Inbred Family (HIF), exhibited broad-spectrum, major and durable blast resistance throughout the growth period. Furthermore, we performed transcriptomic analysis of 3 resistant and 3 sensitive accessions at different time points after infection, revealing 3,311 differentially expressed genes (DEGs) potentially involved in blast resistance. Integration of the above results identified 6 candidate genes within the qPBR1 locus, with no significant negative effect on yield. The results of this study provide valuable germplasm resources, QTLs, blast response genes and candidate functional genes for developing rice varieties with enduring and broad-spectrum blast resistance. The qPBR1, in particular, holds significant potential for breeding new rice varieties with comprehensive and durable resistance throughout their growth period.},
}

@article {pmid38604355,
year = {2024},
author = {Yin, Z and Liang, J and Zhang, M and Chen, B and Yu, Z and Tian, X and Deng, X and Peng, L},
title = {Pan-genome insights into adaptive evolution of bacterial symbionts in mixed host-microbe symbioses represented by human gut microbiota Bacteroides cellulosilyticus.},
journal = {The Science of the total environment},
volume = {},
number = {},
pages = {172251},
doi = {10.1016/j.scitotenv.2024.172251},
pmid = {38604355},
issn = {1879-1026},
abstract = {Animal hosts harbor diverse assemblages of microbial symbionts that play crucial roles in the host's lifestyle. The link between microbial symbiosis and host development remains poorly understood. In particular, little is known about the adaptive evolution of gut bacteria in host-microbe symbioses. Recently, symbiotic relationships have been categorized as open, closed, or mixed, reflecting their modes of inter-host transmission and resulting in distinct genomic features. Members of the genus Bacteroides are the most abundant human gut microbiota and possess both probiotic and pathogenic potential, providing an excellent model for studying pan-genome evolution in symbiotic systems. Here, we determined the complete genome of an novel clinical strain PL2022, which was isolated from a blood sample and performed pan-genome analyses on a representative set of Bacteroides cellulosilyticus strains to quantify the influence of the symbiotic relationship on the evolutionary dynamics. B. cellulosilyticus exhibited correlated genomic features with both open and closed symbioses, suggesting a mixed symbiosis. An open pan-genome is characterized by abundant accessory gene families, potential horizontal gene transfer (HGT), and diverse mobile genetic elements (MGEs), indicating an innovative gene pool, mainly associated with genomic islands and plasmids. However, massive parallel gene loss, weak purifying selection, and accumulation of positively selected mutations were the main drivers of genome reduction in B. cellulosilyticus. Metagenomic read recruitment analyses showed that B. cellulosilyticus members are globally distributed and active in human gut habitats, in line with predominant vertical transmission in the human gut. However, existence and/or high abundance were also detected in non-intestinal tissues, other animal hosts, and non-host environments, indicating occasional horizontal transmission to new niches, thereby creating arenas for the acquisition of novel genes. This case study of adaptive evolution under a mixed host-microbe symbiosis advances our understanding of symbiotic pan-genome evolution. Our results highlight the complexity of genetic evolution in this unusual intestinal symbiont.},
}

@article {pmid38605417,
year = {2024},
author = {Roder, T and Pimentel, G and Fuchsmann, P and Stern, MT and von Ah, U and Vergères, G and Peischl, S and Brynildsrud, O and Bruggmann, R and Bär, C},
title = {Scoary2: rapid association of phenotypic multi-omics data with microbial pan-genomes.},
journal = {Genome biology},
volume = {25},
number = {1},
pages = {93},
pmid = {38605417},
issn = {1474-760X},
support = {GRS-070/17//Gebert Rüf Stiftung/ ; },
abstract = {Unraveling bacterial gene function drives progress in various areas, such as food production, pharmacology, and ecology. While omics technologies capture high-dimensional phenotypic data, linking them to genomic data is challenging, leaving 40-60% of bacterial genes undescribed. To address this bottleneck, we introduce Scoary2, an ultra-fast microbial genome-wide association studies (mGWAS) software. With its data exploration app and improved performance, Scoary2 is the first tool to enable the study of large phenotypic datasets using mGWAS. As proof of concept, we explore the metabolome of yogurts, each produced with a different Propionibacterium reichii strain and discover two genes affecting carnitine metabolism.},
}

@article {pmid38605254,
year = {2024},
author = {Cunha-Ferreira, IC and Vizzotto, CS and Freitas, MAM and Peixoto, J and Carvalho, LS and Tótola, MR and Thompson, FL and Krüger, RH},
title = {Genomic and physiological characterization of Kitasatospora sp. nov., an actinobacterium with potential for biotechnological application isolated from Cerrado soil.},
journal = {Brazilian journal of microbiology : [publication of the Brazilian Society for Microbiology]},
volume = {},
number = {},
pages = {},
pmid = {38605254},
issn = {1678-4405},
support = {Conselho Nacional de Desenvolvimento Científico e Tecnológico//Conselho Nacional de Desenvolvimento Científico e Tecnológico/ ; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior//Coordenação de Aperfeiçoamento de Pessoal de Nível Superior/ ; Fundação de Apoio à Pesquisa do Distrito Federal//Fundação de Apoio à Pesquisa do Distrito Federal/ ; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro//Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro/ ; },
abstract = {An Actinobacteria - Kitasatospora sp. K002 - was isolated from the soil of Cerrado, a savanna-like Brazilian biome. Herein, we conducted a phylogenetic, phenotypic and physiological characterization, revealing its potential for biotechnological applications. Kitasatospora sp. K002 is an aerobic, non-motile, Gram-positive bacteria that forms grayish-white mycelium on solid cultures and submerged spores with vegetative mycelia on liquid cultures. The strain showed antibacterial activity against Bacillus subtilis, Pseudomonas aeruginosa and Escherichia coli. Genomic analysis indicated that Kitasatospora xanthocidica JCM 4862 is the closest strain to K002, with a dDDH of 32.8-37.8% and an ANI of 86.86% and the pangenome investigations identified a high number of rare genes. A total of 60 gene clusters of 22 different types were detected by AntiSMASH, and 22 gene clusters showed low similarity (< 10%) with known compounds, which suggests the potential production of novel bioactive compounds. In addition, phylogenetic analysis and morphophysiological characterization clearly distinguished Kitasatospora sp. K002 from other related species. Therefore, we propose that Kitasatospora sp. K002 should be recognized as a new species of the genus Kitasatospora - Kitasatospora brasiliensis sp. nov. (type strains = K002).},
}

@article {pmid38605175,
year = {2024},
author = {Lian, Q and Huettel, B and Walkemeier, B and Mayjonade, B and Lopez-Roques, C and Gil, L and Roux, F and Schneeberger, K and Mercier, R},
title = {A pan-genome of 69 Arabidopsis thaliana accessions reveals a conserved genome structure throughout the global species range.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {38605175},
issn = {1546-1718},
support = {TRR 341/1-456082119//Deutsche Forschungsgemeinschaft (German Research Foundation)/ ; },
abstract = {Although originally primarily a system for functional biology, Arabidopsis thaliana has, owing to its broad geographical distribution and adaptation to diverse environments, developed into a powerful model in population genomics. Here we present chromosome-level genome assemblies of 69 accessions from a global species range. We found that genomic colinearity is very conserved, even among geographically and genetically distant accessions. Along chromosome arms, megabase-scale rearrangements are rare and typically present only in a single accession. This indicates that the karyotype is quasi-fixed and that rearrangements in chromosome arms are counter-selected. Centromeric regions display higher structural dynamics, and divergences in core centromeres account for most of the genome size variations. Pan-genome analyses uncovered 32,986 distinct gene families, 60% being present in all accessions and 40% appearing to be dispensable, including 18% private to a single accession, indicating unexplored genic diversity. These 69 new Arabidopsis thaliana genome assemblies will empower future genetic research.},
}

@article {pmid38600518,
year = {2024},
author = {Hong, A and Oliva, M and Köppl, D and Bannai, H and Boucher, C and Gagie, T},
title = {Pfp-fm: an accelerated FM-index.},
journal = {Algorithms for molecular biology : AMB},
volume = {19},
number = {1},
pages = {15},
pmid = {38600518},
issn = {1748-7188},
support = {R01AI14180/HG/NHGRI NIH HHS/United States ; },
abstract = {FM-indexes are crucial data structures in DNA alignment, but searching with them usually takes at least one random access per character in the query pattern. Ferragina and Fischer [1] observed in 2007 that word-based indexes often use fewer random accesses than character-based indexes, and thus support faster searches. Since DNA lacks natural word-boundaries, however, it is necessary to parse it somehow before applying word-based FM-indexing. In 2022, Deng et al. [2] proposed parsing genomic data by induced suffix sorting, and showed that the resulting word-based FM-indexes support faster counting queries than standard FM-indexes when patterns are a few thousand characters or longer. In this paper we show that using prefix-free parsing-which takes parameters that let us tune the average length of the phrases-instead of induced suffix sorting, gives a significant speedup for patterns of only a few hundred characters. We implement our method and demonstrate it is between 3 and 18 times faster than competing methods on queries to GRCh38, and is consistently faster on queries made to 25,000, 50,000 and 100,000 SARS-CoV-2 genomes. Hence, it seems our method accelerates the performance of count over all state-of-the-art methods with a moderate increase in the memory. The source code for PFP - FM is available at https://github.com/AaronHong1024/afm .},
}

@article {pmid38592762,
year = {2024},
author = {Lazaridi, E and Kapazoglou, A and Gerakari, M and Kleftogianni, K and Passa, K and Sarri, E and Papasotiropoulos, V and Tani, E and Bebeli, PJ},
title = {Crop Landraces and Indigenous Varieties: A Valuable Source of Genes for Plant Breeding.},
journal = {Plants (Basel, Switzerland)},
volume = {13},
number = {6},
pages = {},
doi = {10.3390/plants13060758},
pmid = {38592762},
issn = {2223-7747},
abstract = {Landraces and indigenous varieties comprise valuable sources of crop species diversity. Their utilization in plant breeding may lead to increased yield and enhanced quality traits, as well as resilience to various abiotic and biotic stresses. Recently, new approaches based on the rapid advancement of genomic technologies such as deciphering of pangenomes, multi-omics tools, marker-assisted selection (MAS), genome-wide association studies (GWAS), and CRISPR/Cas9 gene editing greatly facilitated the exploitation of landraces in modern plant breeding. In this paper, we present a comprehensive overview of the implementation of new genomic technologies and highlight their importance in pinpointing the genetic basis of desirable traits in landraces and indigenous varieties of annual, perennial herbaceous, and woody crop species cultivated in the Mediterranean region. The need for further employment of advanced -omic technologies to unravel the full potential of landraces and indigenous varieties underutilized genetic diversity is also indicated. Ultimately, the large amount of genomic data emerging from the investigation of landraces and indigenous varieties reveals their potential as a source of valuable genes and traits for breeding. The role of landraces and indigenous varieties in mitigating the ongoing risks posed by climate change in agriculture and food security is also highlighted.},
}

@article {pmid38591882,
year = {2024},
author = {Xing, Y and Clark, JR and Chang, JD and Zulk, JJ and Chirman, DM and Piedra, F-A and Vaughan, EE and Hernandez Santos, HJ and Patras, KA and Maresso, AW},
title = {Progress toward a vaccine for extraintestinal pathogenic E. coli (ExPEC) II: efficacy of a toxin-autotransporter dual antigen approach.},
journal = {Infection and immunity},
volume = {},
number = {},
pages = {e0044023},
doi = {10.1128/iai.00440-23},
pmid = {38591882},
issn = {1098-5522},
abstract = {Extraintestinal pathogenic Escherichia coli (ExPEC) is a leading cause of worldwide morbidity and mortality, the top cause of antimicrobial-resistant (AMR) infections, and the most frequent cause of life-threatening sepsis and urinary tract infections (UTI) in adults. The development of an effective and universal vaccine is complicated by this pathogen's pan-genome, its ability to mix and match virulence factors and AMR genes via horizontal gene transfer, an inability to decipher commensal from pathogens, and its intimate association and co-evolution with mammals. Using a pan virulome analysis of >20,000 sequenced E. coli strains, we identified the secreted cytolysin α-hemolysin (HlyA) as a high priority target for vaccine exploration studies. We demonstrate that a catalytically inactive pure form of HlyA, expressed in an autologous host using its own secretion system, is highly immunogenic in a murine host, protects against several forms of ExPEC infection (including lethal bacteremia), and significantly lowers bacterial burdens in multiple organ systems. Interestingly, the combination of a previously reported autotransporter (SinH) with HlyA was notably effective, inducing near complete protection against lethal challenge, including commonly used infection strains ST73 (CFT073) and ST95 (UTI89), as well as a mixture of 10 of the most highly virulent sequence types and strains from our clinical collection. Both HlyA and HlyA-SinH combinations also afforded some protection against UTI89 colonization in a murine UTI model. These findings suggest recombinant, inactive hemolysin and/or its combination with SinH warrant investigation in the development of an E. coli vaccine against invasive disease.},
}

@article {pmid38585972,
year = {2024},
author = {Marin, MG and Wippel, C and Quinones-Olvera, N and Behruznia, M and Jeffrey, BM and Harris, M and Mann, BC and Rosenthal, A and Jacobson, KR and Warren, RM and Li, H and Meehan, CJ and Farhat, MR},
title = {Analysis of the limited M. tuberculosis accessory genome reveals potential pitfalls of pan-genome analysis approaches.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.03.21.586149},
pmid = {38585972},
abstract = {Pan-genome analysis is a fundamental tool in the study of bacterial genome evolution. Benchmarking the accuracy of pan-genome analysis methods is challenging, because it can be significantly influenced by both the methodology used to compare genomes, as well as differences in the accuracy and representativeness of the genomes analyzed. In this work, we curated a collection of 151 Mycobacterium tuberculosis (Mtb) isolates to evaluate sources of variability in pan-genome analysis. Mtb is characterized by its clonal evolution, absence of horizontal gene transfer, and limited accessory genome, making it an ideal test case for this study. Using a state-of-the-art graph-genome approach, we found that a majority of the structural variation observed in Mtb originates from rearrangement, deletion, and duplication of redundant nucleotide sequences. In contrast, we found that pan-genome analyses that focus on comparison of coding sequences (at the amino acid level) can yield surprisingly variable results, driven by differences in assembly quality and the softwares used. Upon closer inspection, we found that coding sequence annotation discrepancies were a major contributor to inflated Mtb accessory genome estimates. To address this, we developed panqc, a software that detects annotation discrepancies and collapses nucleotide redundancy in pan-genome estimates. We characterized the effect of the panqc adjustment on both pan-genome analysis of Mtb and E. coli genomes, and highlight how different levels of genomic diversity are prone to unique biases. Overall, this study illustrates the need for careful methodological selection and quality control to accurately map the evolutionary dynamics of a bacterial species.},
}

@article {pmid38584940,
year = {2024},
author = {Carhuaricra-Huaman, D and Gonzalez, IHL and Ramos, PL and da Silva, AM and Setubal, JC},
title = {Analysis of twelve genomes of the bacterium Kerstersia gyiorum from brown-throated sloths (Bradypus variegatus), the first from a non-human host.},
journal = {PeerJ},
volume = {12},
number = {},
pages = {e17206},
pmid = {38584940},
issn = {2167-8359},
abstract = {Kerstersia gyiorum is a Gram-negative bacterium found in various animals, including humans, where it has been associated with various infections. Knowledge of the basic biology of K. gyiorum is essential to understand the evolutionary strategies of niche adaptation and how this organism contributes to infectious diseases; however, genomic data about K. gyiorum is very limited, especially from non-human hosts. In this work, we sequenced 12 K. gyiorum genomes isolated from healthy free-living brown-throated sloths (Bradypus variegatus) in the Parque Estadual das Fontes do Ipiranga (São Paulo, Brazil), and compared them with genomes from isolates of human origin, in order to gain insights into genomic diversity, phylogeny, and host specialization of this species. Phylogenetic analysis revealed that these K. gyiorum strains are structured according to host. Despite the fact that sloth isolates were sampled from a single geographic location, the intra-sloth K. gyiorum diversity was divided into three clusters, with differences of more than 1,000 single nucleotide polymorphisms between them, suggesting the circulation of various K. gyiorum lineages in sloths. Genes involved in mobilome and defense mechanisms against mobile genetic elements were the main source of gene content variation between isolates from different hosts. Sloth-specific K. gyiorum genome features include an IncN2 plasmid, a phage sequence, and a CRISPR-Cas system. The broad diversity of defense elements in K. gyiorum (14 systems) may prevent further mobile element flow and explain the low amount of mobile genetic elements in K. gyiorum genomes. Gene content variation may be important for the adaptation of K. gyiorum to different host niches. This study furthers our understanding of diversity, host adaptation, and evolution of K. gyiorum, by presenting and analyzing the first genomes of non-human isolates.},
}

@article {pmid38580497,
year = {2024},
author = {Wolfe, JM},
title = {Pangenomes at the limits of evolution.},
journal = {Trends in ecology & evolution},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tree.2024.03.008},
pmid = {38580497},
issn = {1872-8383},
abstract = {Evolutionary pathways can be random or deterministic. In a recent article, Beavan et al. investigate this balance by applying machine learning models to microbial pangenomes. The presence of almost one-third of genes can be reliably inferred, indicating a surprising amount of predictable evolution.},
}

@article {pmid38577974,
year = {2024},
author = {Cannon, EK and Portwood, JL and Hayford, RK and Haley, OC and Gardiner, JM and Andorf, CM and Woodhouse, MR},
title = {Enhanced pan-genomic resources at the maize genetics and genomics database.},
journal = {Genetics},
volume = {},
number = {},
pages = {},
doi = {10.1093/genetics/iyae036},
pmid = {38577974},
issn = {1943-2631},
support = {//US Department of Agriculture/ ; 5030-21000-068-00-D//Agricultural Research Service/ ; 440229//Corn Insects and Crop Genetics Research Unit in Ames, Iowa/ ; },
abstract = {Pan-genomes, encompassing the entirety of genetic sequences found in a collection of genomes within a clade, are more useful than single reference genomes for studying species diversity. This is especially true for a species like Zea mays, which has a particularly diverse and complex genome. Presenting pan-genome data, analyses, and visualization is challenging, especially for a diverse species, but more so when pan-genomic data is linked to extensive gene model and gene data, including classical gene information, markers, insertions, expression and proteomic data, and protein structures as is the case at MaizeGDB. Here, we describe MaizeGDB's expansion to include the genic subset of the Zea pan-genome in a pan-gene data center featuring the maize genomes hosted at MaizeGDB, and the outgroup teosinte Zea genomes from the Pan-Andropoganeae project. The new data center offers a variety of browsing and visualization tools, including sequence alignment visualization, gene trees and other tools, to explore pan-genes in Zea that were calculated by the pipeline Pandagma. Combined, these data will help maize researchers study the complexity and diversity of Zea, and to use the comparative functions to validate pan-gene relationships for a selected gene model.},
}

@article {pmid38576793,
year = {2024},
author = {Borowska-Beszta, M and Smoktunowicz, M and Horoszkiewicz, D and Jonca, J and Waleron, MM and Gawor, J and Mika, A and Sledzinski, T and Waleron, K and Waleron, M},
title = {Comparative genomics, pangenomics, and phenomic studies of Pectobacterium betavasculorum strains isolated from sugar beet, potato, sunflower, and artichoke: insights into pathogenicity, virulence determinants, and adaptation to the host plant.},
journal = {Frontiers in plant science},
volume = {15},
number = {},
pages = {1352318},
pmid = {38576793},
issn = {1664-462X},
abstract = {INTRODUCTION: Bacteria of genus Pectobacterium, encompassing economically significant pathogens affecting various plants, includes the species P. betavasculorum, initially associated with beetroot infection. However, its host range is much broader. It causes diseases of sunflower, potato, tomato, carrots, sweet potato, radish, squash, cucumber, and chrysanthemum. To explain this phenomenon, a comprehensive pathogenomic and phenomic characterisation of P. betavasculorum species was performed.

METHODS: Genomes of P. betavasculorum strains isolated from potato, sunflower, and artichoke were sequenced and compared with those from sugar beet isolates. Metabolic profiling and pathogenomic analyses were conducted to assess virulence determinants and adaptation potential. Pathogenicity assays were performed on potato tubers and chicory leaves to confirm in silico predictions of disease symptoms. Phenotypic assays were also conducted to assess the strains ability to synthesise homoserine lactones and siderophores.

RESULTS: The genome size ranged from 4.675 to 4.931 kbp, and GC % was between 51.0% and 51.2%. The pangenome of P. betavasculorum is open and comprises, on average, 4,220 gene families. Of these, 83% of genes are the core genome, and 2% of the entire pangenome are unique genes. Strains isolated from sugar beet have a smaller pangenome size and a higher number of unique genes than those from other plants. Interestingly, genomes of strains from artichoke and sunflower share 391 common CDS that are not present in the genomes of other strains from sugar beet or potato. Those strains have only one unique gene. All strains could use numerous sugars as building materials and energy sources and possessed a high repertoire of virulence determinants in the genomes. P. betavasculorum strains were able to cause disease symptoms on potato tubers and chicory leaves. They were also able to synthesise homoserine lactones and siderophores.

DISCUSSION: The findings underscore the adaptability of P. betavasculorum to diverse hosts and environments. Strains adapted to plants with high sugar content in tissues have a different composition of fatty acids in membranes and a different mechanism of replenishing nitrogen in case of deficiency of this compound than strains derived from other plant species. Extensive phenomics and genomic analyses performed in this study have shown that P. betavasculorum species is an agronomically relevant pathogen.},
}

@article {pmid38506894,
year = {2024},
author = {Baek, J and Lawson, J and Rahimzadeh, V},
title = {Investigating the Roles and Responsibilities of Institutional Signing Officials After Data Sharing Policy Reform for Federally Funded Research in the United States: National Survey.},
journal = {JMIR formative research},
volume = {8},
number = {},
pages = {e49822},
pmid = {38506894},
issn = {2561-326X},
abstract = {BACKGROUND: New federal policies along with rapid growth in data generation, storage, and analysis tools are together driving scientific data sharing in the United States. At the same, triangulating human research data from diverse sources can also create situations where data are used for future research in ways that individuals and communities may consider objectionable. Institutional gatekeepers, namely, signing officials (SOs), are therefore at the helm of compliant management and sharing of human data for research. Of those with data governance responsibilities, SOs most often serve as signatories for investigators who deposit, access, and share research data between institutions. Although SOs play important leadership roles in compliant data sharing, we know surprisingly little about their scope of work, roles, and oversight responsibilities.

