@article {pmid39261641,
year = {2024},
author = {Sirén, J and Eskandar, P and Ungaro, MT and Hickey, G and Eizenga, JM and Novak, AM and Chang, X and Chang, PC and Kolmogorov, M and Carroll, A and Monlong, J and Paten, B},
title = {Personalized pangenome references.},
journal = {Nature methods},
volume = {},
number = {},
pages = {},
pmid = {39261641},
issn = {1548-7105},
support = {R01HG010485//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; U24HG010262//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; U24HG011853//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; U01HG010961//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; OT2OD033761//U.S. Department of Health & Human Services | National Institutes of Health (NIH)/ ; OT3HL142481//U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI)/ ; },
abstract = {Pangenomes reduce reference bias by representing genetic diversity better than a single reference sequence. Yet when comparing a sample to a pangenome, variants in the pangenome that are not part of the sample can be misleading, for example, causing false read mappings. These irrelevant variants are generally rarer in terms of allele frequency, and have previously been dealt with by filtering rare variants. However, this blunt heuristic both fails to remove some irrelevant variants and removes many relevant variants. We propose a new approach that imputes a personalized pangenome subgraph by sampling local haplotypes according to k-mer counts in the reads. We implement the approach in the vg toolkit (https://github.com/vgteam/vg) for the Giraffe short-read aligner and compare its accuracy to state-of-the-art methods using human pangenome graphs from the Human Pangenome Reference Consortium. This reduces small variant genotyping errors by four times relative to the Genome Analysis Toolkit and makes short-read structural variant genotyping of known variants competitive with long-read variant discovery methods.},
}

@article {pmid39259908,
year = {2024},
author = {Thorgersen, MP and Goff, JL and Trotter, VV and Poole, FL and Arkin, AP and Deutschbauer, AM and Adams, MWW},
title = {Fitness factors impacting survival of a subsurface bacterium in contaminated groundwater.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wrae176},
pmid = {39259908},
issn = {1751-7370},
abstract = {Many factors contribute to the ability of a microbial species to persist when encountering complexly contaminated environments including time of exposure, the nature and concentration of contaminants, availability of nutritional resources, and possession of a combination of appropriate molecular mechanisms needed for survival. Herein we sought to identify genes that are most important for survival of Gram-negative Enterobacteriaceae in contaminated groundwater environments containing high concentrations of nitrate and metals using the metal-tolerant Oak Ridge Reservation (ORR) isolate, Pantoea sp. MT58 (MT58). Survival fitness experiments in which a randomly barcoded transposon insertion (RB-TnSeq) library of MT58 was exposed directly to contaminated ORR groundwater samples from across a nitrate and mixed metal contamination plume were used to identify genes important for survival with increasing exposure times and concentrations of contaminants, and availability of a carbon source. Genes involved in controlling and using carbon, encoding transcriptional regulators, and related to Gram-negative outer membrane processes were among those found to be important for survival in contaminated ORR groundwater. A comparative genomics analysis of 75 Pantoea genus strains allowed us to further separate the survival determinants into core and non-core genes in the Pantoea pangenome, revealing insights into the survival of subsurface microorganisms during contaminant plume intrusion.},
}

@article {pmid39257004,
year = {2024},
author = {Liu, Z and Yang, F and Wan, H and Deng, C and Hu, W and Fan, X and Wang, J and Yang, M and Feng, J and Wang, Q and Yang, N and Cai, L and Liu, Y and Tang, H and Li, S and Luo, J and Zheng, J and Wu, L and Yang, E and Pu, Z and Jia, J and Li, J and Yang, W},
title = {Genome architecture of the allotetraploid wild grass Aegilops ventricosa reveals its evolutionary history and contributions to wheat improvement.},
journal = {Plant communications},
volume = {},
number = {},
pages = {101131},
doi = {10.1016/j.xplc.2024.101131},
pmid = {39257004},
issn = {2590-3462},
abstract = {The allotetraploid wild grass Aegilops ventricosa (2n=4X=28, genome D[v]D[v]N[v]N[v]) has been recognized as an important germplasm resource for wheat improvement due to its ability to tolerate biotic stresses. Especially 2N[v]S segment from Aegilops ventricosa, as a stable and effective resistance source, has greatly contributed to wheat improvement. The 2N[v]S/2AS translocation is a prevalent chromosomal translocation between common wheat and wild relatives, ranking just behind the 1B/1R translocation in importance for modern wheat breeding. Here, we assembled a high-quality chromosome-level reference genome of Ae. ventricosa RM271 with a total length of 8.67 Gb. Phylogenomic analyses revealed that the progenitor of the D[v] subgenome of Ae. ventricosa was Ae. tauschii ssp. tauschii (genome DD); in contrast, the progenitor of the D subgenome of bread wheat (Triticum aestivum L.) was Ae. tauschii ssp. strangulata (genome DD). The oldest polyploidization time of Ae. ventricosa occurred ∼0.7 million years ago. The D[v] subgenome of Ae. ventricosa was less conserved than the D subgenome of bread wheat. Construction of a graph-based pangenome of 2AS/6N[v]L (originally known as 2N[v]S) segments from Ae. ventricosa and other genomes in the Triticeae enables us identifying candidate resistance genes sourced from Ae. ventricosa. We identified 12 nonredundant introgressed segments from the D[v] and N[v] subgenomes using a large winter wheat collection representing the full diversity of the wheat European genetic pool, and 29.40% of European wheat varieties inherited at least one of these segments. The high-quality RM271 reference genome will provide a basis for cloning key genes, including the Yr17-Lr37-Sr38-Cre5 resistance gene cluster in Ae. ventricosa, and facilitate the full use of elite wild genetic resources to accelerate wheat improvement.},
}

@article {pmid39256695,
year = {2024},
author = {Li, X and Huo, L and Li, X and Zhang, C and Gu, M and Fan, J and Xu, C and Gong, J and Hu, X and Zheng, Y and Sun, X},
title = {Genomes of diverse Actinidia species provide insights into cis-regulatory motifs and genes associated with critical traits.},
journal = {BMC biology},
volume = {22},
number = {1},
pages = {200},
pmid = {39256695},
issn = {1741-7007},
support = {LR23C150001//Zhejiang Provincial Natural Science Foundation of China/ ; },
abstract = {BACKGROUND: Kiwifruit, belonging to the genus Actinidia, represents a unique fruit crop characterized by its modern cultivars being genetically diverse and exhibiting remarkable variations in morphological traits and adaptability to harsh environments. However, the genetic mechanisms underlying such morphological diversity remain largely elusive.

RESULTS: We report the high-quality genomes of five Actinidia species, including Actinidia longicarpa, A. macrosperma, A. polygama, A. reticulata, and A. rufa. Through comparative genomics analyses, we identified three whole genome duplication events shared by the Actinidia genus and uncovered rapidly evolving gene families implicated in the development of characteristic kiwifruit traits, including vitamin C (VC) content and fruit hairiness. A range of structural variations were identified, potentially contributing to the phenotypic diversity in kiwifruit. Notably, phylogenomic analyses revealed 76 cis-regulatory elements within the Actinidia genus, predominantly associated with stress responses, metabolic processes, and development. Among these, five motifs did not exhibit similarity to known plant motifs, suggesting the presence of possible novel cis-regulatory elements in kiwifruit. Construction of a pan-genome encompassing the nine Actinidia species facilitated the identification of gene DTZ79_23g14810 specific to species exhibiting extraordinarily high VC content. Expression of DTZ79_23g14810 is significantly correlated with the dynamics of VC concentration, and its overexpression in the transgenic roots of kiwifruit plants resulted in increased VC content.

CONCLUSIONS: Collectively, the genomes and pan-genome of diverse Actinidia species not only enhance our understanding of fruit development but also provide a valuable genomic resource for facilitating the genome-based breeding of kiwifruit.},
}

@article {pmid39253572,
year = {2024},
author = {Duan, S and Yan, L and Shen, Z and Li, X and Chen, B and Li, D and Qin, H and Meegahakumbura, MK and Wambulwa, MC and Gao, L and Chen, W and Dong, Y and Sheng, J},
title = {Genomic analyses of agronomic traits in tea plants and related Camellia species.},
journal = {Frontiers in plant science},
volume = {15},
number = {},
pages = {1449006},
doi = {10.3389/fpls.2024.1449006},
pmid = {39253572},
issn = {1664-462X},
abstract = {The genus Camellia contains three types of domesticates that meet various needs of ancient humans: the ornamental C. japonica, the edible oil-producing C. oleifera, and the beverage-purposed tea plant C. sinensis. The genomic drivers of the functional diversification of Camellia domesticates remain unknown. Here, we present the genomic variations of 625 Camellia accessions based on a new genome assembly of C. sinensis var. assamica ('YK10'), which consists of 15 pseudo-chromosomes with a total length of 3.35 Gb and a contig N50 of 816,948 bp. These accessions were mainly distributed in East Asia, South Asia, Southeast Asia, and Africa. We profiled the population and subpopulation structure in tea tree Camellia to find new evidence for the parallel domestication of C. sinensis var. assamica (CSA) and C. sinensis var. sinensis (CSS). We also identified candidate genes associated with traits differentiating CSA, CSS, oilseed Camellia, and ornamental Camellia cultivars. Our results provide a unique global view of the genetic diversification of Camellia domesticates and provide valuable resources for ongoing functional and molecular breeding research.},
}

@article {pmid39252931,
year = {2024},
author = {Stanley, S and Silva-Costa, C and Gomes-Silva, J and Melo-Cristino, J and Malley, R and Ramirez, M},
title = {CC180 clade dynamics does not universally explain Streptococcus pneumoniae serotype 3 persistence post-vaccine: a global comparative population genomics study.},
journal = {medRxiv : the preprint server for health sciences},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.08.29.24312665},
pmid = {39252931},
abstract = {BACKGROUND: Clonal complex 180 (CC180) is currently the major clone of serotype 3 Streptococcus pneumoniae (Spn). The 13-valent pneumococcal conjugate vaccine (PCV13) does not have significant efficacy against serotype 3 despite polysaccharide inclusion in the vaccine. It was hypothesized that PCV13 may effectively control Clade I of CC180 but that Clades III and IV are resistant, provoking a population shift that enables serotype 3 persistence. This has been observed in the United States, England, and Wales but not Spain. We tested this hypothesis further utilizing a dataset from Portugal.

METHODS: We whole-genome sequenced (WGS) 501 serotype 3 strains from Portugal isolated from patients with pneumococcal infections between 1999-2020. The draft genomes underwent phylogenetic analyses, pangenome profiling, and a genome-wide association study (GWAS). We also completed antibiotic susceptibility testing and compiled over 2,600 serotype 3 multilocus sequence type 180 (MLST180) WGSs to perform global comparative genomics.

FINDINGS: CC180 Clades I, II, III, IV, and VI distributions were similar when comparing non-invasive pneumonia isolates and invasive disease isolates (Fisher's exact test, P=0.29), and adult and pediatric cases (Fisher's exact test, P=0.074). The serotype 3 CCs shifted post-PCV13 (Fisher's exact test, P<0.0001) and Clade I became dominant. Clade I is largely antibiotic-sensitive and carries the ΦOXC141 prophage but the pangenome is heterogenous. Strains from Portugal and Spain, where Clade I remains dominant post-PCV13, have larger pangenomes and are associated with the presence of two genes encoding hypothetical proteins.

INTERPRETATION: Clade I became dominant in Portugal post-PCV13, despite the burden of the prophage and antibiotic sensitivity. The accessory genome content may mitigate these fitness costs. Regional differences in Clade I prevalence and pangenome heterogeneity suggest that clade dynamics is not a generalizable approach to understanding serotype 3 vaccine escape.

FUNDING: National Institute of Child Health and Human Development, Pfizer, and Merck Sharp & Dohme.

RESEARCH IN CONTEXT: Evidence before this study: We conducted this study because of the mounting interest surrounding the changing prevalence of serotype 3 Streptococcus pneumoniae (Spn) genetic lineages and the potential association with escape from 13-valent pneumococcal conjugate vaccine (PCV13) control. To inform our investigation, we searched the PubMed database using different combinations of the following keywords: "Streptococcus pneumoniae", "serotype 3", "CC180", "PCV13", "Clade Iα", "Clade Iβ", and "Clade II". The search included all English language primary research articles published before July 1 [st] , 2024; this language limitation may bias the results of our assessment. Most ST3 isolates belong to clonal complex 180 (CC180), and one study identified three major lineages within CC180: Clade Iα, Clade Iβ, and Clade II. This study observed a global trend of increasing Clade II prevalence with a concomitant decrease in Clade I prevalence over time, which was associated with the introduction of PCV13 in the United States. A report from England and Wales made a similar observation. It was therefore hypothesized that PCV13 may be effective at controlling Clade Iα and that Clade II is driving vaccine escape. Later work refined the clade classification system as follows: Clade I (Clade Iα), Clades II and VI (Clade Iβ), Clades III and IV (Clade II), and Clade V. Clade I strains are marked by a significantly lower recombination rate partly due to the presence of a lineage-specific prophage interfering with competence development, which is a potential mechanism explaining the possible reduced fitness of Clade I. Clade I is also noted to be mostly antibiotic-susceptible. However, a recent study found that Clade I persists as a dominant serotype 3 lineage in Spain, so the generalizability and implications of clade dynamics remain unclear. Added value of this study: Early work assessing the association between changes in serotype 3 clade prevalence and PCV13 was limited by small sample sizes. In addition, studies investigating differences in clade dynamics did not comprehensively consider patient age or disease manifestations such as non-invasive pneumonia and invasive infections. In this study, we evaluated 501 serotype 3 strains from Portugal to investigate clade dynamics. This must be explored in different geographic contexts for a more robust understanding of changing serotype 3 population genomics. We also sought to define genetic determinants linked to strains from regions in which Clade I remains dominant. This is an important step towards a more mechanistic understanding of the serotype 3 CC180 lineage fitness landscape.Implications of all the available evidence: Unlike other serotypes covered by PCV13, serotype 3 has evaded vaccine control. It has been suggested that Clade I prevalence has decreased due to PCV13, which has created an expanded niche for strains from other clades and ultimately renders PCV13 less effective against serotype 3. This postulation has important implications for the future design of an improved vaccine, so this hypothesis must be thoroughly tested in diverse contexts. We find that Clade I remains the dominant lineage in Portugal even after the introduction of PCV13. We delineate Clade I pangenome heterogeneity and show that strains from Portugal and Spain share similar pangenome features in contrast to Clade I strains from regions where Clade I decreased in prevalence, which should motivate future studies to elucidate more generalizable population genomics trends that may better inform strategies for the design of an improved vaccine.},
}

@article {pmid39251928,
year = {2024},
author = {Zorigt, T and Furuta, Y and Paudel, A and Kamboyi, HK and Shawa, M and Chuluun, M and Sugawara, M and Enkhtsetseg, N and Enkhtuya, J and Battsetseg, B and Munyeme, M and Hang'ombe, BM and Higashi, H},
title = {Pan-genome analysis reveals novel chromosomal markers for multiplex PCR-based specific detection of Bacillus anthracis.},
journal = {BMC infectious diseases},
volume = {24},
number = {1},
pages = {942},
pmid = {39251928},
issn = {1471-2334},
support = {23K19460//Japan Society for the Promotion of Science (JSPS) under Grants-in-Aid for Scientific Research (KAKENHI)/ ; 21K15430//Japan Society for the Promotion of Science (JSPS) under Grants-in-Aid for Scientific Research (KAKENHI)/ ; 18K19436//Japan Society for the Promotion of Science (JSPS) under Grants-in-Aid for Scientific Research (KAKENHI)/ ; JP23wm0125008//The Japan Program for Infectious Diseases Research and Infrastructure (JIDRI) from the Japan Agency for Medical Research and Development (AMED)/ ; },
abstract = {BACKGROUND: Bacillus anthracis is a highly pathogenic bacterium that can cause lethal infection in animals and humans, making it a significant concern as a pathogen and biological agent. Consequently, accurate diagnosis of B. anthracis is critically important for public health. However, the identification of specific marker genes encoded in the B. anthracis chromosome is challenging due to the genetic similarity it shares with B. cereus and B. thuringiensis.