OBJECTIVE: The purpose of this study was to describe existing institutional policies and practices of US SOs who manage human genomic data access, as well as how these may change in the wake of new Data Management and Sharing requirements for National Institutes of Health-funded research in the United States.

METHODS: We administered an anonymous survey to institutional SOs recruited from biomedical research institutions across the United States. Survey items probed where data generated from extramurally funded research are deposited, how researchers outside the institution access these data, and what happens to these data after extramural funding ends.

RESULTS: In total, 56 institutional SOs participated in the survey. We found that SOs frequently approve duplicate data deposits and impose stricter access controls when data use limitations are unclear or unspecified. In addition, 21% (n=12) of SOs knew where data from federally funded projects are deposited after project funding sunsets. As a consequence, most investigators deposit their scientific data into "a National Institutes of Health-funded repository" to meet the Data Management and Sharing requirements but also within the "institution's own repository" or a third-party repository.

CONCLUSIONS: Our findings inform 5 policy recommendations and best practices for US SOs to improve coordination and develop comprehensive and consistent data governance policies that balance the need for scientific progress with effective human data protections.},
}

@article {pmid38573185,
year = {2024},
author = {Hall, MB and Coin, LJM},
title = {Pangenome databases improve host removal and mycobacteria classification from clinical metagenomic data.},
journal = {GigaScience},
volume = {13},
number = {},
pages = {},
doi = {10.1093/gigascience/giae010},
pmid = {38573185},
issn = {2047-217X},
support = {2020/MRF1200856//Australian Government Medical Research Future Fund/ ; //Genomics Health Futures Mission/ ; },
abstract = {BACKGROUND: Culture-free real-time sequencing of clinical metagenomic samples promises both rapid pathogen detection and antimicrobial resistance profiling. However, this approach introduces the risk of patient DNA leakage. To mitigate this risk, we need near-comprehensive removal of human DNA sequences at the point of sequencing, typically involving the use of resource-constrained devices. Existing benchmarks have largely focused on the use of standardized databases and largely ignored the computational requirements of depletion pipelines as well as the impact of human genome diversity.

RESULTS: We benchmarked host removal pipelines on simulated and artificial real Illumina and Nanopore metagenomic samples. We found that construction of a custom kraken database containing diverse human genomes results in the best balance of accuracy and computational resource usage. In addition, we benchmarked pipelines using kraken and minimap2 for taxonomic classification of Mycobacterium reads using standard and custom databases. With a database representative of the Mycobacterium genus, both tools obtained improved specificity and sensitivity, compared to the standard databases for classification of Mycobacterium tuberculosis. Computational efficiency of these custom databases was superior to most standard approaches, allowing them to be executed on a laptop device.

CONCLUSIONS: Customized pangenome databases provide the best balance of accuracy and computational efficiency when compared to standard databases for the task of human read removal and M. tuberculosis read classification from metagenomic samples. Such databases allow for execution on a laptop, without sacrificing accuracy, an especially important consideration in low-resource settings. We make all customized databases and pipelines freely available.},
}

@article {pmid38567256,
year = {2024},
author = {Olbrich, M and Bartels, L and Wohlers, I},
title = {Sequencing technologies and hardware-accelerated parallel computing transform computational genomics research.},
journal = {Frontiers in bioinformatics},
volume = {4},
number = {},
pages = {1384497},
pmid = {38567256},
issn = {2673-7647},
}

@article {pmid38567138,
year = {2024},
author = {Jiang, M and Chen, M and Zeng, J and Du, Z and Xiao, J},
title = {A comprehensive evaluation of the potential of three next-generation short-read-based plant pan-genome construction strategies for the identification of novel non-reference sequence.},
journal = {Frontiers in plant science},
volume = {15},
number = {},
pages = {1371222},
pmid = {38567138},
issn = {1664-462X},
abstract = {Pan-genome studies are important for understanding plant evolution and guiding the breeding of crops by containing all genomic diversity of a certain species. Three short-read-based strategies for plant pan-genome construction include iterative individual, iteration pooling, and map-to-pan. Their performance is very different under various conditions, while comprehensive evaluations have yet to be conducted nowadays. Here, we evaluate the performance of these three pan-genome construction strategies for plants under different sequencing depths and sample sizes. Also, we indicate the influence of length and repeat content percentage of novel sequences on three pan-genome construction strategies. Besides, we compare the computational resource consumption among the three strategies. Our findings indicate that map-to-pan has the greatest recall but the lowest precision. In contrast, both two iterative strategies have superior precision but lower recall. Factors of sample numbers, novel sequence length, and the percentage of novel sequences' repeat content adversely affect the performance of all three strategies. Increased sequencing depth improves map-to-pan's performance, while not affecting the other two iterative strategies. For computational resource consumption, map-to-pan demands considerably more than the other two iterative strategies. Overall, the iterative strategy, especially the iterative pooling strategy, is optimal when the sequencing depth is less than 20X. Map-to-pan is preferable when the sequencing depth exceeds 20X despite its higher computational resource consumption.},
}

@article {pmid38564163,
year = {2024},
author = {Marlin, R and Loger, JS and Joachim, C and Ebring, C and Robert-Siegwald, G and Pennont, S and Rose, M and Raguette, K and Suez-Panama, V and Ulric-Gervaise, S and Lusbec, S and Bera, O and Vallard, A and Aline-Fardin, A and Colomba, E and Jean-Laurent, M},
title = {Copy number signatures and CCNE1 amplification reveal the involvement of replication stress in high-grade endometrial tumors oncogenesis.},
journal = {Cellular oncology (Dordrecht)},
volume = {},
number = {},
pages = {},
pmid = {38564163},
issn = {2211-3436},
abstract = {PURPOSE: Managing high-grade endometrial cancer in Martinique poses significant challenges. The diversity of copy number alterations in high-grade endometrial tumors, often associated with a TP53 mutation, is a key factor complicating treatment. Due to the high incidence of high-grade tumors with poor prognosis, our study aimed to characterize the molecular signature of these tumors within a cohort of 25 high-grade endometrial cases.

METHODS: We conducted a comprehensive pangenomic analysis to categorize the copy number alterations involved in these tumors. Whole-Exome Sequencing (WES) and Homologous Recombination (HR) analysis were performed. The alterations obtained from the WES were classified into various signatures using the Copy Number Signatures tool available in COSMIC.

RESULTS: We identified several signatures that correlated with tumor stage and disctinct prognoses. These signatures all seem to be linked to replication stress, with CCNE1 amplification identified as the primary driver of oncogenesis in over 70% of tumors analyzed.

CONCLUSION: The identification of CCNE1 amplification, which is currently being explored as a therapeutic target in clinical trials, suggests new treatment strategies for high-grade endometrial cancer. This finding holds particular significance for Martinique, where access to care is challenging.},
}

@article {pmid38560215,
year = {2024},
author = {Comba-González, NB and Chaves-Moreno, D and Santamaría-Vanegas, J and Montoya-Castaño, D},
title = {A pan-genomic assessment: Delving into the genome of the marine epiphyte Bacillus altitudinis strain 19_A and other very close Bacillus strains from multiple environments.},
journal = {Heliyon},
volume = {10},
number = {7},
pages = {e27820},
doi = {10.1016/j.heliyon.2024.e27820},
pmid = {38560215},
issn = {2405-8440},
abstract = {Marine macroalgae are the habitat of epiphytic bacteria and provide several conditions for a beneficial biological interaction to thrive. Although Bacillus is one of the most abundant epiphytic genera, genomic information on marine macroalgae-associated Bacillus species remains scarce. In this study, we further investigated our previously published genome of the epiphytic strain Bacillus altitudinis 19_A to find features that could be translated to potential metabolites produced by this microorganism, as well as genes that play a role in its interaction with its macroalgal host. To achieve this goal, we performed a pan-genome analysis of Bacillus sp. and a codon bias assessment, including the genome of the strain Bacillus altitudinis 19_A and 29 complete genome sequences of closely related Bacillus strains isolated from soil, marine environments, plants, extreme environments, air, and food. This genomic analysis revealed that Bacillus altitudinis 19_A possessed unique genes encoding proteins involved in horizontal gene transfer, DNA repair, transcriptional regulation, and bacteriocin biosynthesis. In this comparative analysis, codon bias was not associated with the habitat of the strains studied. Some accessory genes were identified in the Bacillus altitudinis 19_A genome that could be related to its epiphytic lifestyle, as well as gene clusters for the biosynthesis of a sporulation-killing factor and a bacteriocin, showing their potential as a source of antimicrobial peptides. Our results provide a comprehensive view of the Bacillus altitudinis 19_A genome to understand its adaptation to the marine environment and its potential as a producer of bioactive compounds.},
}

@article {pmid38559026,
year = {2024},
author = {Marini, S and Barquero, A and Wadhwani, AA and Bian, J and Ruiz, J and Boucher, C and Prosperi, M},
title = {OCTOPUS: Disk-based, Multiplatform, Mobile-friendly Metagenomics Classifier.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.03.15.585215},
pmid = {38559026},
abstract = {Portable genomic sequencers such as Oxford Nanopore's MinION enable real-time applications in both clinical and environmental health, e.g., detection of bacterial outbreaks. However, there is a bottleneck in the downstream analytics when bioinformatics pipelines are unavailable, e.g., when cloud processing is unreachable due to absence of Internet connection, or only low-end computing devices can be carried on site. For instance, metagenomics classifiers usually require a large amount of memory or specific operating systems/libraries. In this work, we present a platform-friendly software for portable metagenomic analysis of Nanopore data, the Oligomer-based Classifier of Taxonomic Operational and Pan-genome Units via Singletons (OCTOPUS). OCTOPUS is written in Java, reimplements several features of the popular Kraken2 and KrakenUniq software, with original components for improving metagenomics classification on incomplete/sampled reference databases (e.g., selection of bacteria of public health priority), making it ideal for running on smartphones or tablets. We indexed both OCTOPUS and Kraken2 on a bacterial database with ∼4,000 reference genomes, then simulated a positive (bacterial genomes from the same species, but different genomes) and two negative (viral, mammalian) Nanopore test sets. On the bacterial test set OCTOPUS yielded sensitivity and precision comparable to Kraken2 (94.4% and 99.8% versus 94.5% and 99.1%, respectively). On non-bacterial sequences (mammals and viral), OCTOPUS dramatically decreased (4-to 16-fold) the false positive rate when compared to Kraken2 (2.1% and 0.7% versus 8.2% and 11.2%, respectively). We also developed customized databases including viruses, and the World Health Organization's set of bacteria of concern for drug resistance, tested with real Nanopore data on an Android smartphone. OCTOPUS is publicly available at https://github.com/DataIntellSystLab/OCTOPUS and https://github.com/Ruiz-HCI-Lab/OctopusMobile .},
}

@article {pmid38558270,
year = {2024},
author = {Montecillo, JAV},
title = {Comparative genomics of the genus Halioglobus reveals the genetic basis for the reclassification of Halioglobus pacificus as Parahalioglobus pacificus gen. nov. comb. nov.},
journal = {International microbiology : the official journal of the Spanish Society for Microbiology},
volume = {},
number = {},
pages = {},
pmid = {38558270},
issn = {1618-1905},
abstract = {The genus Halioglobus is one of the environmentally relevant members of the family Halieaceae, class Gammaproteobacteria. At present, the genus is composed of three validly published species. However, in the recent study of the family Halieaceae, the species Halioglobus pacificus was observed to branch outside of the main clade formed by the members of Halioglobus, suggesting its distinct taxonomic placement within the family. In the present study, the taxonomic placement of H. pacificus was reassessed using comparative genomics. Phylogenomic analysis revealed the paraphyletic relationship of H. pacificus with the type species of the genus Halioglobus, and further demonstrated its genus-level placement. This phylogenetic relationship was reinforced by the average nucleotide and amino acid identity values shared by H. pacificus with the members of the family Halieaceae. Moreover, the results of the pan-genome analysis, together with the phenotype data, further supported the exclusion of H. pacificus from the genus Halioglobus. Based on these findings, the species H. pacificus is thereby assigned to a new genus Parahalioglobus gen. nov. as Parahalioglobus pacificus comb. nov.},
}

@article {pmid38555312,
year = {2024},
author = {Yang, Y and Wang, H and Tu, J and Li, Y and Guan, H},
title = {Comprehensive genomic analysis of Burkholderia arboris PN-1 reveals its biocontrol potential against Fusarium solani-induced root rot in Panax notoginseng.},
journal = {Current genetics},
volume = {70},
number = {1},
pages = {4},
pmid = {38555312},
issn = {1432-0983},
support = {YJSJJ22-A15//Postgraduate research Innovation Fund Project in Yunnan Normal University/ ; 202202AE090025//Major Science and Technology Special Project of Yunnan Province/ ; 202305AF150027//Yunnan Academician Expert Workstation/ ; YSZJGZZ-2021062//Yunnan (Kunming) Academician Expert Workstation/ ; },
abstract = {Panax notoginseng (Burkill) F.H. Chen, a valuable traditional Chinese medicine, faces significant yield and quality challenges stemming from root rot primarily caused by Fusarium solani. Burkholderia arboris PN-1, isolated from the rhizosphere soil of P. notoginseng, demonstrated a remarkable ability to inhibit the growth of F. solani. This study integrates phenotypic, phylogenetic, and genomic analyses to enhance our understanding of the biocontrol mechanisms employed by B. arboris PN-1. Phenotype analysis reveals that B. arboris PN-1 effectively suppresses P. notoginseng root rot both in vitro and in vivo. The genome of B. arboris PN-1 comprises three circular chromosomes (contig 1: 3,651,544 bp, contig 2: 1,355,460 bp, and contig 3: 3,471,056 bp), with a 66.81% GC content, housing 7,550 protein-coding genes. Notably, no plasmids were detected. Phylogenetic analysis places PN-1 in close relation to B. arboris AU14372, B. arboris LMG24066, and B. arboris MEC_B345. Average nucleotide identity (ANI) values confirm the PN-1 classification as B. arboris. Comparative analysis with seven other B. arboris strains identified 4,628 core genes in B. arboris PN-1. The pan-genome of B. arboris appears open but may approach closure. Whole-genome sequencing revealed 265 carbohydrate-active enzymes and identified 9 gene clusters encoding secondary metabolites. This comprehensive investigation enhances our understanding of B. arboris genomes, paving the way for their potential as effective biocontrol agents against fungal plant pathogens in the future.},
}

@article {pmid38550074,
year = {2024},
author = {International, BR},
title = {Retracted: Epi-Gene: An R-Package for Easy Pan-Genome Analysis.},
journal = {BioMed research international},
volume = {2024},
number = {},
pages = {9830450},
doi = {10.1155/2024/9830450},
pmid = {38550074},
issn = {2314-6141},
abstract = {[This retracts the article DOI: 10.1155/2021/5585586.].},
}

@article {pmid38543563,
year = {2024},
author = {Grizon, A and Theil, S and Helinck, S and Gerber, P and Bonnarme, P and Chassard, C},
title = {Genomic Characterization of Wild Lactobacillus delbrueckii Strains Reveals Low Diversity but Strong Typicity.},
journal = {Microorganisms},
volume = {12},
number = {3},
pages = {},
doi = {10.3390/microorganisms12030512},
pmid = {38543563},
issn = {2076-2607},
support = {convention CIFRE N° 2020/0839//Association Nationale de la Recherche et de la Technologie/ ; },
abstract = {Investigating the diversity of a given species could give clues for the development of autochthonous starter cultures. However, few studies have focused on the intraspecies diversity of Lactobacillus delbrueckii strains, a technologically important lactic acid bacterium for the dairy industry. For this reason, Lactobacillus delbrueckii strains from the Saint-Nectaire Protected Designation of Origin (PDO) area were isolated and characterized. Genetic diversity was determined based on core genome phylogenetic reconstruction and pangenome analysis, while phenotypic assessments encompassed proteolysis and volatile compound production potential. A total of 15 L. delbrueckii ssp. lactis unique new strains were obtained. The genetic analysis and further proteolytic activities measurement revealed low variability among these Saint-Nectaire strains, while substantial genetic variability was observed within the L. delbrueckii ssp. lactis subspecies as a whole. The volatile compound profiles slightly differed among strains, and some strains produced volatile compounds that could be of particular interest for cheese flavor development. While the genetic diversity among Saint-Nectaire strains was relatively modest compared to overall subspecies diversity, their distinct characteristics and pronounced differentiation from publicly available genomes position them as promising candidates for developing autochthonous starter cultures for cheese production.},
}

@article {pmid38541621,
year = {2024},
author = {Park, S and Kim, I and Chhetri, G and Jung, Y and Woo, H and Seo, T},
title = {Draft Genome Sequence Analyses of Two Novel Marinobacter suadae sp. nov. and Wenyingzhuangia gilva sp. nov. Isolated from the Root of Suaeda japonica Makino.},
journal = {Life (Basel, Switzerland)},
volume = {14},
number = {3},
pages = {},
doi = {10.3390/life14030296},
pmid = {38541621},
issn = {2075-1729},
support = {2022R1F1A1070108//National Research Foundation of Korea/ ; NIBR202304204//National Institute of Biological Resources/ ; },
abstract = {Gram-negative, rod-shaped, and aerobic bacteria designated chi1[T] and chi5[T] were isolated from the root of Suaeda japonica Makino. Phylogenetics utilizing 16S rRNA and whole-genome sequences of the two novel strains chi1[T] and chi5[T] confirmed that they were related to the genera Marinobacter and Wenyingzhuangia, respectively. For the novel strains chi1[T] and chi5[T], the digital DNA-DNA hybridization values (19-20% and 22.1-36.6%, respectively) and average nucleotide identity values (74.4-76.5% and 79.1-88.9%, respectively) fell within the range for the genera Marinobacter and Wenyingzhuangia, respectively. Pangenome analyses of the novel strains chi1[T] and chi5[T] revealed 357 and 368 singletons genes, respectively. The genomic DNA G + C contents of the strains chi1[T] and chi5[T] were 57.2% and 31.5%, respectively. The major fatty acids of strain chi1[T] were C12:0, C16:0, and summed feature 3 (C16:1ω6c and/or C16:1ω7c), while those of the strain chi5[T] were iso-C15:0 3OH, iso-C17:0 3OH, and iso-C15:0. Data from the phylogenetic, phylogenomic, pangenome, genomic, physiological, and biochemical analyses indicated that the novel strains were distinct. Therefore, we propose the names Marinobacter suadae (type strain chi1[T] = KACC 23259[T] = TBRC 17652[T]) and Wenyingzhangia gilva (type strain chi5[T] = KACC 23262[T] = TBRC 17900[T]) for the studied bacterial strains.},
}

@article {pmid38537199,
year = {2024},
author = {Meng, T and Jiao, H and Zhang, Y and Zhou, Y and Chen, S and Wang, X and Yang, B and Sun, J and Geng, X and Ayhan, DH and Guo, L},
title = {FoPGDB: a pangenome database of Fusarium oxysporum, a cross-kingdom fungal pathogen.},
journal = {Database : the journal of biological databases and curation},
volume = {2024},
number = {},
pages = {},
doi = {10.1093/database/baae017},
pmid = {38537199},
issn = {1758-0463},
support = {//National Natural Science Foundation of China/ ; //Taishan Scholars Program of Shandong Province/ ; //Shandong Provincial Science and Technology Innovation Fund/ ; //National Natural Science Foundation of China/ ; //Taishan Scholars Program of Shandong Province/ ; //Shandong Provincial Science and Technology Innovation Fund/ ; },
abstract = {Pangenomes, capturing the genetic diversity of a species or genus, are essential to understanding the ecology, pathobiology and evolutionary mechanisms of fungi that cause infection in crops and humans. However, fungal pangenome databases remain unavailable. Here, we report the first fungal pangenome database, specifically for Fusarium oxysporum species complex (FOSC), a group of cross-kingdom pathogens causing devastating vascular wilt to over 100 plant species and life-threatening fusariosis to immunocompromised humans. The F. oxysporum Pangenome Database (FoPGDB) is a comprehensive resource integrating 35 high-quality FOSC genomes, coupled with robust analytical tools. FoPGDB allows for both gene-based and graph-based exploration of the F. oxysporum pangenome. It also curates a large repository of putative effector sequences, crucial for understanding the mechanisms of FOSC pathogenicity. With an assortment of functionalities including gene search, genomic variant exploration and tools for functional enrichment, FoPGDB provides a platform for in-depth investigations of the genetic diversity and adaptability of F. oxysporum. The modular and user-friendly interface ensures efficient data access and interpretation. FoPGDB promises to be a valuable resource for F. oxysporum research, contributing to our understanding of this pathogen's pangenomic landscape and aiding in the development of novel disease management strategies. Database URL: http://www.fopgdb.site.},
}

@article {pmid38534692,
year = {2024},
author = {Karampatakis, T and Tsergouli, K and Behzadi, P},
title = {Pan-Genome Plasticity and Virulence Factors: A Natural Treasure Trove for Acinetobacter baumannii.},
journal = {Antibiotics (Basel, Switzerland)},
volume = {13},
number = {3},
pages = {},
doi = {10.3390/antibiotics13030257},
pmid = {38534692},
issn = {2079-6382},
abstract = {Acinetobacter baumannii is a Gram-negative pathogen responsible for a variety of community- and hospital-acquired infections. It is recognized as a life-threatening pathogen among hospitalized individuals and, in particular, immunocompromised patients in many countries. A. baumannii, as a member of the ESKAPE group, encompasses high genomic plasticity and simultaneously is predisposed to receive and exchange the mobile genetic elements (MGEs) through horizontal genetic transfer (HGT). Indeed, A. baumannii is a treasure trove that contains a high number of virulence factors. In accordance with these unique pathogenic characteristics of A. baumannii, the authors aim to discuss the natural treasure trove of pan-genome and virulence factors pertaining to this bacterial monster and try to highlight the reasons why this bacterium is a great concern in the global public health system.},
}

@article {pmid38532808,
year = {2024},
author = {Bundhoo, E and Ghoorah, AW and Jaufeerally-Fakim, Y},
title = {Large-scale Pan Genomic Analysis of Mycobacterium tuberculosis Reveals Key Insights Into Molecular Evolutionary Rate of Specific Processes and Functions.},
journal = {Evolutionary bioinformatics online},
volume = {20},
number = {},
pages = {11769343241239463},
pmid = {38532808},
issn = {1176-9343},
abstract = {Mycobacterium tuberculosis (Mtb) is the causative agent of tuberculosis (TB), an infectious disease that is a major killer worldwide. Due to selection pressure caused by the use of antibacterial drugs, Mtb is characterised by mutational events that have given rise to multi drug resistant (MDR) and extensively drug resistant (XDR) phenotypes. The rate at which mutations occur is an important factor in the study of molecular evolution, and it helps understand gene evolution. Within the same species, different protein-coding genes evolve at different rates. To estimate the rates of molecular evolution of protein-coding genes, a commonly used parameter is the ratio dN/dS, where dN is the rate of non-synonymous substitutions and dS is the rate of synonymous substitutions. Here, we determined the estimated rates of molecular evolution of select biological processes and molecular functions across 264 strains of Mtb. We also investigated the molecular evolutionary rates of core genes of Mtb by computing the dN/dS values, and estimated the pan genome of the 264 strains of Mtb. Our results show that the cellular amino acid metabolic process and the kinase activity function evolve at a significantly higher rate, while the carbohydrate metabolic process evolves at a significantly lower rate for M. tuberculosis. These high rates of evolution correlate well with Mtb physiology and pathogenicity. We further propose that the core genome of M. tuberculosis likely experiences varying rates of molecular evolution which may drive an interplay between core genome and accessory genome during M. tuberculosis evolution.},
}

@article {pmid38529905,
year = {2024},
author = {Crowley, C and Selvaraj, A and Hariharan, A and Healy, CM and Moran, GP},
title = {Fusobacterium nucleatum subsp. polymorphum recovered from malignant and potentially malignant oral disease exhibit heterogeneity in adhesion phenotypes and adhesin gene copy number, shaped by inter-subspecies horizontal gene transfer and recombination-derived mosaicism.},
journal = {Microbial genomics},
volume = {10},
number = {3},
pages = {},
doi = {10.1099/mgen.0.001217},
pmid = {38529905},
issn = {2057-5858},
abstract = {Fusobacterium nucleatum is an anaerobic commensal of the oral cavity associated with periodontitis and extra-oral diseases, including colorectal cancer. Previous studies have shown an increased relative abundance of this bacterium associated with oral dysplasia or within oral tumours. Using direct culture, we found that 75 % of Fusobacterium species isolated from malignant or potentially malignant oral mucosa were F. nucleatum subsp. polymorphum. Whole genome sequencing and pangenome analysis with Panaroo was carried out on 76 F. nucleatum subsp. polymorphum genomes. F. nucleatum subsp. polymorphum was shown to possesses a relatively small core genome of 1604 genes in a pangenome of 7363 genes. Phylogenetic analysis based on the core genome shows the isolates can be separated into three main clades with no obvious genotypic associations with disease. Isolates recovered from healthy and diseased sites in the same patient are generally highly related. A large repertoire of adhesins belonging to the type V secretion system (TVSS) could be identified with major variation in repertoire and copy number between strains. Analysis of intergenic recombination using fastGEAR showed that adhesin complement is shaped by horizontal gene transfer and recombination. Recombination events at TVSS adhesin genes were not only common between lineages of subspecies polymorphum, but also between different subspecies of F. nucleatum. Strains of subspecies polymorphum with low copy numbers of TVSS adhesin encoding genes tended to have the weakest adhesion to oral keratinocytes. This study highlights the genetic heterogeneity of F. nucleatum subsp. polymorphum and provides a new framework for defining virulence in this organism.},
}

@article {pmid38529502,
year = {2024},
author = {Zhou, Q and Ghezelji, M and Hari, A and Ford, MKB and Holley, C and , and Mirabello, L and Chanock, S and Sahinalp, SC and Numanagić, I},
title = {Geny: A Genotyping Tool for Allelic Decomposition of Killer Cell Immunoglobulin-Like Receptor Genes.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.02.27.582413},
pmid = {38529502},
abstract = {Accurate genotyping of Killer cell Immunoglobulin-like Receptor (KIR) genes plays a pivotal role in enhancing our understanding of innate immune responses, disease correlations, and the advancement of personalized medicine. However, due to the high variability of the KIR region and high level of sequence similarity among different KIR genes, the currently available genotyping methods are unable to accurately infer copy numbers, genotypes and haplotypes of individual KIR genes from next-generation sequencing data. Here we introduce Geny, a new computational tool for precise genotyping of KIR genes. Geny utilizes available KIR haplotype databases and proposes a novel combination of expectation-maximization filtering schemes and integer linear programming-based combinatorial optimization models to resolve ambiguous reads, provide accurate copy number estimation and estimate the haplotype of each copy for the genes within the KIR region. We evaluated Geny on a large set of simulated short-read datasets covering the known validated KIR region assemblies and a set of Illumina short-read samples sequenced from 25 validated samples from the Human Pangenome Reference Consortium collection and showed that it outperforms the existing genotyping tools in terms of accuracy, precision and recall. We envision Geny becoming a valuable resource for understanding immune system response and consequently advancing the field of patient-centric medicine.},
}

@article {pmid38524570,
year = {2024},
author = {Nwabor, LC and Chukamnerd, A and Nwabor, OF and Surachat, K and Pomwised, R and Jeenkeawpiam, K and Chusri, S},
title = {Genotypic and phenotypic mechanisms underlying antimicrobial resistance and synergistic efficacy of rifampicin-based combinations against carbapenem-resistant Acinetobacter baumannii.},
journal = {Heliyon},
volume = {10},
number = {6},
pages = {e27326},
pmid = {38524570},
issn = {2405-8440},
abstract = {PURPOSE: Carbapenem-resistant Acinetobacter baumannii (CRAB) is an urgent concern to public health. This study focuses on exploring the resistance mechanisms and the in vitro results of using rifampicin in combination with conventional antibiotics for the management of CRAB.

METHODS: The synergistic and bactericidal effects of rifampicin with conventional antibiotics were evaluated using chequerboard assay and time-kill assay, while the phenotypic and genotypic characteristics of resistant determinants were performed by efflux pump detection and whole genome sequencing on 29 isolates from ICU patients with underlying health diseases.

RESULTS: The isolates showed multidrug resistance, with over 60% showing addictive responses to rifampicin-based combinations at FICI ranging from 0.6 to 0.8. The time-kill assay revealed 99 % killing for rifampicin and minocycline combination in one isolate at 1/4 MIC rifampicin plus 1/4 MIC minocycline, while a bacteriostatic effect was observed at 1/2 MIC rifampici plus 1/2 MIC for a second isolate. Combination with tigecycline resulted in a 99% killing in two out of three isolates with a 2.5-3 log reduction in CFU at 1/4 MIC rifampicin plus 1/4 MIC tigecycline. Rifampicin plus colistin exhibited bactericidal activity against three out of four isolates. The combinations of rifampicin with ciprofloxacin, chloramphenicol, and trimethoprim-sulfamethoxazole were ineffective against the isolates. In addition, a 4-fold reduction in rifampicin MIC was observed in 2 out of 14 isolates in the presence of an efflux pump inhibitor. The pan-genome study demonstrated a progressive evolution with an accessory genome estimated to cover 58% of the matrix. Seven of the ten sequenced isolates belong to sequence type 2 (ST2), while one isolate each was assigned to ST164, ST16, and ST25. Furthermore, 11 plasmids, 34 antimicrobial resistance (AMR) genes, and 65 virulence-associated genes were predicted from the whole genome data. The blaOXA-23blaADC-25, blaOXA-66, blaPER-7, aph(6)-Id, armA, and arr-3 were prevalent among the isolates. Sequence alignment of the bacteria genome to the reference strain revealed a deleterious mutation in the rpoB gene of 4 isolates.

CONCLUSION: The study suggests that rifampicin in combination with either minocycline, tigecycline, or colistin might be a treatment option for CRAB clinical isolates. In addition, genotypic analysis of the bacteria isolates may inform the clinician of the suitable drug regimen for the management of specific bacteria variants.},
}

@article {pmid38521963,
year = {2024},
author = {Sengupta, P and Muthamilselvi Sivabalan, SK and Singh, NK and Raman, K and Venkateswaran, K},
title = {Genomic, functional, and metabolic enhancements in multidrug-resistant Enterobacter bugandensis facilitating its persistence and succession in the International Space Station.},
journal = {Microbiome},
volume = {12},
number = {1},
pages = {62},
pmid = {38521963},
issn = {2049-2618},
support = {19-12829-26//2012 Space Biology NNH12ZTT001N/ ; 19-12829-26//2012 Space Biology NNH12ZTT001N/ ; MTR/2020/000490//Science and Engineering Board (SERB) MATRICS/ ; },
abstract = {BACKGROUND: The International Space Station (ISS) stands as a testament to human achievement in space exploration. Despite its highly controlled environment, characterised by microgravity, increased CO 2 levels, and elevated solar radiation, microorganisms occupy a unique niche. These microbial inhabitants play a significant role in influencing the health and well-being of astronauts on board. One microorganism of particular interest in our study is Enterobacter bugandensis, primarily found in clinical specimens including the human gastrointestinal tract, and also reported to possess pathogenic traits, leading to a plethora of infections.

RESULTS: Distinct from their Earth counterparts, ISS E. bugandensis strains have exhibited resistance mechanisms that categorise them within the ESKAPE pathogen group, a collection of pathogens recognised for their formidable resistance to antimicrobial treatments. During the 2-year Microbial Tracking 1 mission, 13 strains of multidrug-resistant E. bugandensis were isolated from various locations within the ISS. We have carried out a comprehensive study to understand the genomic intricacies of ISS-derived E. bugandensis in comparison to terrestrial strains, with a keen focus on those associated with clinical infections. We unravel the evolutionary trajectories of pivotal genes, especially those contributing to functional adaptations and potential antimicrobial resistance. A hypothesis central to our study was that the singular nature of the stresses of the space environment, distinct from any on Earth, could be driving these genomic adaptations. Extending our investigation, we meticulously mapped the prevalence and distribution of E. bugandensis across the ISS over time. This temporal analysis provided insights into the persistence, succession, and potential patterns of colonisation of E. bugandensis in space. Furthermore, by leveraging advanced analytical techniques, including metabolic modelling, we delved into the coexisting microbial communities alongside E. bugandensis in the ISS across multiple missions and spatial locations. This exploration revealed intricate microbial interactions, offering a window into the microbial ecosystem dynamics within the ISS.

CONCLUSIONS: Our comprehensive analysis illuminated not only the ways these interactions sculpt microbial diversity but also the factors that might contribute to the potential dominance and succession of E. bugandensis within the ISS environment. The implications of these findings are twofold. Firstly, they shed light on microbial behaviour, adaptation, and evolution in extreme, isolated environments. Secondly, they underscore the need for robust preventive measures, ensuring the health and safety of astronauts by mitigating risks associated with potential pathogenic threats. Video Abstract.},
}

@article {pmid38517169,
year = {2024},
author = {Paulay, A and Grimaud, GM and Caballero, R and Laroche, B and Leclerc, M and Labarthe, S and Maguin, E},
title = {Design of a proteolytic module for improved metabolic modeling of Bacteroides caccae.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0015324},
doi = {10.1128/msystems.00153-24},
pmid = {38517169},
issn = {2379-5077},
abstract = {The gut microbiota plays a crucial role in health and is significantly modulated by human diets. In addition to Western diets which are rich in proteins, high-protein diets are used for specific populations or indications, mainly weight loss. In this study, we investigated the effect of protein supplementation on Bacteroides caccae, a Gram-negative gut symbiont. The supplementation with whey proteins led to a significant increase in growth rate, final biomass, and short-chain fatty acids production. A comprehensive genomic analysis revealed that B. caccae possesses a set of 156 proteases with putative intracellular and extracellular localization and allowed to identify amino acid transporters and metabolic pathways. We developed a fully curated genome-scale metabolic model of B. caccae that incorporated its proteolytic activity and simulated its growth and production of fermentation-related metabolites in response to the different growth media. We validated the model by comparing the predicted phenotype to experimental data. The model accurately predicted B. caccae's growth and metabolite production (R[2] = 0.92 for the training set and R[2] = 0.89 for the validation set). We found that accounting for both ATP consumption related to proteolysis, and whey protein accessibility is necessary for accurate predictions of metabolites production. These results provide insights into B. caccae's adaptation to a high-protein diet and its ability to utilize proteins as a source of nutrition. The proposed model provides a useful tool for understanding the feeding mechanism of B. caccae in the gut microbiome.IMPORTANCEMicrobial proteolysis is understudied despite the availability of dietary proteins for the gut microbiota. Here, the proteolytic potential of the gut symbiont Bacteroides caccae was analyzed for the first time using pan-genomics. This sketches a well-equipped bacteria for protein breakdown, capable of producing 156 different proteases with a broad spectrum of cleavage targets. This functional potential was confirmed by the enhancement of growth and metabolic activities at high protein levels. Proteolysis was included in a B. caccae metabolic model which was fitted with the experiments and validated on external data. This model pinpoints the links between protein availability and short-chain fatty acids production, and the importance for B. caccae to gain access to glutamate and asparagine to promote growth. This integrated approach can be generalized to other symbionts and upscaled to complex microbiota to get insights into the ecological impact of proteins on the gut microbiota.},
}

@article {pmid38514651,
year = {2024},
author = {Xie, S and Cui, L and Liao, Z and Zhu, J and Ren, S and Niu, K and Li, H and Jiang, F and Wu, J and Wang, J and Wu, J and Song, B and Wu, W and Peng, C},
title = {Genomic analysis of lumpy skin disease virus asian variants and evaluation of its cellular tropism.},
journal = {NPJ vaccines},
volume = {9},
number = {1},
pages = {65},
pmid = {38514651},
issn = {2059-0105},
support = {32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32172822//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
abstract = {Lumpy skin disease virus (LSDV) is a poxvirus that mainly affects cattle and can lead to symptoms such as severe reduction in milk production as well as infertility and mortality, which has resulted in dramatic economic loss in affected countries in Africa, Europe, and Asia. In this study, we successfully isolated two strains of LSDV from different geographical regions in China. Comparative genomic analyses were performed by incorporating additional LSDV whole genome sequences reported in other areas of Asia. Our analyses revealed that LSDV exhibited an 'open' pan-genome. Phylogenetic analysis unveiled distinct branches of LSDV evolution, signifying the prevalence of multiple lineages of LSDV across various regions in Asia. In addition, a reporter LSDV expressing eGFP directed by a synthetic poxvirus promoter was generated and used to evaluate the cell tropism of LSDV in various mammalian and avian cell lines. Our results demonstrated that LSDV replicated efficiently in several mammalian cell lines, including human A549 cells. In conclusion, our results underscore the necessity for strengthening LSD outbreak control measures and continuous epidemiological surveillance.},
}

@article {pmid38509359,
year = {2024},
author = {Zepeda-Rivera, M and Minot, SS and Bouzek, H and Wu, H and Blanco-Míguez, A and Manghi, P and Jones, DS and LaCourse, KD and Wu, Y and McMahon, EF and Park, SN and Lim, YK and Kempchinsky, AG and Willis, AD and Cotton, SL and Yost, SC and Sicinska, E and Kook, JK and Dewhirst, FE and Segata, N and Bullman, S and Johnston, CD},
title = {A distinct Fusobacterium nucleatum clade dominates the colorectal cancer niche.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {38509359},
issn = {1476-4687},
abstract = {Fusobacterium nucleatum (Fn), a bacterium present in the human oral cavity and rarely found in the lower gastrointestinal tract of healthy individuals[1], is enriched in human colorectal cancer (CRC) tumours[2-5]. High intratumoural Fn loads are associated with recurrence, metastases and poorer patient prognosis[5-8]. Here, to delineate Fn genetic factors facilitating tumour colonization, we generated closed genomes for 135 Fn strains; 80 oral strains from individuals without cancer and 55 unique cancer strains cultured from tumours from 51 patients with CRC. Pangenomic analyses identified 483 CRC-enriched genetic factors. Tumour-isolated strains predominantly belong to Fn subspecies animalis (Fna). However, genomic analyses reveal that Fna, considered a single subspecies, is instead composed of two distinct clades (Fna C1 and Fna C2). Of these, only Fna C2 dominates the CRC tumour niche. Inter-Fna analyses identified 195 Fna C2-associated genetic factors consistent with increased metabolic potential and colonization of the gastrointestinal tract. In support of this, Fna C2-treated mice had an increased number of intestinal adenomas and altered metabolites. Microbiome analysis of human tumour tissue from 116 patients with CRC demonstrated Fna C2 enrichment. Comparison of 62 paired specimens showed that only Fna C2 is tumour enriched compared to normal adjacent tissue. This was further supported by metagenomic analysis of stool samples from 627 patients with CRC and 619 healthy individuals. Collectively, our results identify the Fna clade bifurcation, show that specifically Fna C2 drives the reported Fn enrichment in human CRC and reveal the genetic underpinnings of pathoadaptation of Fna C2 to the CRC niche.},
}

@article {pmid38509222,
year = {2024},
author = {Xie, L and Gong, X and Yang, K and Huang, Y and Zhang, S and Shen, L and Sun, Y and Wu, D and Ye, C and Zhu, QH and Fan, L},
title = {Technology-enabled great leap in deciphering plant genomes.},
journal = {Nature plants},
volume = {},
number = {},
pages = {},
pmid = {38509222},
issn = {2055-0278},
support = {2022C02032//Hainan Provincial Department of Science and Technology (Department of Science and Technology of Hainan Province)/ ; },
abstract = {Plant genomes provide essential and vital basic resources for studying many aspects of plant biology and applications (for example, breeding). From 2000 to 2020, 1,144 genomes of 782 plant species were sequenced. In the past three years (2021-2023), 2,373 genomes of 1,031 plant species, including 793 newly sequenced species, have been assembled, representing a great leap. The 2,373 newly assembled genomes, of which 63 are telomere-to-telomere assemblies and 921 have been generated in pan-genome projects, cover the major phylogenetic clades. Substantial advances in read length, throughput, accuracy and cost-effectiveness have notably simplified the achievement of high-quality assemblies. Moreover, the development of multiple software tools using different algorithms offers the opportunity to generate more complete and complex assemblies. A database named N3: plants, genomes, technologies has been developed to accommodate the metadata associated with the 3,517 genomes that have been sequenced from 1,575 plant species since 2000. We also provide an outlook for emerging opportunities in plant genome sequencing.},
}

@article {pmid38503725,
year = {2024},
author = {Zhao, X and Yu, J and Chanda, B and Zhao, J and Wu, S and Zheng, Y and Sun, H and Levi, A and Ling, KS and Fei, Z},
title = {Genomic and pangenomic analyses provide insights into the population history and genomic diversification of bottle gourd.},
journal = {The New phytologist},
volume = {},
number = {},
pages = {},
doi = {10.1111/nph.19673},
pmid = {38503725},
issn = {1469-8137},
support = {2015-51181-24285//National Institute of Food and Agriculture/ ; 2020-51181-32139//National Institute of Food and Agriculture/ ; },
abstract = {Bottle gourd (Lagenaria siceraria (Mol.) Strandl.) is an economically important vegetable crop and one of the earliest domesticated crops. However, the population history and genomic diversification of bottle gourd have not been extensively studied. We generated a comprehensive bottle gourd genome variation map from genome sequences of 197 world-wide representative accessions, which enables a genome-wide association study for identifying genomic loci associated with resistance to zucchini yellow mosaic virus, and constructed a bottle gourd pangenome that harbors 1534 protein-coding genes absent in the reference genome. Demographic analyses uncover that domesticated bottle gourd originated in Southern Africa c. 12 000 yr ago, and subsequently radiated to the New World via the Atlantic drift and to Eurasia through the efforts of early farmers in the initial Holocene. The identified highly differentiated genomic regions among different bottle gourd populations harbor many genes contributing to their local adaptations such as those related to disease resistance and stress tolerance. Presence/absence variation analysis of genes in the pangenome reveals numerous genes including those involved in abiotic/biotic stress responses that have been under selection during the world-wide expansion of bottle gourds. The bottle gourd variation map and pangenome provide valuable resources for future functional studies and genomics-assisted breeding.},
}

@article {pmid38502137,
year = {2024},
author = {Guo, X and Zhang, Z and Chen, Q and Wang, L and Xu, X and Wei, Z and Zhang, Y and Chen, K and Wang, Z and Lu, X and Liang, Q},
title = {Whole Genome Sequencing Highlights the Pathogenic Profile in Nocardia Keratitis.},
journal = {Investigative ophthalmology & visual science},
volume = {65},
number = {3},
pages = {26},
doi = {10.1167/iovs.65.3.26},
pmid = {38502137},
issn = {1552-5783},
abstract = {PURPOSE: Nocardia keratitis is a serious and sight-threatening condition. This study aims to reveal the virulence and antimicrobial resistance gene profile of Nocardia strains using whole genome sequencing.

METHODS: Whole-genome sequencing was performed on 23 cornea-derived Nocardia strains. Together with genomic data from the respiratory tract and the environment, 141 genomes were then utilized for phylogenetic and pan-genome analyses, followed by virulence and antibiotic resistance analysis. The correlations between virulence genes and pathogenicity were experimentally validated, including the characteristics of Nocardia colonies and clinical and histopathological evaluations of Nocardia keratitis mice models.

RESULTS: Whole-genome sequencing of 141 Nocardia strains revealed a mean of 220 virulence genes contributed to bacterial pathogenesis. The mce gene family analysis led to the categorization of strains from the cornea into groups A, B, and C. The colonies of group C had the largest diameter, height, and fastest growth rate. The size of corneal ulcers and the clinical scores showed a significant increase in mouse models induced by group C. The relative expression levels of pro-inflammatory cytokines (CD4, IFN-γ, IL-6Rα, and TNF-α) in the lesion area exhibited an increasing trend from group A to group C. Antibiotic resistance genes (ARGs) spanned nine distinct drug classes, four resistance mechanisms, and seven primary antimicrobial resistance gene families.