METHODS: The complete genomes of B. anthracis, B. cereus, B. thuringiensis, and B. weihenstephanensis were de novo annotated with Prokka, and these annotations were used by Roary to produce the pan-genome. B. anthracis exclusive genes were identified by Perl script, and their specificity was examined by nucleotide BLAST search. A local BLAST alignment was performed to confirm the presence of the identified genes across various B. anthracis strains. Multiplex polymerase chain reactions (PCR) were established based on the identified genes.

RESULT: The distribution of genes among 151 whole-genome sequences exhibited three distinct major patterns, depending on the bacterial species and strains. Further comparative analysis between the three groups uncovered thirty chromosome-encoded genes exclusively present in B. anthracis strains. Of these, twenty were found in known lambda prophage regions, and ten were in previously undefined region of the chromosome. We established three distinct multiplex PCRs for the specific detection of B. anthracis by utilizing three of the identified genes, BA1698, BA5354, and BA5361.

CONCLUSION: The study identified thirty chromosome-encoded genes specific to B. anthracis, encompassing previously described genes in known lambda prophage regions and nine newly discovered genes from an undefined gene region to the best of our knowledge. Three multiplex PCR assays offer an accurate and reliable alternative method for detecting B. anthracis. Furthermore, these genetic markers have value in anthrax vaccine development, and understanding the pathogenicity of B. anthracis.},
}

@article {pmid39251347,
year = {2024},
author = {Ou, S and Scheben, A and Collins, T and Qiu, Y and Seetharam, AS and Menard, CC and Manchanda, N and Gent, JI and Schatz, MC and Anderson, SN and Hufford, MB and Hirsch, CN},
title = {Differences in activity and stability drive transposable element variation in tropical and temperate maize.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.278131.123},
pmid = {39251347},
issn = {1549-5469},
abstract = {Much of the profound interspecific variation in genome content has been attributed to transposable elements (TEs). To explore the extent of TE variation within species, we developed an optimized open-source algorithm, panEDTA, to de novo annotate TEs in a pangenome context. We then generated a unified TE annotation for a maize pangenome derived from 26 reference-quality genomes, which reveals an excess of 35.1 Mb of TE sequences per genome in tropical maize relative to temperate maize. A small number (n = 216) of TE families, mainly LTR retrotransposons, drive these differences. Evidence from the methylome, transcriptome, LTR age distribution, and LTR insertional polymorphisms reveals that 64.7% of the variability is contributed by LTR families that are young, less methylated, and more expressed in tropical maize, whereas 18.5% is driven by LTR families with removal or loss in temperate maize. Additionally, we find enrichment for Young LTR families adjacent to nucleotide-binding and leucine-rich repeat (NLR) clusters of varying copy number across lines, suggesting TE activity may be associated with disease resistance in maize.},
}

@article {pmid39251346,
year = {2024},
author = {Hung, TK and Liu, WC and Lai, SK and Chuang, HW and Lee, YC and Lin, HY and Hsu, CL and Chen, CY and Yang, YC and Hsu, JS and Chen, PL},
title = {Genetic complexity of killer-cell immunoglobulin-like receptor genes in human pangenome assemblies.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.278358.123},
pmid = {39251346},
issn = {1549-5469},
abstract = {The killer-cell immunoglobulin-like receptor (KIR) gene complex, a highly polymorphic region of the human genome that encodes proteins involved in immune responses, poses strong challenges in genotyping owing to its remarkable genetic diversity and structural intricacy. Accurate analysis of KIR alleles, including their structural variations, is crucial for understanding their roles in various immune responses. Leveraging the high-quality genome assemblies from the Human Pangenome Reference Consortium (HPRC), we present a novel bioinformatic tool, the structural KIR annoTator (SKIRT), to investigate gene diversity and facilitate precise KIR allele analysis. In 47 HPRC-phased assemblies, SKIRT identifies a recurrent novel KIR2DS4/3DL1 fusion gene in the paternal haplotype of HG02630 and maternal haplotype of NA19240. Additionally, SKIRT accurately identifies eight structural variants and 15 novel nonsynonymous alleles, all of which are independently validated using short-read data or quantitative polymerase chain reaction. Our study has discovered a total of 570 novel alleles, among which eight haplotypes harbor at least one KIR gene duplication, six haplotypes have lost at least one framework gene, and 75 out of 94 haplotypes (79.8%) carry at least five novel alleles, thus confirming KIR genetic diversity. These findings are pivotal in providing insights into KIR gene diversity and serve as a solid foundation for understanding the functional consequences of KIR structural variations. High-resolution genome assemblies offer unprecedented opportunities to explore polymorphic regions that are challenging to investigate using short-read sequencing methods. The SKIRT pipeline emerges as a highly efficient tool, enabling the comprehensive detection of the complete spectrum of KIR alleles within human genome assemblies.},
}

@article {pmid39245770,
year = {2024},
author = {Kenneally, C and Murphy, CP and Sleator, RD and Culligan, EP},
title = {Genotypic and phenotypic characterisation of asymptomatic bacteriuria (ABU) isolates displaying bacterial interference against multi-drug resistant uropathogenic E. Coli.},
journal = {Archives of microbiology},
volume = {206},
number = {10},
pages = {394},
pmid = {39245770},
issn = {1432-072X},
mesh = {Humans ; *Bacteriuria/microbiology ; *Uropathogenic Escherichia coli/genetics/drug effects/isolation & purification/classification ; *Escherichia coli Infections/microbiology ; *Drug Resistance, Multiple, Bacterial/genetics ; *Genotype ; *Phenotype ; *Urinary Tract Infections/microbiology ; *Anti-Bacterial Agents/pharmacology ; Virulence/genetics ; Phylogeny ; Adult ; Virulence Factors/genetics ; Genome, Bacterial ; Microbial Sensitivity Tests ; },
abstract = {Escherichia coli can colonise the urogenital tract of individuals without causing symptoms of infection, in a condition referred to as asymptomatic bacteriuria (ABU). ABU isolates can protect the host against symptomatic urinary tract infections (UTIs) by bacterial interference against uropathogenic E. coli (UPEC). The aim of this study was to investigate the genotypic and phenotypic characteristics of five ABU isolates from midstream urine samples of adults. Comparative genomic and phenotypic analysis was conducted including an antibiotic resistance profile, pangenome analysis, and a putative virulence profile. Based on the genome analysis, the isolates consisted of one from phylogroup A, three from phylogroup B2, and one from phylogroup D. Two of the isolates, PUTS 58 and SK-106-1, were noted for their lack of antibiotic resistance and virulence genes compared to the prototypic ABU strain E. coli 83,972. This study provides insights into the genotypic and phenotypic profiles of uncharacterised ABU isolates, and how relevant fitness and virulence traits can impact their potential suitability for therapeutic bacterial interference.},
}

Humans
*Bacteriuria/microbiology
*Uropathogenic Escherichia coli/genetics/drug effects/isolation & purification/classification
*Escherichia coli Infections/microbiology
*Drug Resistance, Multiple, Bacterial/genetics
*Genotype
*Phenotype
*Urinary Tract Infections/microbiology
*Anti-Bacterial Agents/pharmacology
Virulence/genetics
Phylogeny
Adult
Virulence Factors/genetics
Genome, Bacterial
Microbial Sensitivity Tests

@article {pmid39244587,
year = {2024},
author = {Campbell, AM and Gavilan, RG and Abanto Marin, M and Yang, C and Hauton, C and van Aerle, R and Martinez-Urtaza, J},
title = {Evolutionary dynamics of the successful expansion of pandemic Vibrio parahaemolyticus ST3 in Latin America.},
journal = {Nature communications},
volume = {15},
number = {1},
pages = {7828},
pmid = {39244587},
issn = {2041-1723},
support = {2021 SGR 00526//Generalitat de Catalunya (Government of Catalonia)/ ; NE/S007210/1//RCUK | Natural Environment Research Council (NERC)/ ; },
mesh = {*Vibrio parahaemolyticus/genetics/isolation & purification/classification ; Latin America/epidemiology ; *Evolution, Molecular ; *Vibrio Infections/epidemiology/microbiology ; Humans ; *Phylogeny ; Genome, Bacterial/genetics ; Pandemics ; Mutation ; },
abstract = {The underlying evolutionary mechanisms driving global expansions of pathogen strains are poorly understood. Vibrio parahaemolyticus is one of only two marine pathogens where variants have emerged in distinct climates globally. The success of a Vibrio parahaemolyticus clone (VpST3) in Latin America- the first spread identified outside its endemic region of tropical Asia- provided an invaluable opportunity to investigate mechanisms of VpST3 expansion into a distinct marine climate. A global collection of VpST3 isolates and novel Latin American isolates were used for evolutionary population genomics, pangenome analysis and combined with oceanic climate data. We found a VpST3 population (LatAm-VpST3) introduced in Latin America well before the emergence of this clone in India, previously considered the onset of the VpST3 epidemic. LatAm-VpST3 underwent successful adaptation to local conditions over its evolutionary divergence from Asian VpST3 isolates, to become dominant in Latin America. Selection signatures were found in genes providing resilience to the distinct marine climate. Core genome mutations and accessory gene presences that promoted survival over long dispersals or increased environmental fitness were associated with environmental conditions. These results provide novel insights into the global expansion of this successful V. parahaemolyticus clone into regions with different climate scenarios.},
}

*Vibrio parahaemolyticus/genetics/isolation & purification/classification
Latin America/epidemiology
*Evolution, Molecular
*Vibrio Infections/epidemiology/microbiology
Humans
*Phylogeny
Genome, Bacterial/genetics
Pandemics
Mutation

@article {pmid39243017,
year = {2024},
author = {Kim, HS and Haley, OC and Portwood Ii, JL and Harding, S and Proctor, RH and Woodhouse, MR and Sen, TZ and Andorf, CM},
title = {Fusarium Protein Toolkit: a web-based resource for structural and variant analysis of Fusarium species.},
journal = {BMC microbiology},
volume = {24},
number = {1},
pages = {326},
pmid = {39243017},
issn = {1471-2180},
support = {5010-11420-001-000-D and 5010-42000-053-000-D//USDA, Agricultural Research Service, United States/ ; 0201-88888-003-000D and 0201-88888-002-000D//USDA, Agricultural Research Service, United States/ ; 5030-21000-072-00-D//USDA, Agricultural Research Service, United States/ ; 5010-11420-001-000-D and 5010-42000-053-000-D//USDA, Agricultural Research Service, United States/ ; 5010-11420-001-000-D and 5010-42000-053-000-D//USDA, Agricultural Research Service, United States/ ; 5030-21000-072-00-D//USDA, Agricultural Research Service, United States/ ; 2030-21000-056-000-D//USDA, Agricultural Research Service, United States/ ; 5030-21000-072-00-D//USDA, Agricultural Research Service, United States/ ; },
mesh = {*Fusarium/genetics/metabolism/classification ; *Fungal Proteins/genetics/chemistry/metabolism ; *Internet ; Genome, Fungal/genetics ; Genetic Variation ; Models, Molecular ; Software ; Protein Conformation ; },
abstract = {BACKGROUND: The genus Fusarium poses significant threats to food security and safety worldwide because numerous species of the fungus cause destructive diseases and/or mycotoxin contamination in crops. The adverse effects of climate change are exacerbating some existing threats and causing new problems. These challenges highlight the need for innovative solutions, including the development of advanced tools to identify targets for control strategies.

DESCRIPTION: In response to these challenges, we developed the Fusarium Protein Toolkit (FPT), a web-based tool that allows users to interrogate the structural and variant landscape within the Fusarium pan-genome. The tool displays both AlphaFold and ESMFold-generated protein structure models from six Fusarium species. The structures are accessible through a user-friendly web portal and facilitate comparative analysis, functional annotation inference, and identification of related protein structures. Using a protein language model, FPT predicts the impact of over 270 million coding variants in two of the most agriculturally important species, Fusarium graminearum and F. verticillioides. To facilitate the assessment of naturally occurring genetic variation, FPT provides variant effect scores for proteins in a Fusarium pan-genome based on 22 diverse species. The scores indicate potential functional consequences of amino acid substitutions and are displayed as intuitive heatmaps using the PanEffect framework.

CONCLUSION: FPT fills a knowledge gap by providing previously unavailable tools to assess structural and missense variation in proteins produced by Fusarium. FPT has the potential to deepen our understanding of pathogenic mechanisms in Fusarium, and aid the identification of genetic targets for control strategies that reduce crop diseases and mycotoxin contamination. Such targets are vital to solving the agricultural problems incited by Fusarium, particularly evolving threats resulting from climate change. Thus, FPT has the potential to contribute to improving food security and safety worldwide.},
}

*Fusarium/genetics/metabolism/classification
*Fungal Proteins/genetics/chemistry/metabolism
*Internet
Genome, Fungal/genetics
Genetic Variation
Models, Molecular
Software
Protein Conformation

@article {pmid39242972,
year = {2024},
author = {Masignani, V and Rappuoli, R and Pizza, M},
title = {Next generation of "magic bullets", solutions from the microbial pangenome.},
journal = {EMBO molecular medicine},
volume = {},
number = {},
pages = {},
pmid = {39242972},
issn = {1757-4684},
}

@article {pmid39238887,
year = {2024},
author = {Najjari, A and Jabberi, M and Chérif, SF and Cherif, A and Ouzari, HI and Linares-Pastén, JA and Sghaier, H},
title = {Genome and pan-genome analysis of a new exopolysaccharide-producing bacterium Pyschrobacillus sp. isolated from iron ores deposit and insights into iron uptake.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1440081},
pmid = {39238887},
issn = {1664-302X},
abstract = {Bacterial exopolysaccharides (EPS) have emerged as one of the key players in the field of heavy metal-contaminated environmental bioremediation. This study aimed to characterize and evaluate the metal biosorption potential of EPS produced by a novel Psychrobacillus strain, NEAU-3TGS, isolated from an iron ore deposit at Tamra iron mine, northern Tunisia. Genomic and pan-genomic analysis of NEAU-3TGS bacterium with nine validated published Psychrobacillus species was also performed. The results showed that the NEAU-3TGS genome (4.48 Mb) had a mean GC content of 36%, 4,243 coding sequences and 14 RNA genes. Phylogenomic analysis and calculation of nucleotide identity (ANI) values (less than 95% for new species with all strains) confirmed that NEAU-3TGS represents a potential new species. Pangenomic analysis revealed that Psychrobacillus genomic diversity represents an "open" pangenome model with 33,091 homologous genes, including 65 core, 3,738 shell, and 29,288 cloud genes. Structural EPS characterization by attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectroscopy showed uronic acid and α-1,4-glycosidic bonds as dominant components of the EPS. X-ray diffraction (XRD) analysis revealed the presence of chitin, chitosan, and calcite CaCO3 and confirmed the amorphous nature of the EPS. Heavy metal bioabsorption assessment showed that iron and lead were more adsorbed than copper and cadmium. Notably, the optimum activity was observed at 37°C, pH=7 and after 3 h contact of EPS with each metal. Genomic insights on iron acquisition and metabolism in Psychrobacillus sp. NEAU-3TGS suggested that no genes involved in siderophore biosynthesis were found, and only the gene cluster FeuABCD and trilactone hydrolase genes involved in the uptake of siderophores, iron transporter and exporter are present. Molecular modelling and docking of FeuA (protein peptidoglycan siderophore-binding protein) and siderophores ferrienterobactine [Fe[+3] (ENT)][-3] and ferribacillibactine [Fe[+3] (BB)][-3] ligand revealed that [Fe[+3] (ENT)][-3] binds to Phe122, Lys127, Ile100, Gln314, Arg215, Arg217, and Gln252. Almost the same for [Fe[+3] (ENT)][-3] in addition to Cys222 and Tyr229, but not Ile100.To the best of our knowledge, this is the first report on the characterization of EPS and the adsorption of heavy metals by Psychrobacillus species. The heavy metal removal capabilities may be advantageous for using these organisms in metal remediation.},
}

@article {pmid39237905,
year = {2024},
author = {Cheng, R and Zhao, Z and Tang, Y and Gu, Y and Chen, G and Sun, Y and Wang, X},
title = {Genome-wide survey of KT/HAK/KUP genes in the genus Citrullus and analysis of their involvement in K[+]-deficiency and drought stress responses in between C. lanatus and C. amarus.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {836},
pmid = {39237905},
issn = {1471-2164},
support = {HABL202228//Huai'an Natural Science Research Project/ ; JBGS[2021]072//Seed Industry Vitalization Research Projects of Jiangsu Province/ ; CARS-25//China Agriculture Research System of MOF and MARA/ ; },
mesh = {*Citrullus/genetics/metabolism/growth & development ; *Stress, Physiological/genetics ; *Plant Proteins/genetics/metabolism ; *Droughts ; *Phylogeny ; Potassium/metabolism ; Gene Expression Regulation, Plant ; Genome, Plant ; Multigene Family ; Cation Transport Proteins/genetics/metabolism ; Potassium Deficiency/genetics/metabolism ; Promoter Regions, Genetic ; },
abstract = {BACKGROUND: The KT/HAK/KUP is the largest K[+] transporter family in plants, playing crucial roles in K[+] absorption, transport, and defense against environmental stress. Sweet watermelon is an economically significant horticultural crop belonging to the genus Citrullus, with a high demand for K[+] during its growth process. However, a comprehensive analysis of the KT/HAK/KUP gene family in watermelon has not been reported.

RESULTS: 14 KT/HAK/KUP genes were identified in the genomes of each of seven Citrullus species. These KT/HAK/KUPs in watermelon were unevenly distributed across seven chromosomes. Segmental duplication is the primary driving force behind the expansion of the KT/HAK/KUP family, subjected to purifying selection during domestication (Ka/Ks < 1), and all KT/HAK/KUPs exhibit conserved motifs and could be phylogenetically classified into four groups. The promoters of KT/HAK/KUPs contain numerous cis-regulatory elements related to plant growth and development, phytohormone response, and stress response. Under K[+] deficiency, the growth of watermelon seedlings was significantly inhibited, with cultivated watermelon experiencing greater impacts (canopy width, redox enzyme activity) compared to the wild type. All KT/HAK/KUPs in C. lanatus and C. amarus exhibit specific expression responses to K[+]-deficiency and drought stress by qRT-PCR. Notably, ClG42_07g0120700/CaPI482276_07g014010 were predominantly expressed in roots and were further induced by K[+]-deficiency and drought stress. Additionally, the K[+] transport capacity of ClG42_07g0120700 under low K[+] stress was confirmed by yeast functional complementation assay.

CONCLUSIONS: KT/HAK/KUP genes in watermelon were systematically identified and analyzed at the pangenome level and provide a foundation for understanding the classification and functions of the KT/HAK/KUPs in watermelon plants.},
}

*Citrullus/genetics/metabolism/growth & development
*Stress, Physiological/genetics
*Plant Proteins/genetics/metabolism
*Droughts
*Phylogeny
Potassium/metabolism
Gene Expression Regulation, Plant
Genome, Plant
Multigene Family
Cation Transport Proteins/genetics/metabolism
Potassium Deficiency/genetics/metabolism
Promoter Regions, Genetic

@article {pmid39235714,
year = {2024},
author = {de Oliva, BHD and do Nascimento, AB and de Oliveira, JP and Guidone, GHM and Schoeps, BL and Silva, LC and Barbosa, MGL and Montini, VH and de Oliveira Junior, AG and Rocha, SPD},
title = {Genomic insights into a Proteus mirabilis strain inducing avian cellulitis.},
journal = {Brazilian journal of microbiology : [publication of the Brazilian Society for Microbiology]},
volume = {},
number = {},
pages = {},
pmid = {39235714},
issn = {1678-4405},
support = {Finance Code 001//Coordenação de Aperfeiçoamento de Pessoal de Nível Superior/ ; },
abstract = {Proteus mirabilis, a microorganism distributed in soil, water, and animals, is clinically known for causing urinary tract infections in humans. However, recent studies have linked it to skin infections in broiler chickens, termed avian cellulitis, which poses a threat to animal welfare. While Avian Pathogenic Escherichia coli (APEC) is the primary cause of avian cellulitis, few cases of P. mirabilis involvement are reported, raising questions about the factors facilitating such occurrences. This study employed a pan-genomic approach to investigate whether unique genes exist in P. mirabilis strains causing avian cellulitis. The genome of LBUEL-A33, a P. mirabilis strain known to cause this infection, was assembled, and compared with other P. mirabilis strains isolated from poultry and other sources. Additionally, in silico serogroup analysis was conducted. Results revealed numerous genes unique to the LBUEL-A33 strain. No function in cellulitis was identified for these genes, and in silico investigation of the virulence potential of LBUEL-A33's exclusive proteins proved inconclusive. These findings support that multiple factors are necessary for P. mirabilis to cause avian cellulitis. Furthermore, this species likely employs its own unique arsenal of virulence factors, as many identified mechanisms are analogous to those of E. coli. While antigenic gene clusters responsible for serogroups were identified, no clear trend was observed, and the gene cluster of LBUEL-A33 did not show homology with any sequenced Proteus serogroups. These results reinforce the understanding that this disease is multifactorial, necessitating further research to unravel the mechanisms and underpin the development of control and prevention strategies.},
}

@article {pmid38736416,
year = {2024},
author = {Brandenburg, JM and Stapleton, GS and Kline, KE and Khoury, J and Mallory, K and Machesky, KD and Ladd-Wilson, SG and Scholz, R and Freiman, J and Schwensohn, C and Palacios, A and Gieraltowski, L and Ellison, Z and Tolar, B and Webb, HE and Tagg, KA and Salah, Z and Nichols, M},
title = {Salmonella Hadar linked to two distinct transmission vehicles highlights challenges to enteric disease outbreak investigations.},
journal = {Epidemiology and infection},
volume = {152},
number = {},
pages = {e86},
doi = {10.1017/S0950268824000682},
pmid = {38736416},
issn = {1469-4409},
mesh = {*Disease Outbreaks ; Animals ; *Salmonella/genetics/classification/isolation & purification ; *Turkeys/microbiology ; *Poultry Diseases/epidemiology/microbiology/transmission ; Humans ; Salmonella Infections, Animal/epidemiology/transmission/microbiology ; Chickens/microbiology ; Multilocus Sequence Typing ; Ducks/microbiology ; Poultry/microbiology ; Salmonella Infections/epidemiology/transmission/microbiology ; },
abstract = {In 2020, an outbreak of Salmonella Hadar illnesses was linked to contact with non-commercial, privately owned (backyard) poultry including live chickens, turkeys, and ducks, resulting in 848 illnesses. From late 2020 to 2021, this Salmonella Hadar strain caused an outbreak that was linked to ground turkey consumption. Core genome multilocus sequence typing (cgMLST) analysis determined that the Salmonella Hadar isolates detected during the outbreak linked to backyard poultry and the outbreak linked to ground turkey were closely related genetically (within 0-16 alleles). Epidemiological and traceback investigations were unable to determine how Salmonella Hadar detected in backyard poultry and ground turkey were linked, despite this genetic relatedness. Enhanced molecular characterization methods, such as analysis of the pangenome of Salmonella isolates, might be necessary to understand the relationship between these two outbreaks. Similarly, enhanced data collection during outbreak investigations and further research could potentially aid in determining whether these transmission vehicles are truly linked by a common source and what reservoirs exist across the poultry industries that allow Salmonella Hadar to persist. Further work combining epidemiological data collection, more detailed traceback information, and genomic analysis tools will be important for monitoring and investigating future enteric disease outbreaks.},
}

*Disease Outbreaks
Animals
*Salmonella/genetics/classification/isolation & purification
*Turkeys/microbiology
*Poultry Diseases/epidemiology/microbiology/transmission
Humans
Salmonella Infections, Animal/epidemiology/transmission/microbiology
Chickens/microbiology
Multilocus Sequence Typing
Ducks/microbiology
Poultry/microbiology
Salmonella Infections/epidemiology/transmission/microbiology

@article {pmid39232082,
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 Aspergillus fungus highlights factors associated with virulence.},
journal = {Communications biology},
volume = {7},
number = {1},
pages = {1082},
pmid = {39232082},
issn = {2399-3642},
support = {R01 AI153356/AI/NIAID NIH HHS/United States ; DEB-2110404//National Science Foundation (NSF)/ ; },
mesh = {Animals ; Virulence ; *Aspergillus/pathogenicity/genetics/metabolism ; Mice ; Gliotoxin/metabolism ; Disease Models, Animal ; Pulmonary Aspergillosis/microbiology ; Female ; Genome, Fungal ; },
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 metabolic 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.},
}

Animals
Virulence
*Aspergillus/pathogenicity/genetics/metabolism
Mice
Gliotoxin/metabolism
Disease Models, Animal
Pulmonary Aspergillosis/microbiology
Female
Genome, Fungal

@article {pmid39232008,
year = {2024},
author = {Veseli, I and DeMers, MA and Cooper, ZS and Schechter, MS and Miller, S and Weber, L and Smith, CB and Rodriguez, LT and Schroer, WF and McIlvin, MR and Lopez, PZ and Saito, M and Dyhrman, S and Eren, AM and Moran, MA and Braakman, R},
title = {Digital Microbe: a genome-informed data integration framework for team science on emerging model organisms.},
journal = {Scientific data},
volume = {11},
number = {1},
pages = {967},
pmid = {39232008},
issn = {2052-4463},
support = {1746045//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; OCE-2019589//National Science Foundation (NSF)/ ; 542391//Simons Foundation/ ; },
mesh = {*Genome, Bacterial ; Genomics ; Software ; Flavobacteriaceae/genetics ; },
abstract = {The remarkable pace of genomic data generation is rapidly transforming our understanding of life at the micron scale. Yet this data stream also creates challenges for team science. A single microbe can have multiple versions of genome architecture, functional gene annotations, and gene identifiers; additionally, the lack of mechanisms for collating and preserving advances in this knowledge raises barriers to community coalescence around shared datasets. "Digital Microbes" are frameworks for interoperable and reproducible collaborative science through open source, community-curated data packages built on a (pan)genomic foundation. Housed within an integrative software environment, Digital Microbes ensure real-time alignment of research efforts for collaborative teams and facilitate novel scientific insights as new layers of data are added. Here we describe two Digital Microbes: 1) the heterotrophic marine bacterium Ruegeria pomeroyi DSS-3 with > 100 transcriptomic datasets from lab and field studies, and 2) the pangenome of the cosmopolitan marine heterotroph Alteromonas containing 339 genomes. Examples demonstrate how an integrated framework collating public (pan)genome-informed data can generate novel and reproducible findings.},
}

*Genome, Bacterial
Genomics
Software
Flavobacteriaceae/genetics

@article {pmid39232174,
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, CS and Garrison, E and Sudmant, PH},
title = {Recurrent evolution and selection shape structural diversity at the amylase locus.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {39232174},
issn = {1476-4687},
abstract = {The adoption of agriculture triggered a rapid shift towards starch-rich diets in human populations[1]. Amylase genes facilitate starch digestion, and increased amylase copy number has been observed in some modern human populations with high-starch intake[2], although evidence of recent selection is lacking[3,4]. Here, using 94 long-read haplotype-resolved assemblies and short-read data from approximately 5,600 contemporary and ancient humans, we resolve the diversity and evolutionary history of structural variation at the amylase locus. We find that amylase genes have higher copy numbers in agricultural populations than in fishing, hunting and pastoral populations. We identify 28 distinct amylase structural architectures and demonstrate that nearly identical structures have arisen recurrently on different haplotype backgrounds throughout recent human history. AMY1 and AMY2A genes each underwent multiple duplication/deletion events with mutation rates up to more than 10,000-fold the single-nucleotide polymorphism mutation rate, whereas AMY2B gene duplications share a single origin. Using a pangenome-based approach, we infer structural haplotypes across thousands of humans identifying extensively duplicated haplotypes at higher frequency in modern agricultural populations. Leveraging 533 ancient human genomes, we find that duplication-containing haplotypes (with more gene copies than the ancestral haplotype) have rapidly increased in frequency over the past 12,000 years in West Eurasians, suggestive of positive selection. Together, our study highlights the potential effects of the agricultural revolution on human genomes and the importance of structural variation in human adaptation.},
}