CONCLUSIONS: Whole genome sequencing highlights the pathogenic role of mce gene family in Nocardia keratitis. Its distribution pattern may contribute to the distinct characteristics of the growth of Nocardia colonies and the clinical severity of the mice models.},
}

@article {pmid38501935,
year = {2024},
author = {Piper, KR and Ikhimiukor, OO and Souza, SSR and Garcia-Aroca, T and Andam, CP},
title = {Evolutionary dynamics of the accessory genomes of Staphylococcus aureus.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0075123},
doi = {10.1128/msphere.00751-23},
pmid = {38501935},
issn = {2379-5042},
abstract = {Staphylococcus aureus is a ubiquitous commensal and opportunistic bacterial pathogen that can cause a wide gamut of infections, which are exacerbated by the presence of multidrug-resistant and methicillin-resistant S. aureus. S. aureus is genetically heterogeneous and consists of numerous distinct lineages. Using 558 complete genomes of S. aureus, we aim to determine how the accessory genome content among phylogenetic lineages of S. aureus is structured and has evolved. Bayesian hierarchical clustering identified 10 sequence clusters, of which seven contained major sequence types (ST 1, 5, 8, 30, 59, 239, and 398). The seven sequence clusters differed in their accessory gene content, including genes associated with antimicrobial resistance and virulence. Focusing on the two largest clusters, BAPS8 and BAPS10, and each consisting mostly of ST5 and ST8, respectively, we found that the structure and connected components in the co-occurrence networks of accessory genomes varied between them. These differences are explained, in part, by the variation in the rates at which the two sequence clusters gained and lost accessory genes, with the highest rate of gene accumulation occurring recently in their evolutionary histories. We also identified a divergent group within BAPS10 that has experienced high gene gain and loss early in its history. Together, our results show highly variable and dynamic accessory genomes in S. aureus that are structured by the history of the specific lineages that carry them.IMPORTANCEStaphylococcus aureus is an opportunistic, multi-host pathogen that can cause a variety of benign and life-threatening infections. Our results revealed considerable differences in the structure and evolution of the accessory genomes of major lineages within S. aureus. Such genomic variation within a species can have important implications on disease epidemiology, pathogenesis of infection, and interactions with the vertebrate host. Our findings provide important insights into the underlying genetic basis for the success of S. aureus as a highly adaptable and resistant pathogen, which will inform current efforts to control and treat staphylococcal diseases.},
}

@article {pmid38500021,
year = {2024},
author = {Zouagui, R and Zouagui, H and Aurag, J and Ibrahimi, A and Sbabou, L},
title = {Functional analysis and comparative genomics of Rahnella perminowiae S11P1 and Variovorax sp. S12S4, two plant growth-promoting rhizobacteria isolated from Crocus sativus L. (saffron) rhizosphere.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {289},
pmid = {38500021},
issn = {1471-2164},
abstract = {BACKGROUND: Rahnella perminowiae S11P1 and Variovorax sp. S12S4 are two plant growth-promoting rhizobacteria that were previously isolated from the rhizosphere of Crocus sativus L. (saffron), and have demonstrated interesting PGP activities and promising results when used as inoculants in field trials. To further elucidate the molecular mechanisms underlying their beneficial effects on plant growth, comprehensive genome mining of S11P1 and S12S4 and comparative genomic analysis with closely related strains were conducted.

RESULTS: Functional annotation of the two strains predicted a large number of genes involved in auxin and siderophore production, nitrogen fixation, sulfur metabolism, organic acid biosynthesis, pyrroloquinoline quinone production, 1-aminocyclopropane-1-carboxylate (ACC) deaminase activity, volatile organic compounds production, and polyamine biosynthesis. In addition, numerous genes implicated in plant-bacteria interactions, such as those involved in chemotaxis and quorum sensing, were predicted. Moreover, the two strains carried genes involved in bacterial fitness under abiotic stress conditions. Comparative genomic analysis revealed an open pan-genomic structure for the two strains. COG annotation showed that higher fractions of core and accessory genes were involved in the metabolism and transport of carbohydrates and amino acids, suggesting the metabolic versatility of the two strains as effective rhizosphere colonizers. Furthermore, this study reports the first comparison of Multilocus sequence analysis (MLSA) and core-based phylogenies of the Rahnella and Variovorax genera.

CONCLUSIONS: The present study unveils the molecular mechanisms underlying plant growth promotion and biocontrol activity of S11P1 and S12S4, and provides a basis for their further biotechnological application in agriculture.},
}

@article {pmid38496489,
year = {2024},
author = {Rinker, DC and Sauters, TJC and Steffen, K and Gumilang, A and Raja, HA and Rangel-Grimaldo, M and Pinzan, CF and de Castro, PA and Dos Reis, TF and Delbaje, E and Houbraken, J and Goldman, GH and Oberlies, NH and Rokas, A},
title = {Strain heterogeneity in a non-pathogenic fungus highlights factors contributing to virulence.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.03.08.583994},
pmid = {38496489},
abstract = {Fungal pathogens exhibit extensive strain heterogeneity, including variation in virulence. Whether closely related non-pathogenic species also exhibit strain heterogeneity remains unknown. Here, we comprehensively characterized the pathogenic potentials (i.e., the ability to cause morbidity and mortality) of 16 diverse strains of Aspergillus fischeri , a non-pathogenic close relative of the major pathogen Aspergillus fumigatus . In vitro immune response assays and in vivo virulence assays using a mouse model of pulmonary aspergillosis showed that A. fischeri strains varied widely in their pathogenic potential. Furthermore, pangenome analyses suggest that A. fischeri genomic and phenotypic diversity is even greater. Genomic, transcriptomic, and metabolomic profiling identified several pathways and secondary metabolites associated with variation in virulence. Notably, strain virulence was associated with the simultaneous presence of the secondary metabolites hexadehydroastechrome and gliotoxin. We submit that examining the pathogenic potentials of non-pathogenic close relatives is key for understanding the origins of fungal pathogenicity.},
}

@article {pmid38495945,
year = {2024},
author = {Lecomte, L and Árnyasi, M and Ferchaud, AL and Kent, M and Lien, S and Stenløkk, K and Sylvestre, F and Bernatchez, L and Mérot, C},
title = {Investigating structural variant, indel and single nucleotide polymorphism differentiation between locally adapted Atlantic salmon populations.},
journal = {Evolutionary applications},
volume = {17},
number = {3},
pages = {e13653},
pmid = {38495945},
issn = {1752-4571},
abstract = {Genomic structural variants (SVs) are now recognized as an integral component of intraspecific polymorphism and are known to contribute to evolutionary processes in various organisms. However, they are inherently difficult to detect and genotype from readily available short-read sequencing data, and therefore remain poorly documented in wild populations. Salmonid species displaying strong interpopulation variability in both life history traits and habitat characteristics, such as Atlantic salmon (Salmo salar), offer a prime context for studying adaptive polymorphism, but the contribution of SVs to fine-scale local adaptation has yet to be explored. Here, we performed a comparative analysis of SVs, single nucleotide polymorphisms (SNPs) and small indels (<50 bp) segregating in the Romaine and Puyjalon salmon, two putatively locally adapted populations inhabiting neighboring rivers (Québec, Canada) and showing pronounced variation in life history traits, namely growth, fecundity, and age at maturity and smoltification. We first catalogued polymorphism using a hybrid SV characterization approach pairing both short- (16X) and long-read sequencing (20X) for variant discovery with graph-based genotyping of SVs across 60 salmon genomes, along with characterization of SNPs and small indels from short reads. We thus identified 115,907 SVs, 8,777,832 SNPs and 1,089,321 short indels, with SVs covering 4.8 times more base pairs than SNPs. All three variant types revealed a highly congruent population structure and similar patterns of F ST and density variation along the genome. Finally, we performed outlier detection and redundancy analysis (RDA) to identify variants of interest in the putative local adaptation of Romaine and Puyjalon salmon. Genes located near these variants were enriched for biological processes related to nervous system function, suggesting that observed variation in traits such as age at smoltification could arise from differences in neural development. This study therefore demonstrates the feasibility of large-scale SV characterization and highlights its relevance for salmonid population genomics.},
}

@article {pmid38492232,
year = {2024},
author = {Poretsky, E and Cagirici, HB and Andorf, CM and Sen, TZ},
title = {Harnessing the predicted maize pan-interactome for putative gene function prediction and prioritization of candidate genes for important traits.},
journal = {G3 (Bethesda, Md.)},
volume = {},
number = {},
pages = {},
doi = {10.1093/g3journal/jkae059},
pmid = {38492232},
issn = {2160-1836},
abstract = {The recent assembly and annotation of the 26 maize nested association mapping (NAM) population founder inbreds have enabled large-scale pan-genomic comparative studies. These studies have expanded our understanding of agronomically important traits by integrating pan-transcriptomic data with trait-specific gene candidates from previous association mapping results. In contrast to the availability of pan-transcriptomic data, obtaining reliable protein-protein interaction (PPI) data has remained a challenge due to its high cost and complexity. We generated predicted PPI networks for each of the 26 genomes using the established STRING database. The individual genome-interactomes were then integrated to generate core- and pan-interactomes. We deployed the PPI clustering algorithm ClusterONE to identify numerous PPI clusters that were functionally annotated using gene ontology (GO) functional enrichment, demonstrating a diverse range of enriched GO terms across different clusters. Additional cluster annotations were generated by integrating gene co-expression data and gene description annotations, providing additional useful information. We show that the functionally annotated PPI clusters establish a useful framework for protein function prediction and prioritization of candidate genes of interest. Our study not only provides a comprehensive resource of predicted PPI networks for 26 maize genomes, but also offers annotated interactome clusters for predicting protein functions and prioritizing gene candidates. The source code for the Python implementation of the analysis workflow and a standalone web application for accessing the analysis results are available at https://github.com/eporetsky/PanPPI.},
}

@article {pmid38491145,
year = {2024},
author = {Wang, Y and Tang, H and Wang, X and Sun, Y and Joseph, PV and Paterson, AH},
title = {Detection of colinear blocks and synteny and evolutionary analyses based on utilization of MCScanX.},
journal = {Nature protocols},
volume = {},
number = {},
pages = {},
pmid = {38491145},
issn = {1750-2799},
abstract = {As different taxa evolve, gene order often changes slowly enough that chromosomal 'blocks' with conserved gene orders (synteny) are discernible. The MCScanX toolkit (https://github.com/wyp1125/MCScanX) was published in 2012 as freely available software for the detection of such 'colinear blocks' and subsequent synteny and evolutionary analyses based on genome-wide gene location and protein sequence information. Owing to its simplicity and high efficiency for colinear block detection, MCScanX provides a powerful tool for conducting diverse synteny and evolutionary analyses. Moreover, the detection of colinear blocks has been embraced as an integral step for pangenome graph construction. Here, new application trends of MCScanX are explored, striving to better connect this increasingly used tool to other tools and accelerate insight generation from exponentially growing sequence data. We provide a detailed protocol that covers how to install MCScanX on diverse platforms, tune parameters, prepare input files from data from the National Center for Biotechnology Information, run MCScanX and its visualization and evolutionary analysis tools, and connect MCScanX with external tools, including MCScanX-transposed, Circos and SynVisio. This protocol is easily implemented by users with minimal computational background and is adaptable to new data of interest to them. The data and utility programs for this protocol can be obtained from http://bdx-consulting.com/mcscanx-protocol .},
}

@article {pmid38488860,
year = {2024},
author = {Freddi, S and Rajabal, V and Tetu, SG and Gillings, MR and Penesyan, A},
title = {Microbial biofilms on macroalgae harbour diverse integron gene cassettes.},
journal = {Microbiology (Reading, England)},
volume = {170},
number = {3},
pages = {},
doi = {10.1099/mic.0.001446},
pmid = {38488860},
issn = {1465-2080},
abstract = {Integrons are genetic platforms that capture, rearrange and express mobile modules called gene cassettes. The best characterized gene cassettes encode antibiotic resistance, but the function of most integron gene cassettes remains unknown. Functional predictions suggest that many gene cassettes could encode proteins that facilitate interactions with other cells and with the extracellular environment. Because cell interactions are essential for biofilm stability, we sequenced gene cassettes from biofilms growing on the surface of the marine macroalgae Ulva australis and Sargassum linearifolium. Algal samples were obtained from coastal rock platforms around Sydney, Australia, using seawater as a control. We demonstrated that integrons in microbial biofilms did not sample genes randomly from the surrounding seawater, but harboured specific functions that potentially provided an adaptive advantage to both the bacterial cells in biofilm communities and their macroalgal host. Further, integron gene cassettes had a well-defined spatial distribution, suggesting that each bacterial biofilm acquired these genetic elements via sampling from a large but localized pool of gene cassettes. These findings suggest two forms of filtering: a selective acquisition of different integron-containing bacterial species into the distinct biofilms on Ulva and Sargassum surfaces, and a selective retention of unique populations of gene cassettes at each sampling location.},
}

@article {pmid38488392,
year = {2024},
author = {Wang, M and Li, X and Liu, X and Hou, X and He, Y and Yu, J-H and Hu, S and Yin, H and Xie, B-B},
title = {Annotation of 2,507 Saccharomyces cerevisiae genomes.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0358223},
doi = {10.1128/spectrum.03582-23},
pmid = {38488392},
issn = {2165-0497},
abstract = {Saccharomyces cerevisiae (baker's yeast, budding yeast) is one of the most important model organisms for biological research and is a crucial microorganism in industry. Currently, a huge number of Saccharomyces cerevisiae genome sequences are available at the public domain. However, these genomes are distributed at different websites and a large number of them are released without annotation information. To provide one complete annotated genome data resource, we collected 2,507 Saccharomyces cerevisiae genome assemblies and re-annotated 2,506 assemblies using a custom annotation pipeline, producing a total of 15,407,164 protein-coding gene models. With a custom pipeline, all these gene sequences were clustered into families. A total of 1,506 single-copy genes were selected as marker genes, which were then used to evaluate the genome completeness and base qualities of all assemblies. Pangenomic analyses were performed based on a selected subset of 847 medium-high-quality genomes. Statistical comparisons revealed a number of gene families showing copy number variations among different organism sources. To the authors' knowledge, this study represents the largest genome annotation project of S. cerevisiae so far, providing rich genomic resources for the future studies of the model organism S. cerevisiae and its relatives.IMPORTANCESaccharomyces cerevisiae (baker's yeast, budding yeast) is one of the most important model organisms for biological research and is a crucial microorganism in industry. Though a huge number of Saccharomyces cerevisiae genome sequences are available at the public domain, these genomes are distributed at different websites and most are released without annotation, hindering the efficient reuse of these genome resources. Here, we collected 2,507 genomes for Saccharomyces cerevisiae, performed genome annotation, and evaluated the genome qualities. All the obtained data have been deposited at public repositories and are freely accessible to the community. This study represents the largest genome annotation project of S. cerevisiae so far, providing one complete annotated genome data set for S. cerevisiae, an important workhorse for fundamental biology, biotechnology, and industry.},
}

@article {pmid38488280,
year = {2024},
author = {Giacomini, JJ and Torres-Morales, J and Tang, J and Dewhirst, FE and Borisy, GG and Mark Welch, JL},
title = {Spatial ecology of Haemophilus and Aggregatibacter in the human oral cavity.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0401723},
doi = {10.1128/spectrum.04017-23},
pmid = {38488280},
issn = {2165-0497},
abstract = {UNLABELLED: Haemophilus and Aggregatibacter are two of the most common bacterial genera in the human oral cavity, encompassing both commensals and pathogens of substantial ecological and medical significance. In this study, we conducted a metapangenomic analysis of oral Haemophilus and Aggregatibacter species to uncover genomic diversity, phylogenetic relationships, and habitat specialization within the human oral cavity. Using three metrics-pangenomic gene content, phylogenomics, and average nucleotide identity (ANI)-we first identified distinct species and sub-species groups among these genera. Mapping of metagenomic reads then revealed clear patterns of habitat specialization, such as Aggregatibacter species predominantly in dental plaque, a distinctive Haemophilus parainfluenzae sub-species group on the tongue dorsum, and H. sp. HMT-036 predominantly in keratinized gingiva and buccal mucosa. In addition, we found that supragingival plaque samples contained predominantly only one out of the three taxa, H. parainfluenzae, Aggregatibacter aphrophilus, and A. sp. HMT-458, suggesting independent niches or a competitive relationship. Functional analyses revealed the presence of key metabolic genes, such as oxaloacetate decarboxylase, correlated with habitat specialization, suggesting metabolic versatility as a driving force. Additionally, heme synthesis distinguishes H. sp. HMT-036 from closely related Haemophilus haemolyticus, suggesting that the availability of micronutrients, particularly iron, was important in the evolutionary ecology of these species. Overall, our study exemplifies the power of metapangenomics to identify factors that may affect ecological interactions within microbial communities, including genomic diversity, habitat specialization, and metabolic versatility.

IMPORTANCE: Understanding the microbial ecology of the mouth is essential for comprehending human physiology. This study employs metapangenomics to reveal that various Haemophilus and Aggregatibacter species exhibit distinct ecological preferences within the oral cavity of healthy individuals, thereby supporting the site-specialist hypothesis. Additionally, it was observed that the gene pool of different Haemophilus species correlates with their ecological niches. These findings shed light on the significance of key metabolic functions in shaping microbial distribution patterns and interspecies interactions in the oral ecosystem.},
}

@article {pmid38487210,
year = {2023},
author = {Grizon, A and Theil, S and Callon, C and Gerber, P and Helinck, S and Dugat-Bony, E and Bonnarme, P and Chassard, C},
title = {Genetic and technological diversity of Streptococcus thermophilus isolated from the Saint-Nectaire PDO cheese-producing area.},
journal = {Frontiers in microbiology},
volume = {14},
number = {},
pages = {1245510},
doi = {10.3389/fmicb.2023.1245510},
pmid = {38487210},
issn = {1664-302X},
abstract = {Streptococcus thermophilus is of major importance for cheese manufacturing to ensure rapid acidification; however, studies indicate that intensive use of commercial strains leads to the loss of typical characteristics of the products. To strengthen the link between the product and its geographical area and improve the sensory qualities of cheeses, cheese-producing protected designations of origin (PDO) are increasingly interested in the development of specific autochthonous starter cultures. The present study is therefore investigating the genetic and functional diversity of S. thermophilus strains isolated from a local cheese-producing PDO area. Putative S. thermophilus isolates were isolated and identified from milk collected in the Saint-Nectaire cheese-producing PDO area and from commercial starters. Whole genomes of isolates were sequenced, and a comparative analysis based on their pan-genome was carried out. Important functional properties were studied, including acidifying and proteolytic activities. Twenty-two isolates representative of the diversity of the geographical area and four commercial strains were selected for comparison. The resulting phylogenetic trees do not correspond to the geographical distribution of isolates. The clustering based on the pan-genome analysis indicates that isolates are divided into five distinct groups. A Kyoto Encyclopedia of Genes and Genomes (KEGG) functional annotation of the accessory genes indicates that the accessory gene contents of isolates are involved in different functional categories. High variability in acidifying activities and less diversity in proteolytic activities were also observed. These results indicate that high genetic and functional variabilities of the species S. thermophilus may arise from a small (1,800 km[2]) geographical area and may be exploited to meet demand for use as autochthonous starters.},
}

@article {pmid38486452,
year = {2024},
author = {Shi, T and Zhang, X and Hou, Y and Jia, C and Dan, X and Zhang, Y and Jiang, Y and Lai, Q and Feng, J and Feng, J and Ma, T and Wu, J and Liu, S and Zhang, L and Long, Z and Chen, L and Street, NR and Ingvarsson, PK and Liu, J and Yin, T and Wang, J},
title = {The super-pangenome of Populus unveil genomic facets for its adaptation and diversification in widespread forest trees.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2024.03.009},
pmid = {38486452},
issn = {1752-9867},
abstract = {Understanding the underlying mechanisms and links between genome evolution and adaptive innovations stands as a key goal in evolutionary studies. Poplars, among the world's most widely distributed and cultivated trees, exhibit extensive phenotypic diversity and environmental adaptability. In this study, we present a genus-level super-pangenome comprising 19 Populus genomes, revealing the likely pivotal role of private genes in facilitating local environmental and climate adaptation. Through the integration of pan-genomes with transcriptomes, methylomes and chromatin accessibility mapping, we unveil that the evolutionary trajectories of pan-genes and duplicated genes are closely linked to local genomic landscapes of regulatory and epigenetic architectures, notably CG methylation in gene-body regions. Further comparative genomic analyses have enabled the identification of 142,202 structural variants (SVs) across species, which intersect with a significant number of genes and contribute substantially to both phenotypic and adaptive divergence. We have experimentally validated a ∼180 bp presence/absence variant impacting the expression of the CUC2 gene, crucial for leaf serration formation. Finally, we developed a user-friendly web-based tool encompassing the multi-omics resources associated with the Populus super-pangenome (http://www.populus-superpangenome.com/). Together, the present pioneering super-pangenome resource in forest trees not only aid in the advancement of breeding efforts of this globally important tree genus but also offer valuable insights into potential avenues for comprehending tree biology.},
}

@article {pmid38478130,
year = {2024},
author = {Wisal, A and Saeed, N and Aurongzeb, M and Shafique, M and Sohail, S and Anwar, W and Basharat, Z and Irfan, M and Ullah, A and Hassan, SS},
title = {Bridging drug discovery through hierarchical subtractive genomics against asd, trpG, and secY of pneumonia causing MDR Staphylococcus aureus.},
journal = {Molecular genetics and genomics : MGG},
volume = {299},
number = {1},
pages = {34},
pmid = {38478130},
issn = {1617-4623},
abstract = {Staphylococcus aureus (S. aureus) is an opportunistic gram-positive, non-motile, and non-sporulating bacteria that induces pneumonia, a provocative lung infection affecting mainly the terminal bronchioles and the small air sacs known as alveoli. Recently, it has developed antibiotic resistance to the available consortium as per the WHO reports; thereby, novel remedial targets and resilient medications to forestall and cure this illness are desperately needed. Here, using pan-genomics, a total of 1,387 core proteins were identified. Subtractive proteome analyses further identified 12 proteins that are vital for bacteria. One membrane protein (secY) and two cytoplasmic proteins (asd and trpG) were chosen as possible therapeutic targets concerning minimum % host identity, essentiality, and other cutoff values, such as high resistance in the MDR S. aureus. The UniProt AA sequences of the selected targets were modelled and docked against 3 drug-like chemical libraries. The top-ranked compounds i.e., ZINC82049692, ZINC85492658 and 3a of Isosteviol derivative for Aspartate-semialdehyde dehydrogenase (asd); ZINC38222743, ZINC70455378, and 5 m Isosteviol derivative for Anthranilate synthase component II (trpG); and finally, ZINC72292296, ZINC85632684, and 7 m Isosteviol derivative for Protein translocase subunit secY (secY), were further subjected to molecular dynamics studies for thermodynamic stability and energy calculation. Our study proposes new therapeutic targets in S. aureus, some of which have previously been reported in other pathogenic microorganisms. Owing to further experimental validation, we anticipate that the adapted methodology and the predicted results in this work could make major contributions towards novel drug discovery and their targets in S. aureus caused pneumonia.},
}

@article {pmid38472486,
year = {2024},
author = {Martínez-Gallardo, MJ and Villicaña, C and Yocupicio-Monroy, M and Alcaraz-Estrada, SL and Salazar-Salinas, J and Mendoza-Vázquez, OF and Damazo-Hernández, G and León-Félix, J},
title = {Comparative genomic analysis of Pseudomonas aeruginosa strains susceptible and resistant to carbapenems and aztreonam isolated from patients with healthcare-associated infections in a Mexican hospital.},
journal = {Molecular genetics and genomics : MGG},
volume = {299},
number = {1},
pages = {29},
pmid = {38472486},
issn = {1617-4623},
support = {E05//Ciencia y Tecnología ISSSTE/ ; },
abstract = {Pseudomonas aeruginosa (PA) is an important opportunistic pathogen that causes different infections on immunocompromised patients. Within PA accessory genome, differences in virulence, antibiotic resistance and biofilm formation have been described between strains, leading to the emergence of multidrug-resistant strains. The genome sequences of 17 strains isolated from patients with healthcare-associated infections in a Mexican hospital were genomically and phylogenetically analyzed and antibiotic resistance genes, virulence genes, and biofilm formation genes were detected. Fifteen of the 17 strains were resistant to at least two of the carbapenems meropenem, imipenem, and the monobactam aztreonam. The antibiotic resistance (mexA, mexB, and oprM) and the biofilm formation (pslA and pslD) genes were detected in all strains. Differences were found between strains in accessory genome size. The strains had different sequence types, and seven strains had sequence types associated with global high risk epidemic PA clones. All strains were represented in two groups among PA global strains. In the 17 strains, horizontally acquired resistance genes to aminoglycosides and beta-lactams were found, mainly, and between 230 and 240 genes that encode virulence factors. The strains under study were variable in terms of their accessory genome, antibiotic resistance, and virulence genes. With these characteristics, we provide information about the genomic diversity of clinically relevant PA strains.},
}

@article {pmid38470044,
year = {2024},
author = {Liu, D and Xie, L-S and Lian, S and Li, K and Yang, Y and Wang, W-Z and Hu, S and Liu, S-J and Liu, C and He, Z},
title = {Anaerostipes hadrus, a butyrate-producing bacterium capable of metabolizing 5-fluorouracil.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0081623},
doi = {10.1128/msphere.00816-23},
pmid = {38470044},
issn = {2379-5042},
abstract = {UNLABELLED: Anaerostipes hadrus (A. hadrus) is a dominant species in the human gut microbiota and considered a beneficial bacterium for producing probiotic butyrate. However, recent studies have suggested that A. hadrus may negatively affect the host through synthesizing fatty acid and metabolizing the anticancer drug 5-fluorouracil, indicating that the impact of A. hadrus is complex and unclear. Therefore, comprehensive genomic studies on A. hadrus need to be performed. We integrated 527 high-quality public A. hadrus genomes and five distinct metagenomic cohorts. We analyzed these data using the approaches of comparative genomics, metagenomics, and protein structure prediction. We also performed validations with culture-based in vitro assays. We constructed the first large-scale pan-genome of A. hadrus (n = 527) and identified 5-fluorouracil metabolism genes as ubiquitous in A. hadrus genomes as butyrate-producing genes. Metagenomic analysis revealed the wide and stable distribution of A. hadrus in healthy individuals, patients with inflammatory bowel disease, and patients with colorectal cancer, with healthy individuals carrying more A. hadrus. The predicted high-quality protein structure indicated that A. hadrus might metabolize 5-fluorouracil by producing bacterial dihydropyrimidine dehydrogenase (encoded by the preTA operon). Through in vitro assays, we validated the short-chain fatty acid production and 5-fluorouracil metabolism abilities of A. hadrus. We observed for the first time that A. hadrus can convert 5-fluorouracil to α-fluoro-β-ureidopropionic acid, which may result from the combined action of the preTA operon and adjacent hydA (encoding bacterial dihydropyrimidinase). Our results offer novel understandings of A. hadrus, exceptionally functional features, and potential applications.

IMPORTANCE: This work provides new insights into the evolutionary relationships, functional characteristics, prevalence, and potential applications of Anaerostipes hadrus.},
}

@article {pmid38469580,
year = {2024},
author = {Yakubu, B and Appiah, EM and Adu, AF},
title = {Pangenome Analysis of Helicobacter pylori Isolates from Selected Areas of Africa Indicated Diverse Antibiotic Resistance and Virulence Genes.},
journal = {International journal of genomics},
volume = {2024},
number = {},
pages = {5536117},
pmid = {38469580},
issn = {2314-4378},
abstract = {The challenge facing Helicobacter pylori (H. pylori) infection management in some parts of Africa is the evolution of drug-resistant species, the lack of gold standard in diagnostic methods, and the ineffectiveness of current vaccines against the bacteria. It is being established that even though clinical consequences linked to the bacteria vary geographically, there is rather a generic approach to treatment. This situation has remained problematic in the successful fight against the bacteria in parts of Africa. As a result, this study compared the genomes of selected H. pylori isolates from selected areas of Africa and evaluated their virulence and antibiotic drug resistance, those that are highly pathogenic and are associated with specific clinical outcomes and those that are less virulent and rarely associated with clinical outcomes. 146 genomes of H. pylori isolated from selected locations of Africa were sampled, and bioinformatic tools such as Abricate, CARD RGI, MLST, Prokka, Roary, Phandango, Google Sheets, and iTOLS were used to compare the isolates and their antibiotic resistance or susceptibility. Over 20 k virulence and AMR genes were observed. About 95% of the isolates were genetically diverse, 90% of the isolates harbored shell genes, and 50% harbored cloud and core genes. Some isolates did not retain the cagA and vacA genes. Clarithromycin, metronidazole, amoxicillin, and tinidazole were resistant to most AMR genes (vacA, cagA, oip, and bab). Conclusion. This study found both virulence and AMR genes in all H. pylori strains in all the selected geographies around Africa with differing quantities. MLST, Pangenome, and ORF analyses showed disparities among the isolates. This in general could imply diversities in terms of genetics, evolution, and protein production. Therefore, generic administration of antibiotics such as clarithromycin, amoxicillin, and erythromycin as treatment methods in the African subregion could be contributing to the spread of the bacterium's antibiotic resistance.},
}

@article {pmid38463963,
year = {2024},
author = {Young, MG and Straub, TJ and Worby, CJ and Metsky, HC and Gnirke, A and Bronson, RA and van Dijk, LR and Desjardins, CA and Matranga, C and Qu, J and Dodson, K and Schreiber, HL and Manson, AL and Hultgren, SJ and Earl, AM},
title = {Distinct Escherichia coli transcriptional profiles in the guts of recurrent UTI sufferers revealed by pan-genome hybrid selection.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.02.29.582780},
pmid = {38463963},
abstract = {Low-abundance members of microbial communities are difficult to study in their native habitat. This includes Escherichia coli , a minor, but common inhabitant of the gastrointestinal tract and opportunistic pathogen, including of the urinary tract, where it causes most infections. While our understanding of the interactions between uropathogenic Escherichia coli (UPEC) and the bladder is increasing, comparatively little is known about UPEC in its pre-infection reservoir, partly due to its low abundance there (<1% relative abundance). In order to specifically and sensitively explore the genomes and transcriptomes of diverse E. coli from gastrointestinal communities, we developed E. coli PanSelect, a set of probes designed to enrich E. coli 's broad pangenome. First we demonstrated the ability of PanSelect to enrich diverse strains in an unbiased way using a mock community of known composition. Then we enriched E. coli DNA and RNA from human stool microbiomes by 158 and 30-fold, respectively. We also used E. coli PanSelect to explore the gene content and transcriptome of E. coli within the gut microbiomes of women with history of recurrent urinary tract infection (rUTI), finding differential regulation of pathways that suggests that the rUTI gut environment promotes respiratory vs fermentative metabolism. E. coli PanSelect technology holds promise for investigations of native in vivo biology of diverse E. coli in the gut and other environments, where it is a minor component of the microbial community, using unbiased, culture-free shotgun sequencing. This method could also be generally applied to other highly diverse, low abundance bacteria.},
}

@article {pmid38463499,
year = {2024},
author = {Li, H and Marin, M and Farhat, MR},
title = {Exploring gene content with pangenome gene graphs.},
journal = {ArXiv},
volume = {},
number = {},
pages = {},
pmid = {38463499},
issn = {2331-8422},
abstract = {MOTIVATION: The gene content regulates the biology of an organism. It varies between species and between individuals of the same species. Although tools have been developed to identify gene content changes in bacterial genomes, none is applicable to collections of large eukaryotic genomes such as the human pangenome.

RESULTS: We developed pangene, a computational tool to identify gene orientation, gene order and gene copy-number changes in a collection of genomes. Pangene aligns a set of input protein sequences to the genomes, resolves redundancies between protein sequences and constructs a gene graph with each genome represented as a walk in the graph. It additionally finds subgraphs that encodes gene content changes. Applied to the human pangenome, pangene identifies known gene-level variations and reveals complex haplotypes that are not well studied before. Pangene also works with high-quality bacterial pangenome and reports similar numbers of core and accessory genes in comparison to existing tools.

Source code at https://github.com/lh3/pangene; pre-built pangene graphs can be downloaded from https://zenodo.org/records/8118576 and visualized at https://pangene.bioinweb.org.},
}

@article {pmid38461665,
year = {2024},
author = {Feng, NX and Li, DW and Zhang, F and Bin, H and Huang, YT and Xiang, L and Liu, BL and Cai, QY and Li, YW and Xu, DL and Xie, Y and Mo, CH},
title = {Biodegradation of phthalate acid esters and whole-genome analysis of a novel Streptomyces sp. FZ201 isolated from natural habitats.},
journal = {Journal of hazardous materials},
volume = {469},
number = {},
pages = {133972},
doi = {10.1016/j.jhazmat.2024.133972},
pmid = {38461665},
issn = {1873-3336},
abstract = {Di-n-butyl phthalate (DBP) is one of the most extensively used phthalic acid esters (PAEs) and is considered to be an emerging, globally concerning pollutant. The genus Streptomyces holds promise as a degrader of various organic pollutants, but PAE biodegradation mechanisms by Streptomyces species remain unsolved. In this study, a novel PAE-degrading Streptomyces sp. FZ201 isolated from natural habitats efficiently degraded various PAEs. FZ201 had strong resilience against DBP and exhibited immediate degradation, with kinetics adhering to a first-order model. The comprehensive biodegradation of DBP involves de-esterification, β-oxidation, trans-esterification, and aromatic ring cleavage. FZ201 contains numerous catabolic genes that potentially facilitate PAE biodegradation. The DBP metabolic pathway was reconstructed by genome annotation and intermediate identification. Streptomyces species have an open pangenome with substantial genome expansion events during the evolutionary process, enabling extensive genetic diversity and highly plastic genomes within the Streptomyces genus. FZ201 had a diverse array of highly expressed genes associated with the degradation of PAEs, potentially contributing significantly to its adaptive advantage and efficiency of PAE degradation. Thus, FZ201 is a promising candidate for remediating highly PAE-contaminated environments. These findings enhance our preliminary understanding of the molecular mechanisms employed by Streptomyces for the removal of PAEs.},
}

@article {pmid38459435,
year = {2024},
author = {Zhu, L and Liu, H and Li, X and Shi, Y and Yin, X and Pi, X},
title = {Whole-genome sequencing and analysis of Chryseobacterium arthrosphaerae from Rana nigromaculata.},
journal = {BMC microbiology},
volume = {24},
number = {1},
pages = {80},
pmid = {38459435},
issn = {1471-2180},
support = {2022SNJF072//Zhejiang Provincial Science and Technology Cooperation Plan of "Three Rural Areas and Nine Rural Areas"/ ; 2022SNJF072//Zhejiang Provincial Science and Technology Cooperation Plan of "Three Rural Areas and Nine Rural Areas"/ ; 2022SNJF072//Zhejiang Provincial Science and Technology Cooperation Plan of "Three Rural Areas and Nine Rural Areas"/ ; 2022SNJF072//Zhejiang Provincial Science and Technology Cooperation Plan of "Three Rural Areas and Nine Rural Areas"/ ; 2022SNJF072//Zhejiang Provincial Science and Technology Cooperation Plan of "Three Rural Areas and Nine Rural Areas"/ ; 2022SNJF072//Zhejiang Provincial Science and Technology Cooperation Plan of "Three Rural Areas and Nine Rural Areas"/ ; },
abstract = {Chryseobacterium arthrosphaerae strain FS91703 was isolated from Rana nigromaculata in our previous study. To investigate the genomic characteristics, pathogenicity-related genes, antimicrobial resistance, and phylogenetic relationship of this strain, PacBio RS II and Illumina HiSeq 2000 platforms were used for the whole genome sequencing. The genome size of strain FS91703 was 5,435,691 bp and GC content was 37.78%. A total of 4,951 coding genes were predicted; 99 potential virulence factors homologs were identified. Analysis of antibiotic resistance genes revealed that strain FS91703 harbored 10 antibiotic resistance genes in 6 categories and 2 multidrug-resistant efflux pump genes, including adeG and farA. Strain FS91703 was sensitive to β-lactam combination drugs, cephem, monobactam and carbapenems, intermediately resistant to phenicol, and resistant to penicillin, aminoglycosides, tetracycline, fluoroquinolones, and folate pathway inhibitors. Phylogenetic analysis revealed that strain FS91703 and C. arthrosphaerae CC-VM-7[T] were on the same branch of the phylogenetic tree based on 16 S rRNA; the ANI value between them was 96.99%; and the DDH values were 80.2, 72.2 and 81.6% by three default calculation formulae. These results suggested that strain FS91703 was a species of C. arthrosphaerae. Pan-genome analysis showed FS91703 had 566 unique genes compared with 13 other C. arthrosphaerae strains, and had a distant phylogenetic relationship with the other C. arthrosphaerae strains of the same branch in phylogenetic tree based on orthologous genes. The results of this study suggest that strain FS91703 is a multidrug-resistant and highly virulent bacterium, that differs from other C. arthrosphaerae strains at the genomic level. The knowledge about the genomic characteristics and antimicrobial resistance of strain FS91703 provides valuable insights into this rare species, as well as guidance for the treatment of the disease caused by FS91703 in Rana nigromaculata.},
}

@article {pmid38450165,
year = {2024},
author = {Zhou, Y and Tu, T and Yao, X and Luo, Y and Yang, Z and Ren, M and Zhang, G and Yu, Y and Lu, A and Wang, Y},
title = {Pan-genome analysis of Streptococcus suis serotype 2 highlights genes associated with virulence and antibiotic resistance.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1362316},
pmid = {38450165},
issn = {1664-302X},
abstract = {Streptococcus suis serotype 2 (SS2) is a Gram-positive bacterium. It is a common and significant pathogen in pigs and a common cause of zoonotic meningitis in humans. It can lead to sepsis, endocarditis, arthritis, and pneumonia. If not diagnosed and treated promptly, it has a high mortality rate. The pan-genome of SS2 is open, and with an increasing number of genes, the core genome and accessory genome may exhibit more pronounced differences. Due to the diversity of SS2, the genes related to its virulence and resistance are still unclear. In this study, a strain of SS2 was isolated from a pig farm in Sichuan Province, China, and subjected to whole-genome sequencing and characterization. Subsequently, we conducted a Pan-Genome-Wide Association Study (Pan-GWAS) on 230 strains of SS2. Our analysis indicates that the core genome is composed of 1,458 genes related to the basic life processes of the bacterium. The accessory genome, consisting of 4,337 genes, is highly variable and a major contributor to the genetic diversity of SS2. Furthermore, we identified important virulence and resistance genes in SS2 through pan-GWAS. The virulence genes of SS2 are mainly associated with bacterial adhesion. In addition, resistance genes in the core genome may confer natural resistance of SS2 to fluoroquinolone and glycopeptide antibiotics. This study lays the foundation for further research on the virulence and resistance of SS2, providing potential new drug and vaccine targets against SS2.},
}

@article {pmid38448140,
year = {2024},
author = {Mathur, S and Singh, D and Ranjan, R},
title = {Recent advances in plant translational genomics for crop improvement.},
journal = {Advances in protein chemistry and structural biology},
volume = {139},
number = {},
pages = {335-382},
doi = {10.1016/bs.apcsb.2023.11.009},
pmid = {38448140},
issn = {1876-1631},
abstract = {The growing population, climate change, and limited agricultural resources put enormous pressure on agricultural systems. A plateau in crop yields is occurring and extreme weather events and urbanization threaten the livelihood of farmers. It is imperative that immediate attention is paid to addressing the increasing food demand, ensuring resilience against emerging threats, and meeting the demand for more nutritious, safer food. Under uncertain conditions, it is essential to expand genetic diversity and discover novel crop varieties or variations to develop higher and more stable yields. Genomics plays a significant role in developing abundant and nutrient-dense food crops. An alternative to traditional breeding approach, translational genomics is able to improve breeding programs in a more efficient and precise manner by translating genomic concepts into practical tools. Crop breeding based on genomics offers potential solutions to overcome the limitations of conventional breeding methods, including improved crop varieties that provide more nutritional value and are protected from biotic and abiotic stresses. Genetic markers, such as SNPs and ESTs, contribute to the discovery of QTLs controlling agronomic traits and stress tolerance. In order to meet the growing demand for food, there is a need to incorporate QTLs into breeding programs using marker-assisted selection/breeding and transgenic technologies. This chapter primarily focuses on the recent advances that are made in translational genomics for crop improvement and various omics techniques including transcriptomics, metagenomics, pangenomics, single cell omics etc. Numerous genome editing techniques including CRISPR Cas technology and their applications in crop improvement had been discussed.},
}

@article {pmid38439049,
year = {2024},
author = {Chen, C and Wu, S and Sun, Y and Zhou, J and Chen, Y and Zhang, J and Birchler, JA and Han, F and Yang, N and Su, H},
title = {Three near-complete genome assemblies reveal substantial centromere dynamics from diploid to tetraploid in Brachypodium genus.},
journal = {Genome biology},
volume = {25},
number = {1},
pages = {63},
pmid = {38439049},
issn = {1474-760X},
support = {2021YFF1000800//National Key Research and Development Program of China/ ; 32170571//National Natural Science Foundation of China/ ; 2021ZKPY008//Fundamental Research Funds for the Central Universities/ ; No. B21HJ0504//Hainan Yazhou Bay Seed Laboratory/ ; },
abstract = {BACKGROUND: Centromeres are critical for maintaining genomic stability in eukaryotes, and their turnover shapes genome architectures and drives karyotype evolution. However, the co-evolution of centromeres from different species in allopolyploids over millions of years remains largely unknown.

RESULTS: Here, we generate three near-complete genome assemblies, a tetraploid Brachypodium hybridum and its two diploid ancestors, Brachypodium distachyon and Brachypodium stacei. We detect high degrees of sequence, structural, and epigenetic variations of centromeres at base-pair resolution between closely related Brachypodium genomes, indicating the appearance and accumulation of species-specific centromere repeats from a common origin during evolution. We also find that centromere homogenization is accompanied by local satellite repeats bursting and retrotransposon purging, and the frequency of retrotransposon invasions drives the degree of interspecies centromere diversification. We further investigate the dynamics of centromeres during alloploidization process, and find that dramatic genetics and epigenetics architecture variations are associated with the turnover of centromeres between homologous chromosomal pairs from diploid to tetraploid. Additionally, our pangenomes analysis reveals the ongoing variations of satellite repeats and stable evolutionary homeostasis within centromeres among individuals of each Brachypodium genome with different polyploidy levels.