@article {pmid39228856,
year = {2024},
author = {Fan, X and Chen, L and Chen, M and Zhang, N and Chang, H and He, M and Shen, Z and Zhang, L and Ding, H and Xie, Y and Huang, Y and Ke, W and Xiao, M and Zang, X and Xu, H and Fang, W and Li, S and Cao, C and Xu, Y and Shan, S and Wu, W and Chen, C and Xue, X and Wang, L},
title = {Pan-omics-based characterization and prediction of highly multidrug-adapted strains from an outbreak fungal species complex.},
journal = {Innovation (Cambridge (Mass.))},
volume = {5},
number = {5},
pages = {100681},
pmid = {39228856},
issn = {2666-6758},
abstract = {Strains from the Cryptococcus gattii species complex (CGSC) have caused the Pacific Northwest cryptococcosis outbreak, the largest cluster of life-threatening fungal infections in otherwise healthy human hosts known to date. In this study, we utilized a pan-phenome-based method to assess the fitness outcomes of CGSC strains under 31 stress conditions, providing a comprehensive overview of 2,821 phenotype-strain associations within this pathogenic clade. Phenotypic clustering analysis revealed a strong correlation between distinct types of stress phenotypes in a subset of CGSC strains, suggesting that shared determinants coordinate their adaptations to various stresses. Notably, a specific group of strains, including the outbreak isolates, exhibited a remarkable ability to adapt to all three of the most commonly used antifungal drugs for treating cryptococcosis (amphotericin B, 5-fluorocytosine, and fluconazole). By integrating pan-genomic and pan-transcriptomic analyses, we identified previously unrecognized genes that play crucial roles in conferring multidrug resistance in an outbreak strain with high multidrug adaptation. From these genes, we identified biomarkers that enable the accurate prediction of highly multidrug-adapted CGSC strains, achieving maximum accuracy and area under the curve (AUC) of 0.79 and 0.86, respectively, using machine learning algorithms. Overall, we developed a pan-omic approach to identify cryptococcal multidrug resistance determinants and predict highly multidrug-adapted CGSC strains that may pose significant clinical concern.},
}

@article {pmid39228791,
year = {2024},
author = {Do, VH and Nguyen, VS and Nguyen, SH and Le, DQ and Nguyen, TT and Nguyen, CH and Ho, TH and Vo, NS and Nguyen, T and Nguyen, HA and Cao, MD},
title = {PanKA: Leveraging population pangenome to predict antibiotic resistance.},
journal = {iScience},
volume = {27},
number = {9},
pages = {110623},
pmid = {39228791},
issn = {2589-0042},
abstract = {Machine learning has the potential to be a powerful tool in the fight against antimicrobial resistance (AMR), a critical global health issue. Machine learning can identify resistance mechanisms from DNA sequence data without prior knowledge. The first step in building a machine learning model is a feature extraction from sequencing data. Traditional methods like single nucleotide polymorphism (SNP) calling and k-mer counting yield numerous, often redundant features, complicating prediction and analysis. In this paper, we propose PanKA, a method using the pangenome to extract a concise set of relevant features for predicting AMR. PanKA not only enables fast model training and prediction but also improves accuracy. Applied to the Escherichia coli and Klebsiella pneumoniae bacterial species, our model is more accurate than conventional and state-of-the-art methods in predicting AMR.},
}

@article {pmid39227987,
year = {2024},
author = {Bonnici, V and Chicco, D},
title = {Seven quick tips for gene-focused computational pangenomic analysis.},
journal = {BioData mining},
volume = {17},
number = {1},
pages = {28},
pmid = {39227987},
issn = {1756-0381},
support = {InfoLife//CINI (Consorzio Interuniversitario Nazionale per l'Informatica)/ ; Project Age-It (Ageing Well in an Ageing Society)//European Union - Next Generation EU programme/ ; ReGAInS//Ministero dell'Università e della Ricerca of Italy/ ; },
abstract = {Pangenomics is a relatively new scientific field which investigates the union of all the genomes of a clade. The word pan means everything in ancient Greek; the term pangenomics originally regarded genomes of bacteria and was later intended to refer to human genomes as well. Modern bioinformatics offers several tools to analyze pangenomics data, paving the way to an emerging field that we can call computational pangenomics. Current computational power available for the bioinformatics community has made computational pangenomic analyses easy to perform, but this higher accessibility to pangenomics analysis also increases the chances to make mistakes and to produce misleading or inflated results, especially by beginners. To handle this problem, we present here a few quick tips for efficient and correct computational pangenomic analyses with a focus on bacterial pangenomics, by describing common mistakes to avoid and experienced best practices to follow in this field. We believe our recommendations can help the readers perform more robust and sound pangenomic analyses and to generate more reliable results.},
}

@article {pmid39221271,
year = {2024},
author = {Trisakul, K and Hinwan, Y and Eisiri, J and Salao, K and Chaiprasert, A and Kamolwat, P and Tongsima, S and Campino, S and Phelan, J and Clark, TG and Faksri, K},
title = {Comparisons of genome assembly tools for characterization of Mycobacterium tuberculosis genomes using hybrid sequencing technologies.},
journal = {PeerJ},
volume = {12},
number = {},
pages = {e17964},
pmid = {39221271},
issn = {2167-8359},
mesh = {*Mycobacterium tuberculosis/genetics ; *Genome, Bacterial/genetics ; *High-Throughput Nucleotide Sequencing/methods ; Humans ; Polymorphism, Single Nucleotide/genetics ; Sequence Analysis, DNA/methods ; },
abstract = {BACKGROUND: Next-generation sequencing of Mycobacterium tuberculosis, the infectious agent causing tuberculosis, is improving the understanding of genomic diversity of circulating lineages and strain-types, and informing knowledge of drug resistance mutations. An increasingly popular approach to characterizing M. tuberculosis genomes (size: 4.4 Mbp) and variants (e.g., single nucleotide polymorphisms (SNPs)) involves the de novo assembly of sequence data.

METHODS: We compared the performance of genome assembly tools (Unicycler, RagOut, and RagTag) on sequence data from nine drug resistant M. tuberculosis isolates (multi-drug (MDR) n = 1; pre-extensively-drug (pre-XDR) n = 8) generated using Illumina HiSeq, Oxford Nanopore Technology (ONT) PromethION, and PacBio platforms.

RESULTS: Our investigation found that Unicycler-based assemblies had significantly higher genome completeness (~98.7%; p values = 0.01) compared to other assembler tools (RagOut = 98.6%, and RagTag = 98.6%). The genome assembly sizes (bp) across isolates and sequencers based on RagOut was significantly longer (p values < 0.001) (4,418,574 ± 8,824 bp) than Unicycler and RagTag assemblies (Unicycler = 4,377,642 ± 55,257 bp, and RagTag = 4,380,711 ± 51,164 bp). RagOut-based assemblies had the fewest contigs (~32) and the longest genome size (4,418,574 bp; vs. H37Rv reference size 4,411,532 bp) and therefore were chosen for downstream analysis. Pan-genome analysis of Illumina and PacBio hybrid assemblies revealed the greatest number of detected genes (4,639 genes; H37Rv reference contains 3,976 genes), while Illumina and ONT hybrid assemblies produced the highest number of SNPs. The number of genes from hybrid assemblies with ONT and PacBio long-reads (mean: 4,620 genes) was greater than short-read assembly alone (4,478 genes). All nine RagOut hybrid genome assemblies detected known mutations in genes associated with MDR-TB and pre-XDR-TB.

CONCLUSIONS: Unicycler software performed the best in terms of achieving contiguous genomes, whereas RagOut improved the quality of Unicycler's genome assemblies by providing a longer genome size. Overall, our approach has demonstrated that short-read and long-read hybrid assembly can provide a more complete genome assembly than short-read assembly alone by detecting pan-genomes and more genes, including IS6110, and SNPs.},
}

*Mycobacterium tuberculosis/genetics
*Genome, Bacterial/genetics
*High-Throughput Nucleotide Sequencing/methods
Humans
Polymorphism, Single Nucleotide/genetics
Sequence Analysis, DNA/methods

@article {pmid39218842,
year = {2024},
author = {Mane, RS and Prasad, BD and Sahni, S and Quaiyum, Z and Sharma, VK},
title = {Biotechnological studies towards improvement of finger millet using multi-omics approaches.},
journal = {Functional & integrative genomics},
volume = {24},
number = {5},
pages = {148},
pmid = {39218842},
issn = {1438-7948},
mesh = {*Plant Breeding/methods ; *Eleusine/genetics ; *Genomics/methods ; Gene Editing/methods ; Crops, Agricultural/genetics ; Genome, Plant ; Biotechnology ; Multiomics ; },
abstract = {A plethora of studies have uncovered numerous important genes with agricultural significance in staple crops. However, when it comes to orphan crops like minor millet, genomic research lags significantly behind that of major crops. This situation has promoted a focus on exploring research opportunities in minor millets, particularly in finger millet, using cutting-edge methods. Finger millet, a coarse cereal known for its exceptional nutritional content and ability to withstand environmental stresses represents a promising climate-smart and nutritional crop in the battle against escalating environmental challenges. The existing traditional improvement programs for finger millet are insufficient to address global hunger effectively. The lack of utilization of high-throughput platforms, genome editing, haplotype breeding, and advanced breeding approaches hinders the systematic multi-omics studies on finger millet, which are essential for pinpointing crucial genes related to agronomically important and various stress responses. The growing environmental uncertainties have widened the gap between the anticipated and real progress in crop improvement. To overcome these challenges a combination of cutting-edge multi-omics techniques such as high-throughput sequencing, speed breeding, mutational breeding, haplotype-based breeding, genomic selection, high-throughput phenotyping, pangenomics, genome editing, and more along with integration of deep learning and artificial intelligence technologies are essential to accelerate research efforts in finger millet. The scarcity of multi-omics approaches in finger millet leaves breeders with limited modern tools for crop enhancement. Therefore, leveraging datasets from previous studies could prove effective in implementing the necessary multi-omics interventions to enrich the genetic resource in finger millet.},
}

*Plant Breeding/methods
*Eleusine/genetics
*Genomics/methods
Gene Editing/methods
Crops, Agricultural/genetics
Genome, Plant
Biotechnology
Multiomics

@article {pmid39215522,
year = {2024},
author = {Gao, J and Xu, Y},
title = {DNA sequences alignment method using sparse index on pan-genome graph.},
journal = {Journal of bioinformatics and computational biology},
volume = {},
number = {},
pages = {2450019},
doi = {10.1142/S0219720024500197},
pmid = {39215522},
issn = {1757-6334},
abstract = {The graph of sequences represents the genetic variations of pan-genome concisely and space-efficiently than multiple linear reference genome. In order to accelerate aligning reads to the graph, an index of graph-based reference genomes is used to obtain candidate locations. However, the potential combinatorial explosion of nodes on the sequence graph leads to increasing the index space and maximum memory usage of alignment process considerably, especially for large-scale datasets. For this, existing methods typically attempt to prune complex regions, or extend the length of seeds, which sacrifices the recall of alignment algorithm despite reducing space usage slightly. We present the Sparse-index of Graph (SIG) and alignment algorithm SIG-Aligner, capable of indexing and aligning at the lower memory cost. SIG builds the non-overlapping minimizers index inside nodes of sequence graph and SIG-Aligner filters out most of the false positive matches by the method based on the pigeonhole principle. Compared to Giraffe, the results of computational experiments show that SIG achieves a significant reduction in index memory space ranging from 50% to 75% for the human pan-genome graphs, while still preserving superior or comparable accuracy of alignment and the faster alignment time.},
}

@article {pmid39213169,
year = {2024},
author = {Andrews, KR and Besser, TE and Stalder, T and Top, EM and Baker, KN and Fagnan, MW and New, DD and Schneider, GM and Gal, A and Andrews-Dickert, R and Hunter, SS and Beckmen, KB and Christensen, L and Justice-Allen, A and Konetchy, D and Lehman, CP and Manlove, K and Miyasaki, H and Nordeen, T and Roug, A and Cassirer, EF},
title = {Comparative genomic analysis identifies potential adaptive variation in Mycoplasma ovipneumoniae.},
journal = {Microbial genomics},
volume = {10},
number = {8},
pages = {},
doi = {10.1099/mgen.0.001279},
pmid = {39213169},
issn = {2057-5858},
mesh = {Animals ; *Mycoplasma ovipneumoniae/genetics ; *Goats/microbiology ; *Phylogeny ; Sheep/microbiology ; *Genome, Bacterial ; Genomics ; Reindeer/microbiology ; China ; Sheep Diseases/microbiology ; Adaptation, Physiological/genetics ; Australia ; Pneumonia, Mycoplasma/microbiology/veterinary ; },
abstract = {Mycoplasma ovipneumoniae is associated with respiratory disease in wild and domestic Caprinae globally, with wide variation in disease outcomes within and between host species. To gain insight into phylogenetic structure and mechanisms of pathogenicity for this bacterial species, we compared M. ovipneumoniae genomes for 99 samples from 6 countries (Australia, Bosnia and Herzegovina, Brazil, China, France and USA) and 4 host species (domestic sheep, domestic goats, bighorn sheep and caribou). Core genome sequences of M. ovipneumoniae assemblies from domestic sheep and goats fell into two well-supported phylogenetic clades that are divergent enough to be considered different bacterial species, consistent with each of these two clades having an evolutionary origin in separate host species. Genome assemblies from bighorn sheep and caribou also fell within these two clades, indicating multiple spillover events, most commonly from domestic sheep. Pangenome analysis indicated a high percentage (91.4 %) of accessory genes (i.e. genes found only in a subset of assemblies) compared to core genes (i.e. genes found in all assemblies), potentially indicating a propensity for this pathogen to adapt to within-host conditions. In addition, many genes related to carbon metabolism, which is a virulence factor for Mycoplasmas, showed evidence for homologous recombination, a potential signature of adaptation. The presence or absence of annotated genes was very similar between sheep and goat clades, with only two annotated genes significantly clade-associated. However, three M. ovipneumoniae genome assemblies from asymptomatic caribou in Alaska formed a highly divergent subclade within the sheep clade that lacked 23 annotated genes compared to other assemblies, and many of these genes had functions related to carbon metabolism. Overall, our results suggest that adaptation of M. ovipneumoniae has involved evolution of carbon metabolism pathways and virulence mechanisms related to those pathways. The genes involved in these pathways, along with other genes identified as potentially involved in virulence in this study, are potential targets for future investigation into a possible genomic basis for the high variation observed in disease outcomes within and between wild and domestic host species.},
}

Animals
*Mycoplasma ovipneumoniae/genetics
*Goats/microbiology
*Phylogeny
Sheep/microbiology
*Genome, Bacterial
Genomics
Reindeer/microbiology
China
Sheep Diseases/microbiology
Adaptation, Physiological/genetics
Australia
Pneumonia, Mycoplasma/microbiology/veterinary