CONCLUSIONS: Our results provide unprecedented information on the genomic, epigenomic, and functional diversity of highly repetitive DNA between closely related species and their allopolyploid genomes at both coarse and fine scale.},
}

@article {pmid38438804,
year = {2024},
author = {Niu, D and Feng, N and Xi, S and Xu, J and Su, Y},
title = {Genomics-based analysis of four porcine-derived lactic acid bacteria strains and their evaluation as potential probiotics.},
journal = {Molecular genetics and genomics : MGG},
volume = {299},
number = {1},
pages = {24},
pmid = {38438804},
issn = {1617-4623},
support = {2022YFD1300402//Key Technologies Research and Development Program/ ; 31872362//National Natural Science Foundation of China/ ; 32072688//National Natural Science Foundation of China/ ; },
abstract = {The search for probiotics and exploration of their functions are crucial for livestock farming. Recently, porcine-derived lactic acid bacteria (LAB) have shown great potential as probiotics. However, research on the evaluation of porcine-derived LAB as potential probiotics through genomics-based analysis is relatively limited. The present study analyzed four porcine-derived LAB strains (Lactobacillus johnsonii L16, Latilactobacillus curvatus ZHA1, Ligilactobacillus salivarius ZSA5 and Ligilactobacillus animalis ZSB1) using genomic techniques and combined with in vitro tests to evaluate their potential as probiotics. The genome sizes of the four strains ranged from 1,897,301 bp to 2,318,470 bp with the GC contents from 33.03 to 41.97%. Pan-genomic analysis and collinearity analysis indicated differences among the genomes of four strains. Carbohydrate active enzymes analysis revealed that L. johnsonii L16 encoded more carbohydrate active enzymes than other strains. KEGG pathway analysis and in vitro tests confirmed that L. johnsonii L16 could utilize a wide range of carbohydrates and had good utilization capacity for each carbohydrate. The four strains had genes related to acid tolerance and were tolerant to low pH, with L. johnsonii L16 showing the greatest tolerance. The four strains contained genes related to bile salt tolerance and were able to tolerate 0.1% bile salt. Four strains had antioxidant related genes and exhibited antioxidant activity in in vitro tests. They contained the genes linked with organic acid biosynthesis and exhibited antibacterial activity against enterotoxigenic Escherichia coli K88 (ETEC K88) and Salmonella 6,7:c:1,5, wherein, L. johnsonii L16 and L. salivarius ZSA5 had gene clusters encoding bacteriocin. Results suggest that genome analysis combined with in vitro tests is an effective approach for evaluating different strains as probiotics. The findings of this study indicate that L. johnsonii L16 has the potential as a probiotic strain among the four strains and provide theoretical basis for the development of probiotics in swine production.},
}

@article {pmid38421269,
year = {2024},
author = {Deery, J and Carmody, M and Flavin, R and Tomanek, M and O'Keeffe, M and McGlacken, GP and Reen, FJ},
title = {Comparative genomics reveals distinct diversification patterns among LysR-type transcriptional regulators in the ESKAPE pathogen Pseudomonas aeruginosa.},
journal = {Microbial genomics},
volume = {10},
number = {2},
pages = {},
doi = {10.1099/mgen.0.001205},
pmid = {38421269},
issn = {2057-5858},
mesh = {Humans ; Pseudomonas aeruginosa/genetics ; Genomics ; *Pseudomonas Infections ; Pseudomonas ; *Cystic Fibrosis/genetics ; },
abstract = {Pseudomonas aeruginosa, a harmful nosocomial pathogen associated with cystic fibrosis and burn wounds, encodes for a large number of LysR-type transcriptional regulator proteins. To understand how and why LTTR proteins evolved with such frequency and to establish whether any relationships exist within the distribution we set out to identify the patterns underpinning LTTR distribution in P. aeruginosa and to uncover cluster-based relationships within the pangenome. Comparative genomic studies revealed that in the JGI IMG database alone ~86 000 LTTRs are present across the sequenced genomes (n=699). They are widely distributed across the species, with core LTTRs present in >93 % of the genomes and accessory LTTRs present in <7 %. Analysis showed that subsets of core LTTRs can be classified as either variable (typically specific to P. aeruginosa) or conserved (and found to be distributed in other Pseudomonas species). Extending the analysis to the more extensive Pseudomonas database, PA14 rooted analysis confirmed the diversification patterns and revealed PqsR, the receptor for the Pseudomonas quinolone signal (PQS) and 2-heptyl-4-quinolone (HHQ) quorum-sensing signals, to be amongst the most variable in the dataset. Successful complementation of the PAO1 pqsR [-] mutant using representative variant pqsR sequences suggests a degree of structural promiscuity within the most variable of LTTRs, several of which play a prominent role in signalling and communication. These findings provide a new insight into the diversification of LTTR proteins within the P. aeruginosa species and suggests a functional significance to the cluster, conservation and distribution patterns identified.},
}

Humans
Pseudomonas aeruginosa/genetics
Genomics
*Pseudomonas Infections
Pseudomonas
*Cystic Fibrosis/genetics

@article {pmid38421062,
year = {2024},
author = {Ji, G and Long, Y and Cai, G and Wang, A and Yan, G and Li, H and Gao, G and Xu, K and Huang, Q and Chen, B and Li, L and Li, F and Nishio, T and Shen, J and Wu, X},
title = {The chromosome-scale genome of wild Brassica oleracea provides insights into the domestication of Brassica plants.},
journal = {Journal of experimental botany},
volume = {},
number = {},
pages = {},
doi = {10.1093/jxb/erae079},
pmid = {38421062},
issn = {1460-2431},
abstract = {The cultivated diploid Brassica oleracea is an important vegetable crop, but the genetic basis of domestication remains largely unclear without high-quality reference genomes of wild B. oleracea. Here, we report the first chromosome-level assembly of the wild Brassica oleracea L. W03 genome, (total genome size, 630.7 Mb; scaffold N50, 64.6 Mb). Using newly assembled W03 genome, we constructed a gene-based B. oleracea pangenome and identified 29,744 core genes, 23,306 dispensable genes, and 1,896 private genes. We resequenced 53 accessions, which represent six potential wild B. oleracea progenitor species. The results of the population genomic analysis showed that wild B. oleracea population had the highest level of diversity and represented the more closely related population of horticultural B. oleracea. Additionally, the WUSCHEL gene was found to play a decisive role in domestication and to be involved in cauliflower and broccoli curd formation. We also illustrate the loss of disease resistance genes during domestication selection. Our results provide deep insights into B. oleracea domestication and will facilitate Brassica crop genetic improvement.},
}

@article {pmid38418560,
year = {2024},
author = {Chao, P and Zhang, X and Zhang, L and Yang, A and Wang, Y and Chen, X},
title = {Proteomics-based vaccine targets annotation and design of multi-epitope vaccine against antibiotic-resistant Streptococcus gallolyticus.},
journal = {Scientific reports},
volume = {14},
number = {1},
pages = {4836},
pmid = {38418560},
issn = {2045-2322},
abstract = {Streptococcus gallolyticus is a non-motile, gram-positive bacterium that causes infective endocarditis. S. gallolyticus has developed resistance to existing antibiotics, and no vaccine is currently available. Therefore, it is essential to develop an effective S. gallolyticus vaccine. Core proteomics was used in this study together with subtractive proteomics and reverse vaccinology approach to find antigenic proteins that could be utilized for the design of the S. gallolyticus multi-epitope vaccine. The pipeline identified two antigenic proteins as potential vaccine targets: penicillin-binding protein and the ATP synthase subunit. T and B cell epitopes from the specific proteins were forecasted employing several immunoinformatics and bioinformatics resources. A vaccine (360 amino acids) was created using a combination of seven cytotoxic T cell lymphocyte (CTL), three helper T cell lymphocyte (HTL), and five linear B cell lymphocyte (LBL) epitopes. To increase immune responses, the vaccine was paired with a cholera enterotoxin subunit B (CTB) adjuvant. The developed vaccine was highly antigenic, non-allergenic, and stable for human use. The vaccine's binding affinity and molecular interactions with the human immunological receptor TLR4 were studied using molecular mechanics/generalized Born surface area (MMGBSA), molecular docking, and molecular dynamic (MD) simulation analyses. Escherichia coli (strain K12) plasmid vector pET-28a (+) was used to examine the ability of the vaccine to be expressed. According to the outcomes of these computer experiments, the vaccine is quite promising in terms of developing a protective immunity against diseases. However, in vitro and animal research are required to validate our findings.},
}

@article {pmid38417638,
year = {2024},
author = {Banerjee, R and Robinson, SM and Lahiri, A and Verma, P and Banerjee, AK and Basak, S and Basak, K and Paul, S},
title = {Exploring the resistome and virulome in major sequence types of Acinetobacter baumannii genomes: Correlations with genome divergence and sequence types.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105579},
doi = {10.1016/j.meegid.2024.105579},
pmid = {38417638},
issn = {1567-7257},
abstract = {The increasing global prevalence of antimicrobial resistance in Acinetobacter baumannii has led to concerns regarding the effectiveness of infection treatment. Moreover, the critical role of virulence factor genes in A. baumannii's pathogenesis and its propensity to cause severe disease is of particular importance. Comparative genomics, including multi-locus sequence typing (MLST), enhances our understanding of A. baumannii epidemiology. While there is substantial documentation on A. baumannii, a comprehensive study of the antibiotic-resistant mechanisms and the virulence factors contributing to pathogenesis, and their correlation with Sequence Types (STs) remains incompletely elucidated. In this study, we aim to explore the relationship between antimicrobial resistance genes, virulence factor genes, and STs using genomic data from 223 publicly available A. baumannii strains. The core phylogeny analysis revealed five predominant STs in A. baumannii genomes, linked to their geographical sources of isolation. Furthermore, the resistome and virulome of A. baumannii followed an evolutionary pattern consistent with their pan-genome evolution. Among the major STs, we observed significant variations in resistant genes against "aminoglycoside" and "sulphonamide" antibiotics, highlighting the role of genotypic variations in determining resistance profiles. Furthermore, the presence of virulence factor genes, particularly exotoxin and nutritional / metabolic factor genes, played a crucial role in distinguishing the major STs, suggesting a potential link between genetic makeup and pathogenicity. Understanding these associations can provide valuable insights into A. baumannii's virulence potential and clinical outcomes, enabling the development of effective strategies to combat infections caused by this opportunistic pathogen.},
}

@article {pmid38415665,
year = {2024},
author = {Guillén, R and Salinas, C and Mendoza-Álvarez, A and Rubio Rodríguez, LA and Díaz-de Usera, A and Lorenzo-Salazar, JM and González-Montelongo, R and Flores, C and Rodríguez, F},
title = {Genomic epidemiology of the primary methicillin-resistant Staphylococcus aureus clones causing invasive infections in Paraguayan children.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0301223},
doi = {10.1128/spectrum.03012-23},
pmid = {38415665},
issn = {2165-0497},
abstract = {UNLABELLED: Methicillin-resistant Staphylococcus aureus (MRSA) is one of the major human pathogens. It could carry numerous resistance genes and virulence factors in its genome, some of which are related to the severity of the infection. An observational, descriptive, cross-sectional study was designed to molecularly analyze MRSA isolates that cause invasive infections in Paraguayan children from 2009 to 2013. Ten representative MRSA isolates of the main clonal complex identified were analyzed with short-read paired-end sequencing and assessed for the virulome, resistome, and phylogenetic relationships. All the genetically linked MRSA isolates were recovered from diverse clinical sources, patients, and hospitals at broad gap periods. The pan-genomic analysis of these clones revealed three major and different clonal complexes (CC30, CC5, and CC8), each composed of clones closely related to each other. The CC30 genomes prove to be a successful clone, strongly installed and disseminated throughout our country, and closely related to other CC30 public genomes from the region and the world. The CC5 shows the highest genetic variability, and the CC8 carried the complete arginine catabolic mobile element (ACME), closely related to the USA300-NAE-ACME+, identified as the major cause of CA-MRSA infections in North America. Multiple virulence and resistance genes were identified for the first time in this study, highlighting the complex virulence profiles of MRSA circulating in the country. This study opens a wide range of new possibilities for future projects and trials to improve the existing knowledge on the epidemiology of MRSA circulating in Paraguay.

IMPORTANCE: The increasing prevalence of methicillin-resistant Staphylococcus aureus (MRSA) is a public health problem worldwide. The most frequent MRSA clones identified in Paraguay in previous studies (including community and hospital acquired) were the Pediatric (CC5-ST5-IV), the Cordobes-Chilean (CC5-ST5-I), the SouthWest Pacific (CC30-ST30-IV), and the Brazilian (CC8-ST239-III) clones. In this study, the pan-genomic analysis of the most representative MRSA clones circulating in invasive infection in Paraguayan children over the years 2009-2013, such as the CC30-ST30-IV, CC5-ST5-IV, and CC8-ST8-IV, was carried out to evaluate their genetic diversity, their repertoire of virulence factors, and antimicrobial resistance determinants. This revealed multiple virulence and resistance genes, highlighting the complex virulence profiles of MRSA circulating in Paraguay. Our work is the first genomic study of MRSA in Paraguay and will contribute to the development of genomic surveillance in the region and our understanding of the global epidemiology of this pathogen.},
}

@article {pmid38413855,
year = {2024},
author = {Wang, H and Xia, F and Xia, Y and Li, J and Hu, Y and Deng, Y and Zou, M},
title = {Pangenome analysis of Shewanella xiamenensis revealed important genetic traits concerning genetic diversity, pathogenicity and antibiotic resistance.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {216},
pmid = {38413855},
issn = {1471-2164},
support = {No. 2023JJ30942//Natural Science Foundation of Hunan Province/ ; },
abstract = {BACKGROUND: Shewanella xiamenensis, widely distributed in natural environments, has long been considered as opportunistic pathogen. Recently, significant changes in the resistance spectrum have been observed in S. xiamenensis, due to acquired antibiotic resistance genes. Therefore, a pan-genome analysis was conducted to illuminate the genomic changes in S. xiamenensis.

RESULTS: Phylogenetic analysis revealed three major clusters and three singletons, among which close relationship between several strains was discovered, regardless of their host and niches. The "open" genomes with diversity of accessory and strain-specific genomes took advantage towards diversity environments. The purifying selection pressure was the main force on genome evolution, especially in conservative genes. Only 53 gene families were under positive selection pressure. Phenotypic resistance analysis revealed 21 strains were classified as multi-drug resistance (MDR). Ten types of antibiotic resistance genes and two heavy metal resistance operons were discovered in S. xiamenensis. Mobile genetic elements and horizontal gene transfer increased genome diversity and were closely related to MDR strains. S. xiamenensis carried a variety of virulence genes and macromolecular secretion systems, indicating their important roles in pathogenicity and adaptability. Type IV secretion system was discovered in 15 genomes with various sequence structures, indicating it was originated from different donors through horizontal gene transfer.

CONCLUSIONS: This study provided with a detailed insight into the changes in the pan-genome of S. xiamenensis, highlighting its capability to acquire new mobile genetic elements and resistance genes for its adaptation to environment and pathogenicity to human and animals.},
}

@article {pmid38413611,
year = {2024},
author = {Go, S and Koo, H and Jung, M and Hong, S and Yi, G and Kim, YM},
title = {Pan-chloroplast genomes for accession-specific marker development in Hibiscus syriacus.},
journal = {Scientific data},
volume = {11},
number = {1},
pages = {246},
pmid = {38413611},
issn = {2052-4463},
abstract = {Hibiscus syriacus L. is a renowned ornamental plant. We constructed 95 chloroplast genomes of H. syriacus L. cultivars using a short-read sequencing platform (Illumina) and a long-read sequencing platform (Oxford Nanopore Technology). The following genome assembly, we delineate quadripartite structures encompassing large single-copy, small single-copy, and inverted repeat (IRa and IRb) regions, from 160,231 bp to 161,041 bp. Our comprehensive analyses confirmed the presence of 79 protein-coding genes, 30 tRNA genes, and 4 rRNA genes in the pan-chloroplast genome, consistent with prior research on the H. syriacus chloroplast genome. Subsequent pangenome analysis unveiled widespread genome sequence conservation alongside unique cultivar-specific variant patterns consisting of 193 single-nucleotide polymorphisms and 61 insertions or deletions. The region containing intra-species variant patterns, as identified in this study, has the potential to develop accession-specific molecular markers, enhancing precision in cultivar classification. These findings are anticipated to drive advancements in breeding strategies, augment biodiversity, and unlock the agricultural potential inherent in H. syriacus.},
}

@article {pmid38412041,
year = {2024},
author = {Dong, X and Jia, H and Yu, Y and Xiang, Y and Zhang, Y},
title = {Genomic revisitation and reclassification of the genus Providencia.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0073123},
doi = {10.1128/msphere.00731-23},
pmid = {38412041},
issn = {2379-5042},
abstract = {Members of Providencia, although typically opportunistic, can cause severe infections in immunocompromised hosts. Recent advances in genome sequencing provide an opportunity for more precise study of this genus. In this study, we first identified and characterized a novel species named Providencia zhijiangensis sp. nov. It has ≤88.23% average nucleotide identity (ANI) and ≤31.8% in silico DNA-DNA hybridization (dDDH) values with all known Providencia species, which fall significantly below the species-defining thresholds. Interestingly, we found that Providencia stuartii and Providencia thailandensis actually fall under the same species, evidenced by an ANI of 98.59% and a dDDH value of 90.4%. By fusing ANI with phylogeny, we have reclassified 545 genomes within this genus into 20 species, including seven unnamed taxa (provisionally titled Taxon 1-7), which can be further subdivided into 23 lineages. Pangenomic analysis identified 1,550 genus-core genes in Providencia, with coenzymes being the predominant category at 10.56%, suggesting significant intermediate metabolism activity. Resistance analysis revealed that most lineages of the genus (82.61%, 19/23) carry a high number of antibiotic-resistance genes (ARGs) and display diverse resistance profiles. Notably, the majority of ARGs are located on plasmids, underscoring the significant role of plasmids in the resistance evolution within this genus. Three species or lineages (P. stuartii, Taxon 3, and Providencia hangzhouensis L12) that possess the highest number of carbapenem-resistance genes suggest their potential influence on clinical treatment. These findings underscore the need for continued surveillance and study of this genus, particularly due to their role in harboring antibiotic-resistance genes.IMPORTANCEThe Providencia genus, known to harbor opportunistic pathogens, has been a subject of interest due to its potential to cause severe infections, particularly in vulnerable individuals. Our research offers groundbreaking insights into this genus, unveiling a novel species, Providencia zhijiangensis sp. nov., and highlighting the need for a re-evaluation of existing classifications. Our comprehensive genomic assessment offers a detailed classification of 545 genomes into distinct species and lineages, revealing the rich biodiversity and intricate species diversity within the genus. The substantial presence of antibiotic-resistance genes in the Providencia genus underscores potential challenges for public health and clinical treatments. Our study highlights the pressing need for increased surveillance and research, enriching our understanding of antibiotic resistance in this realm.},
}

@article {pmid38412007,
year = {2024},
author = {Kim, M and Kim, W and Park, Y and Jung, J and Park, W},
title = {Lineage-specific evolution of Aquibium, a close relative of Mesorhizobium, during habitat adaptation.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0209123},
doi = {10.1128/aem.02091-23},
pmid = {38412007},
issn = {1098-5336},
abstract = {The novel genus Aquibium that lacks nitrogenase was recently reclassified from the Mesorhizobium genus. The genomes of Aquibium species isolated from water were smaller and had higher GC contents than those of Mesorhizobium species. Six Mesorhizobium species lacking nitrogenase were found to exhibit low similarity in the average nucleotide identity values to the other 24 Mesorhizobium species. Therefore, they were classified as the non-N2-fixing Mesorhizobium lineage (N-ML), an evolutionary intermediate species. The results of our phylogenomic analyses and the loss of Rhizobiales-specific fur/mur indicated that Mesorhizobium species may have evolved from Aquibium species through an ecological transition. Halotolerant and alkali-resistant Aquibium and Mesorhizobium microcysteis belonging to N-ML possessed many tripartite ATP-independent periplasmic transporter and sodium/proton antiporter subunits composed of seven genes (mrpABCDEFG). These genes were not present in the N2-fixing Mesorhizobium lineage (ML), suggesting that genes acquired for adaptation to highly saline and alkaline environments were lost during the evolution of ML as the habitat changed to soil. Land-to-water habitat changes in Aquibium species, close relatives of Mesorhizobium species, could have influenced their genomic evolution by the gain and loss of genes. Our study indicated that lineage-specific evolution could have played a significant role in shaping their genome architecture and conferring their ability to thrive in different habitats.IMPORTANCEPhylogenetic analyses revealed that the Aquibium lineage (AL) and non-N2-fixing Mesorhizobium lineage (N-ML) were monophyletically grouped into distinct clusters separate from the N2-fixing Mesorhizobium lineage (ML). The N-ML, an evolutionary intermediate species having characteristics of both ancestral and descendant species, could provide a genomic snapshot of the genetic changes that occur during adaptation. Genomic analyses of AL, N-ML, and ML revealed that changes in the levels of genes related to transporters, chemotaxis, and nitrogen fixation likely reflect adaptations to different environmental conditions. Our study sheds light on the complex and dynamic nature of the evolution of rhizobia in response to changes in their environment and highlights the crucial role of genomic analysis in understanding these processes.},
}

@article {pmid38411865,
year = {2024},
author = {Seo, B and Jeon, K and Kim, WK and Jang, YJ and Cha, KH and Ko, G},
title = {Strain-Specific Anti-Inflammatory Effects of Faecalibacterium prausnitzii Strain KBL1027 in Koreans.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {38411865},
issn = {1867-1314},
support = {E0170600-07//Korea Food Research Institute/ ; RS-2023-00223831//National Research Foundation of Korea/ ; },
abstract = {Faecalibacterium prausnitzii is one of the most dominant commensal bacteria in the human gut, and certain anti-inflammatory functions have been attributed to a single microbial anti-inflammatory molecule (MAM). Simultaneously, substantial diversity among F. prausnitzii strains is acknowledged, emphasizing the need for strain-level functional studies aimed at developing innovative probiotics. Here, two distinct F. prausnitzii strains, KBL1026 and KBL1027, were isolated from Korean donors, exhibiting notable differences in the relative abundance of F. prausnitzii. Both strains were identified as the core Faecalibacterium amplicon sequence variant (ASV) within the healthy Korean cohort, and their MAM sequences showed a high similarity of 98.6%. However, when a single strain was introduced to mice with dextran sulfate sodium (DSS)-induced colitis, KBL1027 showed the most significant ameliorative effects, including alleviation of colonic inflammation and restoration of gut microbial dysbiosis. Moreover, the supernatant from KBL1027 elevated the secretion of IL-10 cytokine more than that of KBL1026 in mouse bone marrow-derived macrophage (BMDM) cells, suggesting that the strain-specific, anti-inflammatory efficacy of KBL1027 might involve effector compounds other than MAM. Through analysis of the Faecalibacterium pan-genome and comparative genomics, strain-specific functions related to extracellular polysaccharide biosynthesis were identified in KBL1027, which could contribute to the observed morphological disparities. Collectively, our findings highlight the strain-specific, anti-inflammatory functions of F. prausnitzii, even within the same core ASV, emphasizing the influence of their human origin.},
}

@article {pmid38410456,
year = {2024},
author = {Kogay, R and Wolf, YI and Koonin, EV},
title = {Defense systems and horizontal gene transfer in bacteria.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.02.09.579689},
pmid = {38410456},
abstract = {Horizontal gene transfer (HGT) is a fundamental process in the evolution of prokaryotes, making major contributions to diversification and adaptation. Typically, HGT is facilitated by mobile genetic elements (MGEs), such as conjugative plasmids and phages that generally impose fitness costs on their hosts. However, a substantial fraction of bacterial genes is involved in defense mechanisms that limit the propagation of MGEs, raising the possibility that they can actively restrict HGT. Here we examine whether defense systems curb HGT by exploring the connections between HGT rate and the presence of 73 defense systems in 12 bacterial species. We found that only 6 defense systems, 3 of which are different CRISPR-Cas subtypes, are associated with the reduced gene gain rate on the scale of species evolution. The hosts of such defense systems tend to have a smaller pangenome size and harbor fewer phage-related genes compared to genomes lacking these systems, suggesting that these defense mechanisms inhibit HGT by limiting the integration of prophages. We hypothesize that restriction of HGT by defense systems is species-specific and depends on various ecological and genetic factors, including the burden of MGEs and fitness effect of HGT in bacterial populations.},
}

@article {pmid38408562,
year = {2024},
author = {Huy, NQ and Linh, NC and Son, NT and Ngoc, DB and Tam, TTT and Hang, LTT and Thuyet, BT and Song, LH and Van Quyen, D and Hayer, J and Bañuls, AL and Sy, BT},
title = {Genomic insights into an extensively drug-resistant and hypervirulent Burkholderia dolosa N149 isolate of a novel sequence type (ST2237) from a Vietnamese patient hospitalized for stroke.},
journal = {Journal of global antimicrobial resistance},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jgar.2024.02.009},
pmid = {38408562},
issn = {2213-7173},
abstract = {OBJECTIVES: Burkholderia dolosa is a clinically important opportunistic pathogen in inpatients. Here we characterized an extensively drug-resistant and hypervirulent B. dolosa isolate from a patient hospitalized for stroke.

METHODS: Resistance to 41 antibiotics was tested with the agar disc diffusion, minimum inhibitory concentration, or broth microdilution method. The complete genome was assembled using short-reads and long-reads and the hybrid de novo assembly method. Allelic profiles obtained by multilocus sequence typing were analyzed using the PubMLST database. Antibiotic-resistance and virulence genes were predicted in silico using public databases and the "baargin" workflow. B. dolosa N149 phylogenetic relationships with all available B. dolosa strains and Burkholderia cepacia complex strains were analyzed using the pangenome obtained with Roary.

RESULTS: B. dolosa N149 displayed extensive resistance to 31 antibiotics and intermediate resistance to 4 antibiotics. The complete genome included three circular chromosomes (6,338,630 bp in total) and one plasmid (167,591 bp). Genotypic analysis revealed various gene clusters (acr, amr, amp, emr, ade, bla and tet) associated with resistance to 35 antibiotic classes. The major intrinsic resistance mechanisms were multidrug efflux pump alterations, inactivation and reduced permeability of targeted antibiotics. Moreover, 91 virulence genes (encoding proteins involved in adherence, formation of capsule, biofilm and colony, motility, phagocytosis inhibition, secretion systems, protease secretion, transmission and quorum sensing) were identified. B. dolosa N149 was assigned to a novel sequence type (ST2237) and formed a mono-phylogenetic clade separated from other B. dolosa strains.

CONCLUSION: This study provided insights into the antimicrobial resistance and virulence mechanisms of B. dolosa.},
}

@article {pmid38407244,
year = {2024},
author = {Selvaraj Anand, S and Wu, CT and Bremer, J and Bhatti, M and Treangen, TJ and Kalia, A and Shelburne, SA and Shropshire, WC},
title = {Identification of a novel CG307 sub-clade in third-generation-cephalosporin-resistant Klebsiella pneumoniae causing invasive infections in the USA.},
journal = {Microbial genomics},
volume = {10},
number = {2},
pages = {},
doi = {10.1099/mgen.0.001201},
pmid = {38407244},
issn = {2057-5858},
abstract = {Despite the notable clinical impact, recent molecular epidemiology regarding third-generation-cephalosporin-resistant (3GC-R) Klebsiella pneumoniae in the USA remains limited. We performed whole-genome sequencing of 3GC-R K. pneumoniae bacteraemia isolates collected from March 2016 to May 2022 at a tertiary care cancer centre in Houston, TX, USA, using Illumina and Oxford Nanopore Technologies platforms. A comprehensive comparative genomic analysis was performed to dissect population structure, transmission dynamics and pan-genomic signatures of our 3GC-R K. pneumoniae population. Of the 178 3GC-R K. pneumoniae bacteraemias that occurred during our study time frame, we were able to analyse 153 (86 %) bacteraemia isolates, 126 initial and 27 recurrent isolates. While isolates belonging to the widely prevalent clonal group (CG) 258 were rarely observed, the predominant CG, 307, accounted for 37 (29 %) index isolates and displayed a significant correlation (Pearson correlation test P value=0.03) with the annual frequency of 3GC-R K. pneumoniae bacteraemia. Interestingly, only 11 % (4/37) of CG307 isolates belonged to the commonly detected 'Texas-specific' clade that has been observed in previous Texas-based K. pneumoniae antimicrobial-resistance surveillance studies. We identified nearly half of our CG307 isolates (n=18) belonged to a novel, monophyletic CG307 sub-clade characterized by the chromosomally encoded bla SHV-205 and unique accessory genome content. This CG307 sub-clade was detected in various regions of the USA, with genome sequences from 24 additional strains becoming recently available in the National Center for Biotechnology Information (NCBI) SRA database. Collectively, this study underscores the emergence and dissemination of a distinct CG307 sub-clade that is a prevalent cause of 3GC-R K. pneumoniae bacteraemia among cancer patients seen in Houston, TX, and has recently been isolated throughout the USA.},
}

@article {pmid38402521,
year = {2024},
author = {van Westerhoven, AC and Aguilera-Galvez, C and Nakasato-Tagami, G and Shi-Kunne, X and Martinez de la Parte, E and Chavarro-Carrero, E and Meijer, HJG and Feurtey, A and Maryani, N and Ordóñez, N and Schneiders, H and Nijbroek, K and Wittenberg, AHJ and Hofstede, R and García-Bastidas, F and Sørensen, A and Swennen, R and Drenth, A and Stukenbrock, EH and Kema, GHJ and Seidl, MF},
title = {Segmental duplications drive the evolution of accessory regions in a major crop pathogen.},
journal = {The New phytologist},
volume = {},
number = {},
pages = {},
doi = {10.1111/nph.19604},
pmid = {38402521},
issn = {1469-8137},
support = {AG - 442//Bill and Melinda Gates Foundation/ ; 20 04 04 02//Stichting Dioraphte/ ; },
abstract = {Many pathogens evolved compartmentalized genomes with conserved core and variable accessory regions (ARs) that carry effector genes mediating virulence. The fungal plant pathogen Fusarium oxysporum has such ARs, often spanning entire chromosomes. The presence of specific ARs influences the host range, and horizontal transfer of ARs can modify the pathogenicity of the receiving strain. However, how these ARs evolve in strains that infect the same host remains largely unknown. We defined the pan-genome of 69 diverse F. oxysporum strains that cause Fusarium wilt of banana, a significant constraint to global banana production, and analyzed the diversity and evolution of the ARs. Accessory regions in F. oxysporum strains infecting the same banana cultivar are highly diverse, and we could not identify any shared genomic regions and in planta-induced effectors. We demonstrate that segmental duplications drive the evolution of ARs. Furthermore, we show that recent segmental duplications specifically in accessory chromosomes cause the expansion of ARs in F. oxysporum. Taken together, we conclude that extensive recent duplications drive the evolution of ARs in F. oxysporum, which contribute to the evolution of virulence.},
}

@article {pmid38399738,
year = {2024},
author = {Straková, D and Sánchez-Porro, C and de la Haba, RR and Ventosa, A},
title = {Decoding the Genomic Profile of the Halomicroarcula Genus: Comparative Analysis and Characterization of Two Novel Species.},
journal = {Microorganisms},
volume = {12},
number = {2},
pages = {},
pmid = {38399738},
issn = {2076-2607},
support = {PID2020-118136GB-I00//MCIN/AEI/10.13039/501100011033/ ; P20_01066 and BIO-213//Junta de Andalucía/ ; },
abstract = {The genus Halomicroarcula, classified within the family Haloarculaceae, presently comprises eight haloarchaeal species isolated from diverse saline habitats, such as solar salterns, hypersaline soils, marine salt, and marine algae. Here, a detailed taxogenomic study and comparative genomic analysis of the genus Halomicroarcula was carried out. In addition, two strains, designated S1CR25-12[T] and S3CR25-11[T], that were isolated from hypersaline soils located in the Odiel Saltmarshes in Huelva (Spain) were included in this study. The 16S rRNA and rpoB' gene sequence analyses affiliated the two strains to the genus Halomicroarcula. Typically, the species of the genus Halomicroarcula possess multiple heterogeneous copies of the 16S rRNA gene, which can lead to misclassification of the taxa and overestimation of the prokaryotic diversity. In contrast, the application of overall genome relatedness indexes (OGRIs) augments the capacity for the precise taxonomic classification and categorization of prokaryotic organisms. The relatedness indexes of the two new isolates, particularly digital DNA-DNA hybridization (dDDH), orthologous average nucleotide identity (OrthoANI), and average amino acid identity (AAI), confirmed that strains S1CR25-12[T] (= CECT 30620[T] = CCM 9252[T]) and S3CR25-11[T] (= CECT 30621[T] = CCM 9254[T]) constitute two novel species of the genus Halomicroarcula. The names Halomicroarcula saliterrae sp. nov. and Halomicroarcula onubensis sp. nov. are proposed for S1CR25-12[T] and S3CR25-11[T], respectively. Metagenomic fragment recruitment analysis, conducted using seven shotgun metagenomic datasets, revealed that the species belonging to the genus Halomicroarcula were predominantly recruited from hypersaline soils found in the Odiel Saltmarshes and the ponds of salterns with high salt concentrations. This reinforces the understanding of the extreme halophilic characteristics associated with the genus Halomicroarcula. Finally, comparing pan-genomes across the twenty Halomicroarcula and Haloarcula species allowed for the identification of commonalities and differences between the species of these two related genera.},
}

@article {pmid38399654,
year = {2024},
author = {Rhoads, DD and Pummill, J and Alrubaye, AAK},
title = {Molecular Genomic Analyses of Enterococcus cecorum from Sepsis Outbreaks in Broilers.},
journal = {Microorganisms},
volume = {12},
number = {2},
pages = {},
doi = {10.3390/microorganisms12020250},
pmid = {38399654},
issn = {2076-2607},
support = {none//Arkansas Biosciences Institute/ ; },
abstract = {Extensive genomic analyses of Enterococcus cecorum isolates from sepsis outbreaks in broilers suggest a polyphyletic origin, likely arising from core genome mutations rather than gene acquisition. This species is a normal intestinal flora of avian species with particular isolates associated with osteomyelitis. More recently, this species has been associated with sepsis outbreaks affecting broilers during the first 3 weeks post-hatch. Understanding the genetic and management basis of this new phenotype is critical for developing strategies to mitigate this emerging problem. Phylogenomic analyses of 227 genomes suggest that sepsis isolates are polyphyletic and closely related to both commensal and osteomyelitis isolate genomes. Pangenome analyses detect no gene acquisitions that distinguish all the sepsis isolates. Core genome single nucleotide polymorphism analyses have identified a number of mutations, affecting the protein-coding sequences, that are enriched in sepsis isolates. The analysis of the protein substitutions supports the mutational origins of sepsis isolates.},
}

@article {pmid38397433,
year = {2024},
author = {Nedashkovskaya, O and Balabanova, L and Otstavnykh, N and Zhukova, N and Detkova, E and Seitkalieva, A and Bystritskaya, E and Noskova, Y and Tekutyeva, L and Isaeva, M},
title = {In-Depth Genome Characterization and Pan-Genome Analysis of Strain KMM 296, a Producer of Highly Active Alkaline Phosphatase; Proposal for the Reclassification of Cobetia litoralis and Cobetia pacifica as the Later Heterotypic Synonyms of Cobetia amphilecti and Cobetia marina, and Emended Description of the Species Cobetia amphilecti and Cobetia marina.},
journal = {Biomolecules},
volume = {14},
number = {2},
pages = {},
doi = {10.3390/biom14020196},
pmid = {38397433},
issn = {2218-273X},
support = {15.BRK.21.0004 (contract no. 075-15-2021-1052)//the Ministry of Science and Higher Education, Russian Federation/ ; },
abstract = {A strictly aerobic, Gram-stain-negative, rod-shaped, and motile bacterium, designated strain KMM 296, isolated from the coelomic fluid of the mussel Crenomytilus grayanus, was investigated in detail due to its ability to produce a highly active alkaline phosphatase CmAP of the structural family PhoA. A previous taxonomic study allocated the strain to the species Cobetia marina, a member of the family Halomonadaceae of the class Gammaproteobacteria. However, 16S rRNA gene sequencing showed KMM 296's relatedness to Cobetia amphilecti NRIC 0815[T]. The isolate grew with 0.5-19% NaCl at 4-42 °C and hydrolyzed Tweens 20 and 40 and L-tyrosine. The DNA G+C content was 62.5 mol%. The prevalent fatty acids were C18:1 ω7c, C12:0 3-OH, C18:1 ω7c, C12:0, and C17:0 cyclo. The polar lipid profile was characterized by the presence of phosphatidylethanolamine, phosphatidylglycerol, phosphatidic acid, and also an unidentified aminolipid, phospholipid, and a few unidentified lipids. The major respiratory quinone was Q-8. According to phylogenomic and chemotaxonomic evidence, and the nearest neighbors, the strain KMM 296 represents a member of the species C. amphilecti. The genome-based analysis of C. amphilecti NRIC 0815[T] and C. litoralis NRIC 0814[T] showed their belonging to a single species. In addition, the high similarity between the C. pacifica NRIC 0813[T] and C. marina LMG 2217[T] genomes suggests their affiliation to one species. Based on the rules of priority, C. litoralis should be reclassified as a later heterotypic synonym of C. amphilecti, and C. pacifica is a later heterotypic synonym of C. marina. The emended descriptions of the species C. amphilecti and C. marina are also proposed.},
}

@article {pmid38396752,
year = {2024},
author = {Evseev, PV and Shneider, MM and Kolupaeva, LV and Kasimova, AA and Timoshina, OY and Perepelov, AV and Shpirt, AM and Shelenkov, AA and Mikhailova, YV and Suzina, NE and Knirel, YA and Miroshnikov, KA and Popova, AV},
title = {New Obolenskvirus Phages Brutus and Scipio: Biology, Evolution, and Phage-Host Interaction.},
journal = {International journal of molecular sciences},
volume = {25},
number = {4},
pages = {},
doi = {10.3390/ijms25042074},
pmid = {38396752},
issn = {1422-0067},
support = {20-75-10113//Russian Science Foundation/ ; },
abstract = {Two novel virulent phages of the genus Obolenskvirus infecting Acinetobacter baumannii, a significant nosocomial pathogen, have been isolated and studied. Phages Brutus and Scipio were able to infect A. baumannii strains belonging to the K116 and K82 capsular types, respectively. The biological properties and genomic organization of the phages were characterized. Comparative genomic, phylogenetic, and pangenomic analyses were performed to investigate the relationship of Brutus and Scipio to other bacterial viruses and to trace the possible origin and evolutionary history of these phages and other representatives of the genus Obolenskvirus. The investigation of enzymatic activity of the tailspike depolymerase encoded in the genome of phage Scipio, the first reported virus infecting A. baumannii of the K82 capsular type, was performed. The study of new representatives of the genus Obolenskvirus and mechanisms of action of depolymerases encoded in their genomes expands knowledge about the diversity of viruses within this taxonomic group and strategies of Obolenskvirus-host bacteria interaction.},
}

@article {pmid38396294,
year = {2024},
author = {Sepich-Poore, GD and McDonald, D and Kopylova, E and Guccione, C and Zhu, Q and Austin, G and Carpenter, C and Fraraccio, S and Wandro, S and Kosciolek, T and Janssen, S and Metcalf, JL and Song, SJ and Kanbar, J and Miller-Montgomery, S and Heaton, R and Mckay, R and Patel, SP and Swafford, AD and Korem, T and Knight, R},
title = {Robustness of cancer microbiome signals over a broad range of methodological variation.},
journal = {Oncogene},
volume = {},
number = {},
pages = {},
pmid = {38396294},
issn = {1476-5594},
support = {U24 CA248454/CA/NCI NIH HHS/United States ; },
abstract = {In 2020, we identified cancer-specific microbial signals in The Cancer Genome Atlas (TCGA) [1]. Multiple peer-reviewed papers independently verified or extended our findings [2-12]. Given this impact, we carefully considered concerns by Gihawi et al. [13] that batch correction and database contamination with host sequences artificially created the appearance of cancer type-specific microbiomes. (1) We tested batch correction by comparing raw and Voom-SNM-corrected data per-batch, finding predictive equivalence and significantly similar features. We found consistent results with a modern microbiome-specific method (ConQuR [14]), and when restricting to taxa found in an independent, highly-decontaminated cohort. (2) Using Conterminator [15], we found low levels of human contamination in our original databases (~1% of genomes). We demonstrated that the increased detection of human reads in Gihawi et al. [13] was due to using a newer human genome reference. (3) We developed Exhaustive, a method twice as sensitive as Conterminator, to clean RefSeq. We comprehensively host-deplete TCGA with many human (pan)genome references. We repeated all analyses with this and the Gihawi et al. [13] pipeline, and found cancer type-specific microbiomes. These extensive re-analyses and updated methods validate our original conclusion that cancer type-specific microbial signatures exist in TCGA, and show they are robust to methodology.},
}

@article {pmid38389535,
year = {2024},
author = {Patakova, P and Vasylkivska, M and Sedlar, K and Jureckova, K and Bezdicek, M and Lovecka, P and Branska, B and Kastanek, P and Krofta, K},
title = {Whole genome sequencing and characterization of Pantoea agglomerans DBM 3797, endophyte, isolated from fresh hop (Humulus lupulus L.).},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1305338},
pmid = {38389535},
issn = {1664-302X},
abstract = {BACKGROUND: This paper brings new information about the genome and phenotypic characteristics of Pantoea agglomerans strain DBM 3797, isolated from fresh Czech hop (Humulus lupulus) in the Saaz hop-growing region. Although P. agglomerans strains are frequently isolated from different materials, there are not usually thoroughly characterized even if they have versatile metabolism and those isolated from plants may have a considerable potential for application in agriculture as a support culture for plant growth.

METHODS: P. agglomerans DBM 3797 was cultured under aerobic and anaerobic conditions, its metabolites were analyzed by HPLC and it was tested for plant growth promotion abilities, such as phosphate solubilization, siderophore and indol-3-acetic acid productions. In addition, genomic DNA was extracted, sequenced and de novo assembly was performed. Further, genome annotation, pan-genome analysis and selected genome analyses, such as CRISPR arrays detection, antibiotic resistance and secondary metabolite genes identification were carried out.

RESULTS AND DISCUSSION: The typical appearance characteristics of the strain include the formation of symplasmata in submerged liquid culture and the formation of pale yellow colonies on agar. The genetic information of the strain (in total 4.8 Mb) is divided between a chromosome and two plasmids. The strain lacks any CRISPR-Cas system but is equipped with four restriction-modification systems. The phenotypic analysis focused on growth under both aerobic and anaerobic conditions, as well as traits associated with plant growth promotion. At both levels (genomic and phenotypic), the production of siderophores, indoleacetic acid-derived growth promoters, gluconic acid, and enzyme activities related to the degradation of complex organic compounds were found. Extracellular gluconic acid production under aerobic conditions (up to 8 g/l) is probably the result of glucose oxidation by the membrane-bound pyrroloquinoline quinone-dependent enzyme glucose dehydrogenase. The strain has a number of properties potentially beneficial to the hop plant and its closest relatives include the strains also isolated from the aerial parts of plants, yet its safety profile needs to be addressed in follow-up research.},
}

@article {pmid38389084,
year = {2024},
author = {Miao, J and Wei, X and Cao, C and Sun, J and Xu, Y and Zhang, Z and Wang, Q and Pan, Y and Wang, Z},
title = {Pig pangenome graph reveals functional features of non-reference sequences.},
journal = {Journal of animal science and biotechnology},
volume = {15},
number = {1},
pages = {32},
pmid = {38389084},
issn = {1674-9782},
support = {2022YFF1000500//National Key Research and Development Program of China/ ; 31941007//National Natural Science Foundation of China/ ; 2016C02054-2//Zhejiang province agriculture (livestock) varieties breeding Key Technology R&D Program/ ; },
abstract = {BACKGROUND: The reliance on a solitary linear reference genome has imposed a significant constraint on our comprehensive understanding of genetic variation in animals. This constraint is particularly pronounced for non-reference sequences (NRSs), which have not been extensively studied.

RESULTS: In this study, we constructed a pig pangenome graph using 21 pig assemblies and identified 23,831 NRSs with a total length of 105 Mb. Our findings revealed that NRSs were more prevalent in breeds exhibiting greater genetic divergence from the reference genome. Furthermore, we observed that NRSs were rarely found within coding sequences, while NRS insertions were enriched in immune-related Gene Ontology terms. Notably, our investigation also unveiled a close association between novel genes and the immune capacity of pigs. We observed substantial differences in terms of frequencies of NRSs between Eastern and Western pigs, and the heat-resistant pigs exhibited a substantial number of NRS insertions in an 11.6 Mb interval on chromosome X. Additionally, we discovered a 665 bp insertion in the fourth intron of the TNFRSF19 gene that may be associated with the ability of heat tolerance in Southern Chinese pigs.