@article {pmid39212644,
year = {2024},
author = {Askenasy, I and Swain, JEV and Ho, PM and Nazeer, RR and Welch, A and Bényei, ÉB and Mancini, L and Nir, S and Liao, P and Welch, M},
title = {'Wild Type'.},
journal = {Microbiology (Reading, England)},
volume = {170},
number = {8},
pages = {},
doi = {10.1099/mic.0.001495},
pmid = {39212644},
issn = {1465-2080},
mesh = {*Genome, Bacterial ; Bacteria/genetics/classification/isolation & purification ; Evolution, Molecular ; Genetic Variation ; Genomics ; },
abstract = {In this opinion piece, we consider the meaning of the term 'wild type' in the context of microbiology. This is especially pertinent in the post-genomic era, where we have a greater awareness of species diversity than ever before. Genomic heterogeneity, in vitro evolution/selection pressures, definition of 'the wild', the size and importance of the pan-genome, gene-gene interactions (epistasis), and the nature of the 'wild-type gene' are all discussed. We conclude that wild type is an outdated and even misleading phrase that should be gradually phased out.},
}

*Genome, Bacterial
Bacteria/genetics/classification/isolation & purification
Evolution, Molecular
Genetic Variation
Genomics

@article {pmid39212029,
year = {2024},
author = {de Block, T and De Baetselier, I and Van den Bossche, D and Abdellati, S and Gestels, Z and Laumen, JGE and Van Dijck, C and Vanbaelen, T and Claes, N and Vandelannoote, K and Kenyon, C and Harrison, O and Santhini Manoharan-Basil, S},
title = {Genomic oropharyngeal Neisseria surveillance detects MALDI-TOF MS species misidentifications and reveals a novel Neisseria cinerea clade.},
journal = {Journal of medical microbiology},
volume = {73},
number = {8},
pages = {},
doi = {10.1099/jmm.0.001871},
pmid = {39212029},
issn = {1473-5644},
mesh = {*Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization/methods ; *Oropharynx/microbiology ; Humans ; *Whole Genome Sequencing ; *Multilocus Sequence Typing/methods ; *Genome, Bacterial ; Neisseria cinerea/genetics ; Phylogeny ; Neisseria/classification/genetics/isolation & purification ; Belgium ; Neisseria meningitidis/genetics/classification/isolation & purification ; Neisseriaceae Infections/microbiology/diagnosis ; },
abstract = {Introduction. Commensal Neisseria spp. are highly prevalent in the oropharynx as part of the healthy microbiome. N. meningitidis can colonise the oropharynx too from where it can cause invasive meningococcal disease. To identify N. meningitidis, clinical microbiology laboratories often rely on Matrix Assisted Laser Desorption/Ionisation Time of Flight Mass Spectrometry (MALDI-TOF MS).Hypothesis/Gap statement. N. meningitidis may be misidentified by MALDI-TOF MS.Aim. To conduct genomic surveillance of oropharyngeal Neisseria spp. in order to: (i) verify MALDI-TOF MS species identification, and (ii) characterize commensal Neisseria spp. genomes.Methodology. We analysed whole genome sequence (WGS) data from 119 Neisseria spp. isolates from a surveillance programme for oropharyngeal Neisseria spp. in Belgium. Different species identification methods were compared: (i) MALDI-TOF MS, (ii) Ribosomal Multilocus Sequence Typing (rMLST) and (iii) rplF gene species identification. WGS data were used to further characterize Neisseria species found with supplementary analyses of Neisseria cinerea genomes.Results. Based on genomic species identification, isolates from the oropharyngeal Neisseria surveilence study were composed of the following species: N. meningitidis (n=23), N. subflava (n=61), N. mucosa (n=15), N. oralis (n=8), N. cinerea (n=5), N. elongata (n=3), N. lactamica (n=2), N. bacilliformis (n=1) and N. polysaccharea (n=1). Of these 119 isolates, four isolates identified as N. meningitidis (n=3) and N. subflava (n=1) by MALDI-TOF MS, were determined to be N. polysaccharea (n=1), N. cinerea (n=2) and N. mucosa (n=1) by rMLST. Phylogenetic analyses revealed that N. cinerea isolates from the general population (n=3, cluster one) were distinct from those obtained from men who have sex with men (MSM, n=2, cluster two). The latter contained genomes misidentified as N. meningitidis using MALDI-TOF MS. These two N. cinerea clusters persisted after the inclusion of published N. cinerea WGS (n=42). Both N. cinerea clusters were further defined through pangenome and Average Nucleotide Identity (ANI) analyses.Conclusion. This study provides insights into the importance of genomic genus-wide Neisseria surveillance studies to improve the characterization and identification of the Neisseria genus.},
}

*Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization/methods
*Oropharynx/microbiology
Humans
*Whole Genome Sequencing
*Multilocus Sequence Typing/methods
*Genome, Bacterial
Neisseria cinerea/genetics
Phylogeny
Neisseria/classification/genetics/isolation & purification
Belgium
Neisseria meningitidis/genetics/classification/isolation & purification
Neisseriaceae Infections/microbiology/diagnosis

@article {pmid39211246,
year = {2024},
author = {Hughes Lago, C and Blackburn, D and Kinder Pavlicek, M and Threadgill, DS},
title = {Comparative Genomic Analysis of Campylobacter rectus and Closely Related Species.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.07.26.605372},
pmid = {39211246},
issn = {2692-8205},
abstract = {Campylobacter rectus is a gram-negative, anaerobic bacterium strongly associated with periodontitis. It also causes various extraoral infections and is linked to adverse pregnancy outcomes in humans and murine models. C. rectus and related oral Campylobacters have been termed "emerging Campylobacter species" because infections by these organisms are likely underreported. Previously, no comparative methods have been used to analyze more than single C. rectus strains and until recently, very few C. rectus genomes have been publicly available. More sequenced genomes and comparative analyses are needed to study the genomic features and pathogenicity of this species. We sequenced eight new C. rectus strains and used comparative methods to identify regions of interest. An emphasis was put on the type III flagellar secretion system (T3SS), type IV secretion system (T4SS), and type VI secretion system (T6SS) because these protein complexes are important for pathogenesis in other Campylobacter species. RAST, BV-BRC, and other bioinformatics tools were used to assemble, annotate, and compare these regions in the genomes. The pan-genome of C. rectus consists of 2670 genes with core and accessory genomes of 1429 and 1241 genes, respectively. All isolates analyzed in this study have T3SS and T6SS hallmark proteins, while five of the isolates are missing a T4SS system. Twenty-one prophage clusters were identified across the panel of isolates, including four that appear intact. Overall, significant genomic islands were found, suggesting regions in the genomes that underwent horizontal gene transfer. Additionally, the high frequency of CRISPR arrays and other repetitive elements has led to genome rearrangements across the strains, including in areas adjacent to secretion system gene clusters. This study describes the substantial diversity present among C. rectus isolates and highlights tools/assays that have been developed to permit functional genomic studies. Additionally, we have expanded the studies on C. showae T4SS since we have two new C. showae genomes to report. We also demonstrate that unlike C. rectus , C showae does not demonstrate evidence of intact T6SS except for the strain CAM. The only strain of sequenced C. massilensis has neither T4SS or T6SS.},
}

@article {pmid39203545,
year = {2024},
author = {Gheorghe-Barbu, I and Dragomir, RI and Gradisteanu Pircalabioru, G and Surleac, M and Dinu, IA and Gaboreanu, MD and Czobor Barbu, I},
title = {Tracing Acinetobacter baumannii's Journey from Hospitals to Aquatic Ecosystems.},
journal = {Microorganisms},
volume = {12},
number = {8},
pages = {},
doi = {10.3390/microorganisms12081703},
pmid = {39203545},
issn = {2076-2607},
support = {ERANET 243/2021//ERANET/ ; PN-III-P4-PCE-2021-1797 (PCE 96/2022)//Unitatea Executiva Pentru Finantarea Invatamantului Superior a Cercetarii Dezvoltarii si Inovarii/ ; PN-III-P1-1.1-TE-2021-1515 (TE112/2022)//Unitatea Executiva Pentru Finantarea Invatamantului Superior a Cercetarii Dezvoltarii si Inovarii/ ; PN-III-P1-1.1-PD-2021-0540 (PD102/2022)//Unitatea Executiva Pentru Finantarea Invatamantului Superior a Cercetarii Dezvoltarii si Inovarii/ ; },
abstract = {BACKGROUND: This study provides a comprehensive analysis of Acinetobacter baumannii in aquatic environments and fish microbiota by integrating culture-dependent methods, 16S metagenomics, and antibiotic resistance profiling.

METHODS: A total of 83 A. baumannii isolates were recovered using culture-dependent methods from intra-hospital infections (IHI) and wastewater (WW) and surface water (SW) samples from two southern Romanian cities in August 2022. The antibiotic susceptibility was screened using disc diffusion, microdilution, PCR, and Whole Genome Sequencing assays.

RESULTS: The highest microbial load in the analyzed samples was found in Glina, Bucharest, for both WW and SW samples across all investigated phenotypes. For Bucharest isolates, the resistance levels corresponded to fluoroquinolones > aminoglycosides > β-lactam antibiotics. In contrast, A. baumannii from upstream SW samples in Târgoviște showed the highest resistance to aminoglycosides. The blaOXA-23 gene was frequently detected in IHI, WW, and SW isolates in Bucharest, but was absent in Târgoviște. Molecular phylogeny revealed the presence of ST10 in Târgoviște isolates and ST2 in Bucharest isolates, while other minor STs were not specifically correlated with a sampling point. Using 16S rRNA sequencing, significant differences in microbial populations between the two locations was identified. The low abundance of Alphaproteobacteria and Actinobacteria in both locations suggests environmental pressures or contamination events.

CONCLUSIONS: These findings indicate significant fecal contamination and potential public health risks, emphasizing the need for improved water quality monitoring and management.},
}

@article {pmid39203478,
year = {2024},
author = {Zhang, L and Kulyar, MF and Niu, T and Yang, S and Chen, W},
title = {Comparative Genomics of Limosilactobacillus reuteri YLR001 Reveals Genetic Diversity and Probiotic Properties.},
journal = {Microorganisms},
volume = {12},
number = {8},
pages = {},
doi = {10.3390/microorganisms12081636},
pmid = {39203478},
issn = {2076-2607},
support = {32202873//National Natural Science Foundation of China/ ; 22JR5RA885//Youth Science and Technology Fund Project of Gansu Province/ ; GAU-KYQD-2021-09//Scientific Research Start-up Funds for Openly recruited Doctors of Gansu Agricultural University/ ; },
abstract = {To gain deeper insights into the genomic characteristics of Limosilactobacillus reuteri (L. reuteri) YLR001 and uncover its probiotic properties, in the current study, a comprehensive analysis of its whole genome was conducted, explicitly exploring the genetic variations associated with different host organisms. The genome of YLR001 consisted of a circular 2,242,943 bp chromosome with a GC content of 38.84%, along with three circular plasmids (24,864, 38, 926, and 132,625 bp). Among the 2183 protein-coding sequences (CDSs), the specific genes associated with genetic adaptation and stress resistance were identified. We predicted the function of COG protein genes and analyzed the KEGG pathways. Comparative genome analysis revealed that the pan-genome contained 5207 gene families, including 475 core gene families and 941 strain-specific genes. Phylogenetic analysis revealed distinct host specificity among 20 strains of L. reuteri, highlighting substantial genetic diversity across different hosts. This study enhanced our comprehension of the genetic diversity of L. reuteri YLR001, demonstrated its potential probiotic characteristics, and established more solid groundwork for future applications.},
}

@article {pmid39201777,
year = {2024},
author = {Gureeva, MV and Muntyan, MS and Ravin, NV and Grabovich, MY},
title = {Wastewater Treatment with Bacterial Representatives of the Thiothrix Morphotype.},
journal = {International journal of molecular sciences},
volume = {25},
number = {16},
pages = {},
doi = {10.3390/ijms25169093},
pmid = {39201777},
issn = {1422-0067},
support = {20-14-00137//Russian Science Foundation/ ; },
mesh = {*Wastewater/microbiology ; *Thiothrix/metabolism/genetics ; Water Purification/methods ; Sewage/microbiology ; Sulfides/metabolism ; Waste Disposal, Fluid/methods ; },
abstract = {Bacteria of the Thiothrix morphotype, comprising the genera Thiothrix, Thiolinea and Thiofilum, are frequently encountered in domestic and industrial wastewater treatment systems, but they are usually not clearly differentiated due to the marked similarity in their morphologies. Methods ranging from light microscopy, FISH and PCR to modern high-throughput sequencing are used to identify them. The development of these bacteria in wastewater treatment systems has both advantages and disadvantages. On the one hand, the explosive growth of these bacteria can lead to activated sludge bulking or clogging of the treatment system's membranes, with a consequent decrease in the water treatment efficiency. On the other hand, members of the Thiothrix morphotype can improve the quality of granular sludge and increase the water treatment efficiency. This may be due to their capacity for sulfide oxidation, denitrification combined with the oxidation of reduced sulfur compounds, enhanced biological phosphate removal and possibly denitrifying phosphate removal. The recently obtained pangenome of the genus Thiothrix allows the explanation, at the genomic level, of the experimental results of various studies. Moreover, this review summarizes the data on the factors affecting the proliferation of representatives of the Thiothrix morphotype.},
}

*Wastewater/microbiology
*Thiothrix/metabolism/genetics
Water Purification/methods
Sewage/microbiology
Sulfides/metabolism
Waste Disposal, Fluid/methods

@article {pmid39201547,
year = {2024},
author = {Heo, S and Jung, EJ and Park, MK and Sung, MH and Jeong, DW},
title = {Evolution and Competitive Struggles of Lactiplantibacillus plantarum under Different Oxygen Contents.},
journal = {International journal of molecular sciences},
volume = {25},
number = {16},
pages = {},
doi = {10.3390/ijms25168861},
pmid = {39201547},
issn = {1422-0067},
support = {RS-2022-IP322014//Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry (IPET)/ ; },
mesh = {*Oxygen/metabolism ; *Evolution, Molecular ; Phylogeny ; Lactobacillus plantarum/genetics/metabolism ; Genome, Bacterial ; Anaerobiosis ; Animals ; Humans ; },
abstract = {Lactiplantibacillus (Lb.) plantarum is known as a benign bacterium found in various habitats, including the intestines of animals and fermented foods. Since animal intestines lack oxygen, while fermented foods provide a limited or more oxygen environment, this study aimed to investigate whether there were genetic differences in the growth of Lb. plantarum under aerobic vs. anaerobic conditions. Genomic analysis of Lb. plantarum obtained from five sources-animals, dairy products, fermented meat, fermented vegetables, and humans-was conducted. The analysis included not only an examination of oxygen-utilizing genes but also a comparative pan-genomic analysis to investigate evolutionary relationships between genomes. The ancestral gene analysis of the evolutionary pathway classified Lb. plantarum into groups A and B, with group A further subdivided into A1 and A2. It was confirmed that group A1 does not possess the narGHIJ operon, which is necessary for energy production under limited oxygen conditions. Additionally, it was found that group A1 has experienced more gene acquisition and loss compared to groups A2 and B. Despite an initial assumption that there would be genetic distinctions based on the origin (aerobic or anaerobic conditions), it was observed that such differentiation could not be attributed to the origin. However, the evolutionary process indicated that the loss of genes related to nitrate metabolism was essential in anaerobic or limited oxygen conditions, contrary to the initial hypothesis.},
}

*Oxygen/metabolism
*Evolution, Molecular
Phylogeny
Lactobacillus plantarum/genetics/metabolism
Genome, Bacterial
Anaerobiosis
Animals
Humans

@article {pmid39200041,
year = {2024},
author = {González-Fernández, A and Mencía-Ares, O and García-Iglesias, MJ and Petrocchi-Rilo, M and Miguélez-Pérez, R and Gutiérrez-Martín, CB and Martínez-Martínez, S},
title = {Virulence and Antimicrobial Resistance Characterization of Glaesserella parasuis Isolates Recovered from Spanish Swine Farms.},
journal = {Antibiotics (Basel, Switzerland)},
volume = {13},
number = {8},
pages = {},
doi = {10.3390/antibiotics13080741},
pmid = {39200041},
issn = {2079-6382},
support = {PID2019-105125RB-I00//Ministerio de Ciencia, Innovación y Universidades/ ; },
abstract = {Glaesserella (Haemophilus) parasuis, the causative agent of Glässer's disease, is present in most pig farms as an early colonizer of the upper respiratory tract. It exhibits remarkable variability in virulence and antimicrobial resistance (AMR), with virulent strains capable of inducing respiratory or systemic disease. This study aimed to characterize the virulence and the AMR profiles in 65 G. parasuis isolates recovered from Spanish swine farms. Virulence was assessed using multiplex leader sequence (LS)-PCR targeting vtaA genes, with all isolates identified as clinical (presumed virulent). Pathotyping based on ten pangenome genes revealed the virulent HPS_22970 as the most frequent (83.1%). Diverse pathotype profiles were observed, with 29 unique gene combinations and two isolates carrying only potentially non-virulent pangenome genes. AMR phenotyping showed widespread resistance, with 63.3% classified as multidrug resistant, and high resistance to clindamycin (98.3%) and tylosin (93.3%). A very strong association was found between certain pathotype genes and AMR phenotypes, notably between the virulent HPS_22970 and tetracycline resistance (p < 0.001; Φ = 0.58). This study reveals the wide diversity and complexity of G. parasuis pathogenicity and AMR phenotype, emphasizing the need for the targeted characterization of clinical isolates to ensure appropriate antimicrobial treatments and the implementation of prophylactic measures against virulent strains.},
}

@article {pmid39200037,
year = {2024},
author = {Machado, MAM and Panzenhagen, P and Lázaro, C and Rojas, M and Figueiredo, EES and Conte-Junior, CA},
title = {Unveiling the High Diversity of Clones and Antimicrobial Resistance Genes in Escherichia coli Originating from ST10 across Different Ecological Niches.},
journal = {Antibiotics (Basel, Switzerland)},
volume = {13},
number = {8},
pages = {},
doi = {10.3390/antibiotics13080737},
pmid = {39200037},
issn = {2079-6382},
support = {313119/2020-1, 140016/2021-0, and 310181/2021-6//National Council for Scientific and Technological Development/ ; E-26/200.891/2021, E-26/204.145/2022 and E-26/201.638/2024//Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro/ ; },
abstract = {In this pioneering in silico study in Peru, we aimed to analyze Escherichia coli (E. coli) genomes for antimicrobial resistance genes (ARGs) diversity and virulence and for its mobilome. For this purpose, 469 assemblies from human, domestic, and wild animal hosts were investigated. Of these genomes, three were E. coli strains (pv05, pv06, and sf25) isolated from chickens in our previous study, characterized for antimicrobial susceptibility profile, and sequenced in this study. Three other genomes were included in our repertoire for having rare cgMLSTs. The phenotypic analysis for antimicrobial resistance revealed that pv05, pv06, and sf25 strains presented multidrug resistance to antibiotics belonging to at least three classes. Our in silico analysis indicated that many Peruvian genomes included resistance genes, mainly to the aminoglycoside class, ESBL-producing E. coli, sulfonamides, and tetracyclines. In addition, through Multi-locus Sequence Typing, we found more than 180 different STs, with ST10 being the most prevalent among the genomes. Pan-genome mapping revealed that, with new lineages, the repertoire of accessory genes in E. coli increased, especially genes related to resistance and persistence, which may be carried by plasmids. The results also demonstrated several genes related to adhesion, virulence, and pathogenesis, especially genes belonging to the high pathogenicity island (HPI) from Yersinia pestis, with a prevalence of 42.2% among the genomes. The complexity of the genetic profiles of resistance and virulence in our study highlights the adaptability of the pathogen to different environments and hosts. Therefore, our in silico analysis through genome sequencing enables tracking the epidemiology of E. coli from Peru and the future development of strategies to mitigate its survival.},
}

@article {pmid39196267,
year = {2024},
author = {King, AC and Kumar, N and Mellor, KC and Hawkins, PA and McGee, L and Croucher, NJ and Bentley, SD and Lees, JA and Lo, SW},
title = {Comparison of gene-by-gene and genome-wide short nucleotide sequence-based approaches to define the global population structure of Streptococcus pneumoniae.},
journal = {Microbial genomics},
volume = {10},
number = {8},
pages = {},
doi = {10.1099/mgen.0.001278},
pmid = {39196267},
issn = {2057-5858},
mesh = {*Streptococcus pneumoniae/genetics/classification ; *Multilocus Sequence Typing/methods ; *Genome, Bacterial ; *Phylogeny ; Cluster Analysis ; Humans ; Genomics/methods ; },
abstract = {Defining the population structure of a pathogen is a key part of epidemiology, as genomically related isolates are likely to share key clinical features such as antimicrobial resistance profiles and invasiveness. Multiple different methods are currently used to cluster together closely related genomes, potentially leading to inconsistency between studies. Here, we use a global dataset of 26 306 Streptococcus pneumoniae genomes to compare four clustering methods: gene-by-gene seven-locus MLST, core genome MLST (cgMLST)-based hierarchical clustering (HierCC) assignments, life identification number (LIN) barcoding and k-mer-based PopPUNK clustering (known as GPSCs in this species). We compare the clustering results with phylogenetic and pan-genome analyses to assess their relationship with genome diversity and evolution, as we would expect a good clustering method to form a single monophyletic cluster that has high within-cluster similarity of genomic content. We show that the four methods are generally able to accurately reflect the population structure based on these metrics and that the methods were broadly consistent with each other. We investigated further to study the discrepancies in clusters. The greatest concordance was seen between LIN barcoding and HierCC (adjusted mutual information score=0.950), which was expected given that both methods utilize cgMLST, but have different methods for defining an individual cluster and different core genome schema. However, the existence of differences between the two methods shows that the selection of a core genome schema can introduce inconsistencies between studies. GPSC and HierCC assignments were also highly concordant (AMI=0.946), showing that k-mer-based methods which use the whole genome and do not require the careful selection of a core genome schema are just as effective at representing the population structure. Additionally, where there were differences in clustering between these methods, this could be explained by differences in the accessory genome that were not identified in cgMLST. We conclude that for S. pneumoniae, standardized and stable nomenclature is important as the number of genomes available expands. Furthermore, the research community should transition away from seven-locus MLST, whilst cgMLST, GPSC and LIN assignments should be used more widely. However, to allow for easy comparison between studies and to make previous literature relevant, the reporting of multiple clustering names should be standardized within the research.},
}

*Streptococcus pneumoniae/genetics/classification
*Multilocus Sequence Typing/methods
*Genome, Bacterial
*Phylogeny
Cluster Analysis
Humans
Genomics/methods

@article {pmid39194902,
year = {2024},
author = {Chen, G and Shi, G and Dai, Y and Zhao, R and Wu, Q},
title = {Graph-Based Pan-Genome Reveals the Pattern of Deleterious Mutations during the Domestication of Saccharomyces cerevisiae.},
journal = {Journal of fungi (Basel, Switzerland)},
volume = {10},
number = {8},
pages = {},
doi = {10.3390/jof10080575},
pmid = {39194902},
issn = {2309-608X},
support = {32170015//National Natural Science Foundation of China/ ; },
abstract = {The "cost of domestication" hypothesis suggests that the domestication of wild species increases the number, frequency, and/or proportion of deleterious genetic variants, potentially reducing their fitness in the wild. While extensively studied in domesticated species, this phenomenon remains understudied in fungi. Here, we used Saccharomyces cerevisiae, the world's oldest domesticated fungus, as a model to investigate the genomic characteristics of deleterious variants arising from fungal domestication. Employing a graph-based pan-genome approach, we identified 1,297,761 single nucleotide polymorphisms (SNPs), 278,147 insertion/deletion events (indels; <30 bp), and 19,967 non-redundant structural variants (SVs; ≥30 bp) across 687 S. cerevisiae isolates. Comparing these variants with synonymous SNPs (sSNPs) as neutral controls, we found that the majority of the derived nonsynonymous SNPs (nSNPs), indels, and SVs were deleterious. Heterozygosity was positively correlated with the impact of deleterious SNPs, suggesting a role of genetic diversity in mitigating their effects. The domesticated isolates exhibited a higher additive burden of deleterious SNPs (dSNPs) than the wild isolates, but a lower burden of indels and SVs. Moreover, the domesticated S. cerevisiae showed reduced rates of adaptive evolution relative to the wild S. cerevisiae. In summary, deleterious variants tend to be heterozygous, which may mitigate their harmful effects, but they also constrain breeding potential. Addressing deleterious alleles and minimizing the genetic load are crucial considerations for future S. cerevisiae breeding efforts.},
}

@article {pmid39192886,
year = {2024},
author = {Gagie, T},
title = {How to Find Long Maximal Exact Matches and Ignore Short Ones.},
journal = {Developments in language theory. Conference on Developments in Language Theory},
volume = {14791},
number = {},
pages = {131-140},
doi = {10.1007/978-3-031-66159-4_10},
pmid = {39192886},
abstract = {Finding maximal exact matches (MEMs) between strings is an important task in bioinformatics, but it is becoming increasingly challenging as geneticists switch to pangenomic references. Fortunately, we are usually interested only in the relatively few MEMs that are longer than we would expect by chance. In this paper we show that under reasonable assumptions we can find all MEMs of length at least L between a pattern of length m and a text of length n in O (m) time plus extra O (l o g n) time only for each MEM of length at least nearly L using a compact index for the text, suitable for pangenomics.},
}

@article {pmid39191402,
year = {2024},
author = {Aoun, N and Georgoulis, SJ and Avalos, JK and Grulla, KJ and Miqueo, K and Tom, C and Lowe-Power, TM},
title = {A pangenomic atlas reveals eco-evolutionary dynamics that shape type VI secretion systems in plant-pathogenic Ralstonia.},
journal = {mBio},
volume = {},
number = {},
pages = {e0032324},
doi = {10.1128/mbio.00323-24},
pmid = {39191402},
issn = {2150-7511},
abstract = {Soilborne Ralstonia solanacearum species complex (RSSC) pathogens disrupt microbial communities as they invade roots and fatally wilt plants. RSSC pathogens secrete antimicrobial toxins using a type VI secretion system (T6SS). To investigate how evolution and ecology have shaped the T6SS of these bacterial pathogens, we analyzed the T6SS gene content and architecture across the RSSC and their evolutionary relatives. Our analysis reveals that two ecologically similar Burkholderiaceae taxa, xylem-pathogenic RSSC and Paracidovorax, have convergently evolved to wield large arsenals of T6SS toxins. To understand the mechanisms underlying genomic enrichment of T6SS toxins, we compiled an atlas of 1,066 auxiliary T6SS toxin clusters ("aux" clusters) across 99 high-quality RSSC genomes. We classified 25 types of aux clusters with toxins that predominantly target lipids, nucleic acids, or unknown cellular substrates. The aux clusters were located in diverse genetic neighborhoods and had complex phylogenetic distributions, suggesting frequent horizontal gene flow. Phages and other mobile genetic elements account for most of the aux cluster acquisition on the chromosome but very little on the megaplasmid. Nevertheless, RSSC genomes were more enriched in aux clusters on the megaplasmid. Although the single, ancestral T6SS was broadly conserved in the RSSC, the T6SS has been convergently lost in atypical, non-soilborne lineages. Overall, our data suggest dynamic interplay between the lifestyle of RSSC lineages and the evolution of T6SSes with robust arsenals of toxins. This pangenomic atlas poises the RSSC as an emerging, tractable model to understand the role of the T6SS in shaping pathogen populations.IMPORTANCEWe explored the eco-evolutionary dynamics that shape the inter-microbial warfare mechanisms of a globally significant plant pathogen, the Ralstonia solanacearum species complex. We discovered that most Ralstonia wilt pathogens have evolved extensive and diverse repertoires of type VI secretion system-associated antimicrobial toxins. These expansive toxin arsenals potentially enhance the ability of Ralstonia pathogens to invade plant microbiomes, enabling them to rapidly colonize and kill their host plants. We devised a classification system to categorize the Ralstonia toxins. Interestingly, many of the toxin gene clusters are encoded on mobile genetic elements, including prophages, which may be mutualistic symbionts that enhance the inter-microbial competitiveness of Ralstonia wilt pathogens. Moreover, our findings suggest that the convergent loss of this multi-gene trait contributes to genome reduction in two vector-transmitted lineages of Ralstonia pathogens. Our findings demonstrate that the interplay between microbial ecology and pathogen lifestyle shapes the evolution of a genetically complex antimicrobial weapon.},
}

@article {pmid39192052,
year = {2024},
author = {Huang, B and Fan, C and Chen, K and Rao, J and Ou, P and Tian, C and Yang, Y and Cooper, DN and Zhao, H},
title = {VCAT: an integrated variant function annotation tools.},
journal = {Human genetics},
volume = {},
number = {},
pages = {},
pmid = {39192052},
issn = {1432-1203},
support = {2023YFF1204900//National Key Research and Development Program of China/ ; 81971190//Natural Science Foundation of China/ ; 2021A1515010256//Guangdong Key Field Research and Development Plan/ ; 202007030010//Guangzhou Science and Technology Research Plan/ ; },
abstract = {The development of sequencing technology has promoted discovery of variants in the human genome. Identifying functions of these variants is important for us to link genotype to phenotype, and to diagnose diseases. However, it usually requires researchers to visit multiple databases. Here, we presented a one-stop webserver for variant function annotation tools (VCAT, https://biomed.nscc-gz.cn/zhaolab/VCAT/) that is the first one connecting variant to functions via the epigenome, protein, drug and RNA. VCAT is also the first one to make all annotations visualized in interactive charts or molecular structures. VCAT allows users to upload data in VCF format, and download results via a URL. Moreover, VCAT has annotated a huge number (1,262,041,068) of variants collected from dbSNP, 1000 Genomes projects, gnomAD, ICGC, TCGA, and HPRC Pangenome project. For these variants, users are able to searcher their functions, related diseases and drugs from VCAT. In summary, VCAT provides a one-stop webserver to explore the potential functions of human genomic variants including their relationship with diseases and drugs.},
}

@article {pmid39191555,
year = {2024},
author = {Tiwari, VK and Saripalli, G and Sharma, PK and Poland, J},
title = {Wheat genomics: genomes, pangenomes, and beyond.},
journal = {Trends in genetics : TIG},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tig.2024.07.004},
pmid = {39191555},
issn = {0168-9525},
abstract = {There is an urgent need to improve wheat for upcoming challenges, including biotic and abiotic stresses. Sustainable wheat improvement requires the introduction of new genes and alleles in high-yielding wheat cultivars. Using new approaches, tools, and technologies to identify and introduce new genes in wheat cultivars is critical. High-quality genomes, transcriptomes, and pangenomes provide essential resources and tools to examine wheat closely to identify and manipulate new and targeted genes and alleles. Wheat genomics has improved excellently in the past 5 years, generating multiple genomes, pangenomes, and transcriptomes. Leveraging these resources allows us to accelerate our crop improvement pipelines. This review summarizes the progress made in wheat genomics and trait discovery in the past 5 years.},
}

@article {pmid39189818,
year = {2024},
author = {Olawoye, IB and Waglechner, N and McIntosh, F and Akochy, PM and Cloutier, N and Grandjean Lapierre, S and Tannir, B and Greenaway, C and Matouk, E and Poirier, L and Levesque, RC and Boyle, B and Quach, C and Soualhine, H and Batt, J and Behr, MA and Lee, RS and Guthrie, JL},
title = {Genomic Epidemiology of Mycobacterium abscessus on the Island of Montréal Not Suggestive of Healthcare-associated Person-to-Person Transmission.},
journal = {The Journal of infectious diseases},
volume = {},
number = {},
pages = {},
doi = {10.1093/infdis/jiae407},
pmid = {39189818},
issn = {1537-6613},
abstract = {BACKGROUND: Mycobacterium abscessus complex (MABC), an opportunistic nontuberculous mycobacteria (NTM), can lead to poor clinical outcomes in pulmonary infections. Conflicting data exist on person-to-person transmission of MABC within and across healthcare facilities. To investigate further, a comprehensive retrospective study across five healthcare institutions on the Island of Montréal was undertaken.