CONCLUSIONS: Our findings demonstrate the potential of a graph genome approach to reveal important functional features of NRSs in pig populations.},
}

@article {pmid38388650,
year = {2024},
author = {Pena-Fernández, N and Ocejo, M and van der Graaf-van Bloois, L and Lavín, JL and Kortabarria, N and Collantes-Fernández, E and Hurtado, A and Aduriz, G},
title = {Comparative pangenomic analysis of Campylobacter fetus isolated from Spanish bulls and other mammalian species.},
journal = {Scientific reports},
volume = {14},
number = {1},
pages = {4347},
pmid = {38388650},
issn = {2045-2322},
support = {Pre2018-086113 funded by MCIN/AEI/ 10.13039/501100011033 and by "ESF Investing in your future"//Ministerio de Ciencia e Innovación/ ; },
abstract = {Campylobacter fetus comprises two closely related mammal-associated subspecies: Campylobacter fetus subsp. fetus (Cff) and Campylobacter fetus subsp. venerealis (Cfv). The latter causes bovine genital campylobacteriosis, a sexually-transmitted disease endemic in Spain that results in significant economic losses in the cattle industry. Here, 33 C. fetus Spanish isolates were whole-genome sequenced and compared with 62 publicly available C. fetus genomes from other countries. Genome-based taxonomic identification revealed high concordance with in silico PCR, confirming Spanish isolates as Cff (n = 4), Cfv (n = 9) and Cfv biovar intermedius (Cfvi, n = 20). MLST analysis assigned the Spanish isolates to 6 STs, including three novel: ST-76 and ST-77 for Cfv and ST-78 for Cff. Core genome SNP phylogenetic analysis of the 95 genomes identified multiple clusters, revealing associations at subspecies and biovar level between genomes with the same ST and separating the Cfvi genomes from Spain and other countries. A genome-wide association study identified pqqL as a Cfv-specific gene and a potential candidate for more accurate identification methods. Functionality analysis revealed variations in the accessory genome of C. fetus subspecies and biovars that deserve further studies. These results provide valuable information about the regional variants of C. fetus present in Spain and the genetic diversity and predicted functionality of the different subspecies.},
}

@article {pmid38385549,
year = {2024},
author = {Arizala, D and Arif, M},
title = {Impact of homologous recombination on core genome evolution and host adaptation of Pectobacterium parmentieri.},
journal = {Genome biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/gbe/evae032},
pmid = {38385549},
issn = {1759-6653},
abstract = {Homologous recombination is a major force mechanism driving bacterial evolution, host adaptability and acquisition of novel virulence traits. Pectobacterium parmentieri is a plant bacterial pathogen distributed worldwide, primarily affecting potatoes, by causing soft rot and blackleg diseases. The goal of this investigation was to understand the impact of homologous recombination on the genomic evolution of P. parmentieri. Analysis of P. parmentieri genomes using Roary revealed a dynamic pan-genome with 3,742 core genes and over 55% accessory genome variability. Bayesian population structure analysis identified seven lineages, indicating species heterogeneity. ClonalFrameML analysis displayed 5,125 recombination events, with the lineage 4 exhibiting the highest events. fastGEAR analysis identified 486 ancestral and 941 recent recombination events ranging 43 bp - 119 kb and 36 bp - 13.96 kb, respectively, suggesting ongoing adaptation. Notably, 11% (412 genes) of the core genome underwent recent recombination, with lineage 1 as the main donor. The prevalence of recent recombination (double compared to ancient) events implies continuous adaptation, possibly driven by global potato trade. Recombination events were found in genes involved in vital cellular processes (DNA replication, DNA repair, RNA processing, homeostasis, and metabolism), pathogenicity determinants (type secretion systems, cell-wall degrading enzymes, iron scavengers, lipopolysaccharides, flagellum, etc.), antimicrobial compounds (phenazine and colicin) and even CRISPR-Cas genes. Overall, these results emphasize the potential role of homologous recombination in P. parmentieri's evolutionary dynamics, influencing host colonization, pathogenicity, adaptive immunity, and ecological fitness.},
}

@article {pmid38385476,
year = {2024},
author = {Tariq, DE},
title = {Pangenomic analyses of tuberculosis strains to identify resistomes using computational approaches.},
journal = {JPMA. The Journal of the Pakistan Medical Association},
volume = {74},
number = {1 (Supple-2)},
pages = {S74-S78},
doi = {10.47391/JPMA-DUHS-S15},
pmid = {38385476},
issn = {0030-9982},
abstract = {OBJECTIVE: To locate resistomes in tuberculosis strains, to determine the severity of drug resistance, and to infer its implications with respect to high tuberculosis prevalence in a Third World setting.

METHODS: The pangenomic study was conducted from October 2022 to January 2023 in Sir Syed University of Engineering and Technology, Karachi, and comprised 2012-22 data on multiple sequence alignment to assess the genetic evolution of tuberculosis strains. Antibiotic resistance drug classes were identified using the Canadian Antibiotic Resistance Database, which entailed multidrug-resistant and extremely drug-resistant strains. Also, GenBank was used for tuberculosis genome FASTA (fast-all; nucleotide and protein sequence representation) files, prediction of resistome sequences on the basis of Canadian Antibiotic Resistance Database, and multiple sequence alignment was done in Mauve.

RESULTS: Evolutionarily, the 6 strains identified were structurally similar with polymorphisms in their core chromosomal regions. Their resistome genes showed perfect hits for isoniazid, rifamycin, cephalosporin, fluoroquinolone, aminoglycosides, penem, penam and cephamycin.

CONCLUSION: Drugs discovered in antibiotic resistance genes are now less effective in treatment, and have the potential to develop into more dangerous bacteria, if not monitored. For treatment, staying long durations in hospitals for quality healthcare and supervision in third world countries is unaffordable.},
}

@article {pmid38379925,
year = {2024},
author = {Turco, S and Russo, S and Pietrucci, D and Filippi, A and Milanesi, M and Luzzago, C and Garbarino, C and Palladini, G and Chillemi, G and Ricchi, M},
title = {High clonality of Mycobacterium avium subsp. paratuberculosis field isolates from red deer revealed by two different methodological approaches of comparative genomic analysis.},
journal = {Frontiers in veterinary science},
volume = {11},
number = {},
pages = {1301667},
pmid = {38379925},
issn = {2297-1769},
abstract = {Mycobacterium avium subsp. paratuberculosis (MAP) is the aetiological agent of paratuberculosis (Johne's disease) in both domestic and wild ruminants. In the present study, using a whole-genome sequence (WGS) approach, we investigated the genetic diversity of 15 Mycobacterium avium field strains isolated in the last 10 years from red deer inhabiting the Stelvio National Park and affected by paratuberculosis. Combining de novo assembly and a reference-based method, followed by a pangenome analysis, we highlight a very close relationship among 13 MAP field isolates, suggesting that a single infecting event occurred in this population. Moreover, two isolates have been classified as Mycobacterium avium subsp. hominissuis, distinct from the other MAPs under comparison but close to each other. This is the first time that this subspecies has been found in Italy in samples without evident epidemiological correlations, having been isolated in two different locations of the Stelvio National Park and in different years. Our study highlights the importance of a multidisciplinary approach incorporating molecular epidemiology and ecology into traditional infectious disease knowledge in order to investigate the nature of infectious disease in wildlife populations.},
}

@article {pmid38378816,
year = {2024},
author = {Schreiber, M and Jayakodi, M and Stein, N and Mascher, M},
title = {Plant pangenomes for crop improvement, biodiversity and evolution.},
journal = {Nature reviews. Genetics},
volume = {},
number = {},
pages = {},
pmid = {38378816},
issn = {1471-0064},
abstract = {Plant genome sequences catalogue genes and the genetic elements that regulate their expression. Such inventories further research aims as diverse as mapping the molecular basis of trait diversity in domesticated plants or inquiries into the origin of evolutionary innovations in flowering plants millions of years ago. The transformative technological progress of DNA sequencing in the past two decades has enabled researchers to sequence ever more genomes with greater ease. Pangenomes - complete sequences of multiple individuals of a species or higher taxonomic unit - have now entered the geneticists' toolkit. The genomes of crop plants and their wild relatives are being studied with translational applications in breeding in mind. But pangenomes are applicable also in ecological and evolutionary studies, as they help classify and monitor biodiversity across the tree of life, deepen our understanding of how plant species diverged and show how plants adapt to changing environments or new selection pressures exerted by human beings.},
}

@article {pmid38376942,
year = {2024},
author = {Truong, TC and Park, H and Kim, JH and Tran, VT and Kim, W},
title = {The evolutionary phylodynamics of human parechovirus A type 3 reveal multiple recombination events in South Korea.},
journal = {Journal of medical virology},
volume = {96},
number = {2},
pages = {e29477},
doi = {10.1002/jmv.29477},
pmid = {38376942},
issn = {1096-9071},
support = {NRF-2021R1C1C2003223//National Research Foundation of Korea/ ; NRF-2022R1A2C2012209//National Research Foundation of Korea/ ; },
abstract = {Human parechovirus A (HPeV-A) is a causative agent of respiratory and gastrointestinal illnesses, acute flaccid paralysis encephalitis, meningitis, and neonatal sepsis. To clarify the characteristics of HPeV-A infection in children, 391 fecal specimens were collected from January 2014 to October 2015 from patients with acute gastroenteritis in Seoul, South Korea. Of these, 221/391 (56.5%) HPeV-A positive samples were found in children less than 2 years old. Three HPeV-A genotypes HPeV-A1 (117/221; 52.94%), HPeV-A3 (100/221; 45.25%), and HPeV-A6 (4/221; 1.81%) were detected, among which HPeV-A3 was predominant with the highest recorded value of 58.6% in 2015. Moreover, recombination events in the Korean HPeV-A3 strains were detected. Phylogenetic analysis revealed that the capsid-encoding regions and noncapsid gene 2A of the four Korean HPeV-A3 strains are closely related to the HPeV-A3 strains isolated in Canada in 2007 (Can82853-01), Japan in 2008 (A308/99), and Taiwan in 2011 (TW-03067-2011) while noncapsid genes P2 (2B-2C) and P3 (3A-3D) are closely related to those of HPeV-A1 strains BNI-788St (Germany in 2008) and TW-71594-2010 (Taiwan in 2010). This first report on the whole-genome analysis of HPeV-A3 in Korea provides insight into the evolving status and pathogenesis of HPeVs in children.},
}

@article {pmid38376382,
year = {2024},
author = {Cooper, HB and Vezina, B and Hawkey, J and Passet, V and López-Fernández, S and Monk, JM and Brisse, S and Holt, KE and Wyres, KL},
title = {A validated pangenome-scale metabolic model for the Klebsiella pneumoniae species complex.},
journal = {Microbial genomics},
volume = {10},
number = {2},
pages = {},
doi = {10.1099/mgen.0.001206},
pmid = {38376382},
issn = {2057-5858},
abstract = {The Klebsiella pneumoniae species complex (KpSC) is a major source of nosocomial infections globally with high rates of resistance to antimicrobials. Consequently, there is growing interest in understanding virulence factors and their association with cellular metabolic processes for developing novel anti-KpSC therapeutics. Phenotypic assays have revealed metabolic diversity within the KpSC, but metabolism research has been neglected due to experiments being difficult and cost-intensive. Genome-scale metabolic models (GSMMs) represent a rapid and scalable in silico approach for exploring metabolic diversity, which compile genomic and biochemical data to reconstruct the metabolic network of an organism. Here we use a diverse collection of 507 KpSC isolates, including representatives of globally distributed clinically relevant lineages, to construct the most comprehensive KpSC pan-metabolic model to date, KpSC pan v2. Candidate metabolic reactions were identified using gene orthology to known metabolic genes, prior to manual curation via extensive literature and database searches. The final model comprised a total of 3550 reactions, 2403 genes and can simulate growth on 360 unique substrates. We used KpSC pan v2 as a reference to derive strain-specific GSMMs for all 507 KpSC isolates, and compared these to GSMMs generated using a prior KpSC pan-reference (KpSC pan v1) and two single-strain references. We show that KpSC pan v2 includes a greater proportion of accessory reactions (8.8 %) than KpSC pan v1 (2.5 %). GSMMs derived from KpSC pan v2 also generate more accurate growth predictions, with high median accuracies of 95.4 % (aerobic, n=37 isolates) and 78.8 % (anaerobic, n=36 isolates) for 124 matched carbon substrates. KpSC pan v2 is freely available at https://github.com/kelwyres/KpSC-pan-metabolic-model, representing a valuable resource for the scientific community, both as a source of curated metabolic information and as a reference to derive accurate strain-specific GSMMs. The latter can be used to investigate the relationship between KpSC metabolism and traits of interest, such as reservoirs, epidemiology, drug resistance or virulence, and ultimately to inform novel KpSC control strategies.},
}

@article {pmid38376357,
year = {2024},
author = {Benning, S and Pritsch, K and Radl, V and Siani, R and Wang, Z and Schloter, M},
title = {(Pan)genomic analysis of two Rhodococcus isolates and their role in phenolic compound degradation.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0378323},
doi = {10.1128/spectrum.03783-23},
pmid = {38376357},
issn = {2165-0497},
abstract = {The genus Rhodococcus is recognized for its potential to degrade a large range of aromatic substances, including plant-derived phenolic compounds. We used comparative genomics in the context of the broader Rhodococcus pan-genome to study genomic traits of two newly described Rhodococcus strains (type-strain Rhodococcus pseudokoreensis R79[T] and Rhodococcus koreensis R85) isolated from apple rhizosphere. Of particular interest was their ability to degrade phenolic compounds as part of an integrated approach to treat apple replant disease (ARD) syndrome. The pan-genome of the genus Rhodococcus based on 109 high-quality genomes was open with a small core (1.3%) consisting of genes assigned to basic cell functioning. The range of genome sizes in Rhodococcus was high, from 3.7 to 10.9 Mbp. Genomes from host-associated strains were generally smaller compared to environmental isolates which were characterized by exceptionally large genome sizes. Due to large genomic differences, we propose the reclassification of distinct groups of rhodococci like the Rhodococcus equi cluster to new genera. Taxonomic species affiliation was the most important factor in predicting genetic content and clustering of the genomes. Additionally, we found genes that discriminated between the strains based on habitat. All members of the genus Rhodococcus had at least one gene involved in the pathway for the degradation of benzoate, while biphenyl degradation was mainly restricted to strains in close phylogenetic relationships with our isolates. The ~40% of genes still unclassified in larger Rhodococcus genomes, particularly those of environmental isolates, need more research to explore the metabolic potential of this genus.IMPORTANCERhodococcus is a diverse, metabolically powerful genus, with high potential to adapt to different habitats due to the linear plasmids and large genome sizes. The analysis of its pan-genome allowed us to separate host-associated from environmental strains, supporting taxonomic reclassification. It was shown which genes contribute to the differentiation of the genomes based on habitat, which can possibly be used for targeted isolation and screening for desired traits. With respect to apple replant disease (ARD), our isolates showed genome traits that suggest potential for application in reducing plant-derived phenolic substances in soil, which makes them good candidates for further testing against ARD.},
}

@article {pmid38375235,
year = {2024},
author = {Lagerstrom, KM and Scales, NC and Hadly, EA},
title = {Impressive pan-genomic diversity of E. coli from a wild animal community near urban development reflects human impacts.},
journal = {iScience},
volume = {27},
number = {3},
pages = {109072},
pmid = {38375235},
issn = {2589-0042},
abstract = {Human and domesticated animal waste infiltrates global freshwater, terrestrial, and marine environments, widely disseminating fecal microbes, antibiotics, and other chemical pollutants. Emerging evidence suggests that guts of wild animals are being invaded by our microbes, including Escherichia coli, which face anthropogenic selective pressures to gain antimicrobial resistance (AMR) and increase virulence. However, wild animal sources remain starkly under-represented among genomic sequence repositories. We sequenced whole genomes of 145 E. coli isolates from 55 wild and 13 domestic animal fecal samples, averaging 2 (ranging 1-7) isolates per sample, on a preserve imbedded in a human-dominated landscape in California Bay Area, USA, to assess AMR, virulence, and pan-genomic diversity. With single nucleotide polymorphism analyses we predict potential transmission routes. We illustrate the usefulness of E. coli to aid our understanding of and ability to surveil the emergence of zoonotic pathogens created by the mixing of human and wild bacteria in the environment.},
}

@article {pmid38370750,
year = {2024},
author = {Bolognini, D and Halgren, A and Lou, RN and Raveane, A and Rocha, JL and Guarracino, A and Soranzo, N and Chin, J and Garrison, E and Sudmant, PH},
title = {Global diversity, recurrent evolution, and recent selection on amylase structural haplotypes in humans.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.02.07.579378},
pmid = {38370750},
abstract = {The adoption of agriculture, first documented ∼12,000 years ago in the Fertile Crescent, triggered a rapid shift toward starch-rich diets in human populations. Amylase genes facilitate starch digestion and increased salivary amylase copy number has been observed in some modern human populations with high starch intake, though evidence of recent selection is lacking. Here, using 52 long-read diploid assemblies and short read data from ∼5,600 contemporary and ancient humans, we resolve the diversity, evolutionary history, and selective impact of structural variation at the amylase locus. We find that both salivary and pancreatic amylase genes have higher copy numbers in populations with agricultural subsistence compared to fishing, hunting, and pastoral groups. We identify 28 distinct amylase structural architectures and demonstrate that identical structures have arisen independently multiple times throughout recent human history. Using a pangenome graph-based approach to infer structural haplotypes across thousands of humans, we identify extensively duplicated haplotypes present at higher frequencies in modern agricultural populations. Leveraging 534 ancient human genomes we find that duplication-containing haplotypes have increased in frequency more than seven-fold over the last 12,000 years providing evidence for recent selection in Eurasians at this locus comparable in magnitude to that at lactase. Together, our study highlights the strong impact of the agricultural revolution on human genomes and the importance of long-read sequencing in identifying signatures of selection at structurally complex loci.},
}

@article {pmid38370713,
year = {2024},
author = {Lypaczewski, P and Chac, D and Dunmire, CN and Tandoc, KM and Chowdhury, F and Khan, AI and Bhuiyan, T and Harris, JB and LaRocque, RC and Calderwood, SB and Ryan, ET and Qadri, F and Shapiro, BJ and Weil, AA},
title = {Diversity of Vibrio cholerae O1 through the human gastrointestinal tract during cholera.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.02.08.579476},
pmid = {38370713},
abstract = {UNLABELLED: Vibrio cholerae O1 causes the diarrheal disease cholera, and the small intestine is the site of active infection. During cholera, cholera toxin is secreted from V. cholerae and induces a massive fluid influx into the small intestine, which causes vomiting and diarrhea. Typically, V. cholerae genomes are sequenced from bacteria passed in stool, but rarely from vomit, a fluid that may more closely represents the site of active infection. We hypothesized that the V. cholerae O1 population bottlenecks along the gastrointestinal tract would result in reduced genetic variation in stool compared to vomit. To test this, we sequenced V. cholerae genomes from ten cholera patients with paired vomit and stool samples. Genetic diversity was low in both vomit and stool, consistent with a single infecting population rather than co-infection with divergent V. cholerae O1 lineages. The number of single nucleotide variants decreased between vomit and stool in four patients, increased in two, and remained unchanged in four. The number of genes encoded in the V. cholerae genome decreased between vomit and stool in eight patients and increased in two. Pangenome analysis of assembled short-read sequencing demonstrated that the toxin-coregulated pilus operon more frequently contained deletions in genomes from vomit compared to stool. However, these deletions were not detected by PCR or long-read sequencing, indicating that interpreting gene presence or absence patterns from short-read data alone may be incomplete. Overall, we found that V. cholerae O1 isolated from stool is genetically similar to V. cholerae recovered from the upper intestinal tract.

IMPORTANCE: Vibrio cholerae O1, the bacterium that causes cholera, is ingested in contaminated food or water and then colonizes the upper small intestine and is excreted in stool. Shed V. cholerae genomes are usually studied, but V. cholerae isolated from vomit may be more representative of where V. cholerae colonizes in the upper intestinal epithelium. V. cholerae may experience bottlenecks, or large reductions in bacterial population sizes or genetic diversity, as it passes through the gut. Passage through the gut may select for distinct V. cholerae mutants that are adapted for survival and gut colonization. We did not find strong evidence for such adaptive mutations, and instead observed that passage through the gut results in modest reductions in V. cholerae genetic diversity, and only in some patients. These results fill a gap in our understanding of the V. cholerae life cycle, transmission, and evolution.},
}

@article {pmid38370577,
year = {2023},
author = {Yuan, C and An, T and Li, X and Zou, J and Lin, Z and Gu, J and Hu, R and Fang, Z},
title = {Genomic analysis of Ralstonia pickettii reveals the genetic features for potential pathogenicity and adaptive evolution in drinking water.},
journal = {Frontiers in microbiology},
volume = {14},
number = {},
pages = {1272636},
pmid = {38370577},
issn = {1664-302X},
abstract = {Ralstonia pickettii, the most critical clinical pathogen of the genus Ralstonia, has been identified as a causative agent of numerous harmful infections. Additionally, Ralstonia pickettii demonstrates adaptability to extreme environmental conditions, such as those found in drinking water. In this study, we conducted a comprehensive genomic analysis to investigate the genomic characteristics related to potential pathogenicity and adaptive evolution in drinking water environments of Ralstonia pickettii. Through phylogenetic analysis and population genetic analysis, we divided Ralstonia pickettii into five Groups, two of which were associated with drinking water environments. The open pan-genome with a large and flexible gene repertoire indicated a high genetic plasticity. Significant differences in functional enrichment were observed between the core- and pan-genome of different groups. Diverse mobile genetic elements (MGEs), extensive genomic rearrangements, and horizontal gene transfer (HGT) events played a crucial role in generating genetic diversity. In drinking water environments, Ralstonia pickettii exhibited strong adaptability, and the acquisition of specific adaptive genes was potentially facilitated by genomic islands (GIs) and HGT. Furthermore, environmental pressures drove the adaptive evolution of Ralstonia pickettii, leading to the accumulation of unique mutations in key genes. These mutations may have a significant impact on various physiological functions, particularly carbon metabolism and energy metabolism. The presence of virulence-related elements associated with macromolecular secretion systems, virulence factors, and antimicrobial resistance indicated the potential pathogenicity of Ralstonia pickettii, making it capable of causing multiple nosocomial infections. This study provides comprehensive insights into the potential pathogenicity and adaptive evolution of Ralstonia pickettii in drinking water environments from a genomic perspective.},
}

@article {pmid38365240,
year = {2024},
author = {Shen, L and Liu, Y and Chen, L and Lei, T and Ren, P and Ji, M and Song, W and Lin, H and Su, W and Wang, S and Rooman, M and Pucci, F},
title = {Genomic basis of environmental adaptation in the widespread poly-extremophilic Exiguobacterium group.},
journal = {The ISME journal},
volume = {18},
number = {1},
pages = {},
doi = {10.1093/ismejo/wrad020},
pmid = {38365240},
issn = {1751-7370},
support = {U21A20176//National Natural Science Foundation of China/ ; 2019QZKK0503//Second Tibetan Plateau Scientific Expedition and Research/ ; 92251304//National Natural Science Foundation of China/ ; swzy202008//Open Project Fund of Anhui Provincial Key Laboratory of Protection and Utilization of Important Biological Resources/ ; 2022AH010012//Anhui Provincial Engineering Research Centre for Molecular Detection and Diagnostics/ ; },
abstract = {Delineating cohesive ecological units and determining the genetic basis for their environmental adaptation are among the most important objectives in microbiology. In the last decade, many studies have been devoted to characterizing the genetic diversity in microbial populations to address these issues. However, the impact of extreme environmental conditions, such as temperature and salinity, on microbial ecology and evolution remains unclear so far. In order to better understand the mechanisms of adaptation, we studied the (pan)genome of Exiguobacterium, a poly-extremophile bacterium able to grow in a wide range of environments, from permafrost to hot springs. To have the genome for all known Exiguobacterium type strains, we first sequenced those that were not yet available. Using a reverse-ecology approach, we showed how the integration of phylogenomic information, genomic features, gene and pathway enrichment data, regulatory element analyses, protein amino acid composition, and protein structure analyses of the entire Exiguobacterium pangenome allows to sharply delineate ecological units consisting of mesophilic, psychrophilic, halophilic-mesophilic, and halophilic-thermophilic ecotypes. This in-depth study clarified the genetic basis of the defined ecotypes and identified some key mechanisms driving the environmental adaptation to extreme environments. Our study points the way to organizing the vast microbial diversity into meaningful ecologically units, which, in turn, provides insight into how microbial communities adapt and respond to different environmental conditions in a changing world.},
}