METHODS: We analyzed the genomes of 221 MABC isolates obtained from 115 individuals (2010-2018) to identify possible links. Genetic similarity, defined as ≤25 single-nucleotide polymorphisms (SNPs), was investigated through a blinded epidemiological inquiry.

RESULTS: Bioinformatics analyses identified 28 sequence types (STs), including globally observed dominant circulating clones (DCCs). Further analysis revealed 210 isolate pairs within the SNP threshold. Among these pairs, there was one possible lab contamination where isolates from different patients processed in the same lab differed by only 2 SNPs. There were 37 isolate pairs from patients who had provided specimens from the same hospital; however, epidemiological analysis found no evidence of healthcare-associated person-to-person transmission between these patients. Additionally, pan-genome analysis showed higher discriminatory power than core genome analysis for examining genomic similarity.

CONCLUSIONS: Genomics alone is insufficient to establish MABC transmission, particularly considering the genetic similarity and wide distribution of DCCs, although pan-genome analysis has the potential to add further insight. Our findings indicate that MABC infections in Montréal are unlikely attributable to healthcare-associated person-to-person transmission.},
}

@article {pmid39185728,
year = {2024},
author = {Švara, A and Sun, H and Fei, Z and Khan, A},
title = {Advancing apple genetics research: Malus coronaria and Malus ioensis genomes and a gene family-based pangenome of native North American apples.},
journal = {DNA research : an international journal for rapid publication of reports on genes and genomes},
volume = {},
number = {},
pages = {},
doi = {10.1093/dnares/dsae026},
pmid = {39185728},
issn = {1756-1663},
abstract = {Wild Malus species flourished in North America long before Europeans introduced domesticated apples. Malus coronaria and M. ioensis are native to the mid-western and eastern USA, while M. angustifolia and M. fusca grow in the southeast and west, respectively. They offer disease resistance, climate and soil adaptability, and horticultural traits for apple breeding. However, their utilization remains limited due to insufficient genomic resources and specific genetics. We report high-quality phased chromosome-scale assemblies of M. coronaria and M. ioensis, generated using long-read and conformation capture sequencing. Phylogenetic and synteny analysis indicated high relatedness between these two genomes and previously-published genome of M. angustifolia, and lower relatedness with M. fusca. Gene family-based pangenome of North American Malus identified 60,211 orthogroups containing 340,087 genes. Genes involved in basic cellular and metabolic processes, growth, and development were core to the existence of these species, whereas genes involved in secondary metabolism, stress response, and interactions with other organisms were accessory and are likely associated with adaptation to specific environments. Structural variation hotspots were mostly overlapping with high gene density. This study offers novel native North American Malus genome resources that can be used to identify genes for apple breeding and understand their evolution and adaptation.},
}

@article {pmid39182659,
year = {2024},
author = {Arjun, OK and Sethi, M and Parida, D and Dash, J and Kumar Das, S and Prakash, T and Senapati, S},
title = {Comprehensive physiological and genomic characterization of a potential probiotic strain, Lactiplantibacillus plantarum ILSF15, isolated from the gut of tribes of Odisha, India.},
journal = {Gene},
volume = {},
number = {},
pages = {148882},
doi = {10.1016/j.gene.2024.148882},
pmid = {39182659},
issn = {1879-0038},
abstract = {Characterizing probiotic features of organisms isolated from diverse environments can lead to the discovery of novel strains with promising functional features and health attributes. The present study attempts to characterize a novel probiotic strain isolated from the gut of the tribal population of Odisha, India. Based on 16S rRNA-based phylogeny, the strain was identified as a species of the Lactiplantibacillus genus and was named Lactiplantibacillus plantarum strain ILSF15. The current investigation focuses on elucidating this strain's genetic and physiological properties associated with probiotic attributes such as biosafety risk, host adaptation/survival traits, and beneficial functional features. The novel strain was observed, in vitro, exhibiting features such as acid/bile tolerance, adhesion to the host enteric epithelial cells, cholesterol assimilation, and pathogen exclusion, indicating its ability to survive the harsh environment of the human GIT and resist the growth of harmful microorganisms. Additionally, the L. plantarum ILSF15 strain was found to harbor genes associated with the metabolism and synthesis of various bioactive molecules, including amino acids, carbohydrates, lipids, and vitamins, highlighting the organism's ability to efficiently utilize diverse resources and contribute to the host's nutrition and health. Several genes involved in host adaptation/survival strategies and host-microbe interactions were also identified from the ILSF15 genome. Moreover, L. plantarum strains, in general, were found to have an open pangenome characterized by high genetic diversity and the absence of specific lineages associated with particular habitats, signifying its versatile nature and potential applications in probiotic and functional food industries.},
}

@article {pmid39181885,
year = {2024},
author = {He, H and Leng, Y and Cao, X and Zhu, Y and Li, X and Yuan, Q and Zhang, B and He, W and Wei, H and Liu, X and Xu, Q and Guo, M and Zhang, H and Yang, L and Lv, Y and Wang, X and Shi, C and Zhang, Z and Chen, W and Zhang, B and Wang, T and Yu, X and Qian, H and Zhang, Q and Dai, X and Liu, C and Cui, Y and Wang, Y and Zheng, X and Xiong, G and Zhou, Y and Qian, Q and Shang, L},
title = {The pan-tandem repeat map highlights multiallelic variants underlying gene expression and agronomic traits in rice.},
journal = {Nature communications},
volume = {15},
number = {1},
pages = {7291},
pmid = {39181885},
issn = {2041-1723},
support = {Y2023QC36//Youth Innovation Promotion Association of the Chinese Academy of Sciences (Youth Innovation Promotion Association CAS)/ ; },
mesh = {*Oryza/genetics/growth & development/metabolism ; *Quantitative Trait Loci ; *Alleles ; *Gene Expression Regulation, Plant ; *Genome, Plant ; *Tandem Repeat Sequences/genetics ; Chromosome Mapping ; Polymorphism, Single Nucleotide ; Phenotype ; Genetic Variation ; },
abstract = {Tandem repeats (TRs) are genomic regions that tandemly change in repeat number, which are often multiallelic. Their characteristics and contributions to gene expression and quantitative traits in rice are largely unknown. Here, we survey rice TR variations based on 231 genome assemblies and the rice pan-genome graph. We identify 227,391 multiallelic TR loci, including 54,416 TR variations that are absent from the Nipponbare reference genome. Only 1/3 TR variations show strong linkage with nearby bi-allelic variants (SNPs, Indels and PAVs). Using 193 panicle and 202 leaf transcriptomic data, we reveal 485 and 511 TRs act as QTLs independently of other bi-allelic variations to nearby gene expression, respectively. Using plant height and grain width as examples, we identify and validate TRs contributions to rice agronomic trait variations. These findings would enhance our understanding of the functions of multiallelic variants and facilitate rice molecular breeding.},
}

*Oryza/genetics/growth & development/metabolism
*Quantitative Trait Loci
*Alleles
*Gene Expression Regulation, Plant
*Genome, Plant
*Tandem Repeat Sequences/genetics
Chromosome Mapping
Polymorphism, Single Nucleotide
Phenotype
Genetic Variation

@article {pmid39179660,
year = {2024},
author = {Wang, S and Sun, S and Wang, Q and Chen, H and Guo, Y and Cai, M and Yin, Y and Ma, S and Wang, H},
title = {PathoTracker: an online analytical metagenomic platform for Klebsiella pneumoniae feature identification and outbreak alerting.},
journal = {Communications biology},
volume = {7},
number = {1},
pages = {1038},
pmid = {39179660},
issn = {2399-3642},
support = {32141001//National Natural Science Foundation of China (National Science Foundation of China)/ ; 81991533//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
mesh = {*Klebsiella pneumoniae/genetics/isolation & purification ; *Metagenomics/methods ; Humans ; *Disease Outbreaks ; *Klebsiella Infections/microbiology/epidemiology/diagnosis ; *Phylogeny ; China/epidemiology ; Nanopore Sequencing/methods ; Databases, Genetic ; Genome, Bacterial ; },
abstract = {Clinical metagenomics (CMg) Nanopore sequencing can facilitate infectious disease diagnosis. In China, sub-lineages ST11-KL64 and ST11-KL47 Carbapenem-resistant Klebsiella pneumoniae (CRKP) are widely prevalent. We propose PathoTracker, a specially compiled database and arranged method for strain feature identification in CMg samples and CRKP traceability. A database targeting high-prevalence horizontal gene transfer in CRKP strains and a ST11-only database for distinguishing two sub-lineages in China were created. To make the database user-friendly, facilitate immediate downstream strain feature identification from raw Nanopore metagenomic data, and avoid the need for phylogenetic analysis from scratch, we developed data analysis methods. The methods included pre-performed phylogenetic analysis, gene-isolate-cluster index and multilevel pan-genome database and reduced storage space by 10-fold and random-access memory by 52-fold compared with normal methods. PathoTracker can provide accurate and fast strain-level analysis for CMg data after 1 h Nanopore sequencing, allowing early warning of outbreaks. A user-friendly page (http://PathoTracker.pku.edu.cn/) was developed to facilitate online analysis, including strain-level feature, species identifications and phylogenetic analyses. PathoTracker proposed in this study will aid in the downstream analysis of CMg.},
}

*Klebsiella pneumoniae/genetics/isolation & purification
*Metagenomics/methods
Humans
*Disease Outbreaks
*Klebsiella Infections/microbiology/epidemiology/diagnosis
*Phylogeny
China/epidemiology
Nanopore Sequencing/methods
Databases, Genetic
Genome, Bacterial

@article {pmid39174505,
year = {2024},
author = {Fang, Y and Xiao, X and Lin, J and Lin, Q and Wang, J and Liu, K and Li, Z and Xing, J and Liu, Z and Wang, B and Qi, Y and Long, X and Zeng, X and Hu, Y and Qi, J and Qin, Y and Yang, J and Zhang, Y and Zhang, S and Ye, D and Zhang, J and Liu, J and Tang, C},
title = {Pan-genome and phylogenomic analyses highlight Hevea species delineation and rubber trait evolution.},
journal = {Nature communications},
volume = {15},
number = {1},
pages = {7232},
pmid = {39174505},
issn = {2041-1723},
mesh = {*Hevea/genetics ; *Genome, Plant ; *Phylogeny ; *Rubber/metabolism ; Plant Breeding ; Genetic Variation ; Evolution, Molecular ; Multigene Family ; },
abstract = {The para rubber tree (Hevea brasiliensis) is the world's sole commercial source of natural rubber, a vital industrial raw material. However, the narrow genetic diversity of this crop poses challenges for rubber breeding. Here, we generate high-quality de novo genome assemblies for three H. brasiliensis cultivars, two H. brasiliensis wild accessions, and three other Hevea species (H. nitida, H. pauciflora, and H. benthamiana). Through analyzing genomes of 94 Hevea accessions, we identify five distinct lineages that do not align with their previous species delineations. We discover multiple accessions with hybrid origins between these lineages, indicating incomplete reproductive isolation between them. Only two out of four wild lineages have been introduced to commercial rubber cultivars. Furthermore, we reveal that the rubber production traits emerged following the development of a large REF/SRPP gene cluster and its functional specialization in rubber-producing laticifers within this genus. These findings would enhance rubber breeding and benefit research communities.},
}

*Hevea/genetics
*Genome, Plant
*Phylogeny
*Rubber/metabolism
Plant Breeding
Genetic Variation
Evolution, Molecular
Multigene Family

@article {pmid39170454,
year = {2024},
author = {Mangal, V and Verma, LK and Singh, SK and Saxena, K and Roy, A and Karn, A and Rohit, R and Kashyap, S and Bhatt, A and Sood, S},
title = {Triumphs of genomic-assisted breeding in crop improvement.},
journal = {Heliyon},
volume = {10},
number = {15},
pages = {e35513},
pmid = {39170454},
issn = {2405-8440},
abstract = {Conventional breeding approaches have played a significant role in meeting the food demand remarkably well until now. However, the increasing population, yield plateaus in certain crops, and limited recombination necessitate using genomic resources for genomics-assisted crop improvement programs. As a result of advancements in the next-generation sequence technology, GABs have developed dramatically to characterize allelic variants and facilitate their rapid and efficient incorporation in crop improvement programs. Genomics-assisted breeding (GAB) has played an important role in harnessing the potential of modern genomic tools, exploiting allelic variation from genetic resources and developing cultivars over the past decade. The availability of pangenomes for major crops has been a significant development, albeit with varying degrees of completeness. Even though adopting these technologies is essentially determined on economic grounds and cost-effective assays, which create a wealth of information that can be successfully used to exploit the latent potential of crops. GAB has been instrumental in harnessing the potential of modern genomic resources and exploiting allelic variation for genetic enhancement and cultivar development. GAB strategies will be indispensable for designing future crops and are expected to play a crucial role in breeding climate-smart crop cultivars with higher nutritional value.},
}

@article {pmid39166875,
year = {2024},
author = {Chan, DTC and Bernstein, HC},
title = {Pangenomic landscapes shape performances of a synthetic genetic circuit across Stutzerimonas species.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0084924},
doi = {10.1128/msystems.00849-24},
pmid = {39166875},
issn = {2379-5077},
abstract = {Engineering identical genetic circuits into different species typically results in large differences in performance due to the unique cellular environmental context of each host, a phenomenon known as the "chassis-effect" or "context-dependency". A better understanding of how genomic and physiological contexts underpin the chassis-effect will improve biodesign strategies across diverse microorganisms. Here, we combined a pangenomic-based gene expression analysis with quantitative measurements of performance from an engineered genetic inverter device to uncover how genome structure and function relate to the observed chassis-effect across six closely related Stutzerimonas hosts. Our results reveal that genome architecture underpins divergent responses between our chosen non-model bacterial hosts to the engineered device. Specifically, differential expression of the core genome, gene clusters shared between all hosts, was found to be the main source of significant concordance to the observed differential genetic device performance, whereas specialty genes from respective accessory genomes were not significant. A data-driven investigation revealed that genes involved in denitrification and components of trans-membrane transporter proteins were among the most differentially expressed gene clusters between hosts in response to the genetic device. Our results show that the chassis-effect can be traced along differences among the most conserved genome-encoded functions and that these differences create a unique biodesign space among closely related species.IMPORTANCEContemporary synthetic biology endeavors often default to a handful of model organisms to host their engineered systems. Model organisms such as Escherichia coli serve as attractive hosts due to their tractability but do not necessarily provide the ideal environment to optimize performance. As more novel microbes are domesticated for use as biotechnology platforms, synthetic biologists are urged to explore the chassis-design space to optimize their systems and deliver on the promises of synthetic biology. The consequences of the chassis-effect will therefore only become more relevant as the field of biodesign grows. In our work, we demonstrate that the performance of a genetic device is highly dependent on the host environment it operates within, promoting the notion that the chassis can be considered a design variable to tune circuit function. Importantly, our results unveil that the chassis-effect can be traced along similarities in genome architecture, specifically the shared core genome. Our study advocates for the exploration of the chassis-design space and is a step forward to empowering synthetic biologists with knowledge for more efficient exploration of the chassis-design space to enable the next generation of broad-host-range synthetic biology.},
}

@article {pmid39166872,
year = {2024},
author = {Wang, L and Cheng, X and Guo, Y and Cao, J and Sun, M and Hwang, J-S and Liu, R and Fang, J},
title = {Novel isolates of hydrogen-oxidizing chemolithoautotrophic Sulfurospirillum provide insight to the functions and adaptation mechanisms of Campylobacteria in shallow-water hydrothermal vents.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0014824},
doi = {10.1128/msystems.00148-24},
pmid = {39166872},
issn = {2379-5077},
abstract = {Enhancing the availability of representative isolates from hydrothermal vents (HTVs) is imperative for comprehending the microbial processes that propel the vent ecosystem. In recent years, Campylobacteria have emerged as the predominant and ubiquitous taxon across both shallow and deep-sea vent systems. Nevertheless, only a few isolates have been cultured, primarily originating from deep-sea HTVs. Presently, no cultivable isolates of Campylobacteria are accessible in shallow water vent systems (<200 m), which exhibit markedly distinct environmental conditions from their deep-sea counterparts. In this study, we enriched a novel isolate (genus Sulfurospirillum, Campylobacteria) from shallow-water HTVs of Kueishan Island. Genomic and physiological analysis revealed that this novel Campylobacteria species grows on a variety of substrate and carbon/energy sources. The pan-genome and phenotypic comparisons with 12 previously isolated Sulfurospirillum species from different environments supported the identification of functional features in Sulfurospirillum genomes crucial for adaptation to vent environments, such as sulfur oxidation, carbon fixation, biofilm formation, and benzoate/toluene degradation, as well as diverse genes related with signal transportation. To conclude, the metabolic characteristics of this novel Campylobacteria augment our understanding of Campylobacteria spanning from deep-sea to shallow-water vent systems.IMPORTANCECampylobacteria emerge as the dominant and ubiquitous taxa within vent systems, playing important roles in the vent ecosystems. However, isolated representatives of Campylobacteria have been mainly from the deep-sea hydrothermal fields, leaving a significant knowledge gap regarding the functions, activities, and adaptation strategies of the vent microorganisms in shallow-water hydrothermal vents (HTVs). This study bridges this gap by providing insights into the phenomics and genomic diversity of genus Sulfurospirillum (order Campylobacterales, class Campylobacteria) based on data derived from a novel isolate obtained from shallow-water HTVs. Our mesophilic isolate of Sulfurospirillum not only augments the genus diversity of Campylobacteria pure cultures derived from vent systems but also serves as the inaugural reference isolate for Campylobacteria in shallow-water environments.},
}

@article {pmid39165128,
year = {2024},
author = {Trost, K and Knopp, MR and Wimmer, JLE and Tria, FDK and Martin, WF},
title = {A universal and constant rate of gene content change traces pangenome flux to LUCA.},
journal = {FEMS microbiology letters},
volume = {},
number = {},
pages = {},
doi = {10.1093/femsle/fnae068},
pmid = {39165128},
issn = {1574-6968},
abstract = {Prokaryotic genomes constantly undergo gene flux via lateral gene transfer, generating a pangenome structure consisting of a conserved core genome surrounded by a more variable accessory genome shell. Over time, flux generates change in genome content. Here we measure and compare the rate of genome flux for 5 655 prokaryotic genomes as a function of amino acid sequence divergence in 36 universally distributed proteins of the informational core (IC). We find a clock of gene content change. The long-term average rate of gene content flux is remarkably constant across all higher prokaryotic taxa sampled, whereby the size of the accessory genome-the proportion of the genome harboring gene content difference for genome pairs-varies across taxa. The proportion of species-level accessory genes per genome, varies from 0% (Chlamydia) to 30-33% (Alphaproteobacteria, Gammaproteobacteria, Clostridia). A clock-like rate of gene content change across all prokaryotic taxa sampled suggest that pangenome structure is a general feature of prokaryotic genomes and that it has been in existence since the divergence of bacteria and archaea.},
}

@article {pmid39162515,
year = {2024},
author = {Wang, Z and Hülpüsch, C and Foesel, B and Traidl-Hoffmann, C and Reiger, M and Schloter, M},
title = {Genomic and functional divergence of Staphylococcus aureus strains from atopic dermatitis patients and healthy individuals: insights from global and local scales.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0057124},
doi = {10.1128/spectrum.00571-24},
pmid = {39162515},
issn = {2165-0497},
abstract = {Atopic dermatitis (AD) is the most common chronic inflammatory skin disease worldwide and is characterized by a complex interplay with skin microbiota, with Staphylococcus aureus often abnormally more abundant in AD patients than in healthy individuals (HE). S. aureus harbors diverse strains with varied genetic compositions and functionalities, which exhibit differential connections with the severity of AD. However, the differences in S. aureus strains between AD and HE remain unclear, with most variations seen at a specific geographic level, implying spontaneous adaptations rather than systematic distinctions. This study presents genomic and functional differences between these S. aureus strains from AD and HE on both global and local levels. We observed reduced gene content diversity but increased functional variation in the global AD-associated strains. Two additional AD-dominant clusters emerged, with Cluster 1 enriched in transposases and Cluster 2 showcasing genes linked to adaptability and antibiotic resistance. Particularly, robust evidence illustrates that the lantibiotic operon of S. aureus, involved in the biosynthesis of lantibiotics, was acquired via horizontal gene transfer from environmental bacteria. Comparisons of the gene abundance profiles in functional categories also indicate limited zoonotic potential between human and animal isolates. Local analysis mirrored global gene diversity but showed distinct functional variations between AD and HE strains. Overall, this research provides foundational insights into the genomic evolution, adaptability, and antibiotic resistance of S. aureus, with significant implications for clinical microbiology.IMPORTANCEOur study uncovers significant genomic variations in Staphylococcus aureus strains associated with atopic dermatitis. We observed adaptive evolution tailored to the disease microenvironment, characterized by a smaller pan-genome than strains from healthy skin both on the global and local levels. Key functional categories driving strain diversification include "replication and repair" and "transporters," with transposases being pivotal. Interestingly, the local strains predominantly featured metal-related genes, whereas global ones emphasized antimicrobial resistances, signifying scale-dependent diversification nuances. We also pinpointed horizontal gene transfer events, indicating interactions between human-associated and environmental bacteria. These insights expand our comprehension of S. aureus's genetic adaptation in atopic dermatitis, yielding valuable implications for clinical approaches.},
}

@article {pmid39160127,
year = {2024},
author = {Song, Y and Long, C and Wang, Y and An, Y and Lu, Y},
title = {Advancements in multi-omics for nutraceutical enhancement and traits improvement in buckwheat.},
journal = {Critical reviews in biotechnology},
volume = {},
number = {},
pages = {1-26},
doi = {10.1080/07388551.2024.2373282},
pmid = {39160127},
issn = {1549-7801},
abstract = {Buckwheat (Fagopyrum spp.) is a typical pseudocereal, valued for its extensive nutraceutical potential as well as its centuries-old cultivation. Tartary buckwheat and common buckwheat have been used globally and become well-known nutritious foods due to their high quantities of: proteins, flavonoids, and minerals. Moreover, its increasing demand makes it critical to improve nutraceutical, traits and yield. In this review, bioactive compounds accumulated in buckwheat were comprehensively evaluated according to their chemical structure, properties, and physiological function. Biosynthetic pathways of flavonoids, phenolic acids, and fagopyrin were methodically summarized, with the regulation of flavonoid biosynthesis. Although there are classic synthesis pathways presented in the previous research, the metabolic flow of how these certain compounds are being synthesized in buckwheat still remains uncovered. The functional genes involved in the biosynthesis of flavonols, stress response, and plant development were identified based on multi-omics research. Furthermore, it delves into the applications of multi-omics in improving buckwheat's agronomic traits, including: yield, nutritional content, stress resilience, and bioactive compounds biosynthesis. While pangenomics combined with other omics to mine elite genes, the regulatory network and mechanism of specific agronomic traits and biosynthetic of bioactive components, and developing a more efficient genetic transformation system for genetic engineering require further investigation for the execution of breeding designs aimed at enhancing desirable traits in buckwheat. This critical review will provide a comprehensive understanding of multi-omics for nutraceutical enhancement and traits improvement in buckwheat.},
}

@article {pmid39158344,
year = {2024},
author = {Klingström, T and Zonabend König, E and Zwane, AA},
title = {Beyond the hype: using AI, big data, wearable devices, and the internet of things for high-throughput livestock phenotyping.},
journal = {Briefings in functional genomics},
volume = {},
number = {},
pages = {},
doi = {10.1093/bfgp/elae032},
pmid = {39158344},
issn = {2041-2657},
support = {//Livestock Genetics Flagship of the Livestock CGIAR Research Program/ ; },
abstract = {Phenotyping of animals is a routine task in agriculture which can provide large datasets for the functional annotation of genomes. Using the livestock farming sector to study complex traits enables genetics researchers to fully benefit from the digital transformation of society as economies of scale substantially reduces the cost of phenotyping animals on farms. In the agricultural sector genomics has transitioned towards a model of 'Genomics without the genes' as a large proportion of the genetic variation in animals can be modelled using the infinitesimal model for genomic breeding valuations. Combined with third generation sequencing creating pan-genomes for livestock the digital infrastructure for trait collection and precision farming provides a unique opportunity for high-throughput phenotyping and the study of complex traits in a controlled environment. The emphasis on cost efficient data collection mean that mobile phones and computers have become ubiquitous for cost-efficient large-scale data collection but that the majority of the recorded traits can still be recorded manually with limited training or tools. This is especially valuable in low- and middle income countries and in settings where indigenous breeds are kept at farms preserving more traditional farming methods. Digitalization is therefore an important enabler for high-throughput phenotyping for smaller livestock herds with limited technology investments as well as large-scale commercial operations. It is demanding and challenging for individual researchers to keep up with the opportunities created by the rapid advances in digitalization for livestock farming and how it can be used by researchers with or without a specialization in livestock. This review provides an overview of the current status of key enabling technologies for precision livestock farming applicable for the functional annotation of genomes.},
}

@article {pmid39158313,
year = {2024},
author = {Rana, R and Nayak, PK and Madhavan, VN and Sonti, RV and Patel, HK and Patil, PB},
title = {Comparative genomics-based insights into Xanthomonas indica, a non-pathogenic species of healthy rice microbiome with bioprotection function.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0084824},
doi = {10.1128/aem.00848-24},
pmid = {39158313},
issn = {1098-5336},
abstract = {Xanthomonas species are major pathogens of plants and have been studied extensively. There is increasing recognition of the importance of non-pathogenic species within the same genus. With this came the need to understand the genomic and functional diversity of non-pathogenic Xanthomonas (NPX) at the species and strain level. This study reports isolation and investigation into the genomic diversity and variation in NPX isolates, chiefly Xanthomonas indica, a newly discovered NPX species from rice. The study establishes the relationship of X. indica strains within clade I of Xanthomonads with another NPX species, X. sontii, also associated with rice seeds. Identification of highly diverse strains, open-pan genome, and systematic hyper-variation at the lipopolysaccharide biosynthetic locus when compared to pathogenic Xanthomonas indicates the acquisition of new functions for adaptation. Furthermore, comparative genomics studies established the absence of major virulence genes such as type III secretion system and effectors, which are present in the pathogens, and the presence of a known bacterial-killing type IV secretion system (X-T4SS). The diverse non-pathogenic strains of X. indica and X. sontii were found to protect rice from bacterial leaf blight pathogen, X. oryzae pv. oryzae (Xoo). The absence of phenotype of an X-T4SS mutant suggests redundancy in the genetic basis of the mechanisms involved in the bioprotection function, which may include multiple genetic loci, such as putative bacteriocin-encoding gene clusters and involvement of other factors such as nutrient and niche competition apart from induction of innate immunity through shared microbial-associated molecular patterns. The rice-NPX community and its pathogenic counterpart can be a promising model for understanding plant-microbe-microbiome interaction studies.IMPORTANCEThe Xanthomonas group of bacteria is known for its characteristic lifestyle as a phytopathogen. However, the discovery of non-pathogenic Xanthomonas (NPX) species is a major shift in understanding this group of bacteria. Multi-strain, in-depth genomic, evolutionary and functional studies on each of these NPX species are still lacking. This study on diverse non-pathogenic strains provides novel insights into genome diversity, dynamics, and evolutionary trends of NPX species from rice microbiome apart from its relationship with other relatives that form a sub-clade. Interestingly, we also uncovered that NPX species protect rice from pathogenic Xanthomonas species. The plant protection property shows their importance as a part of a healthy plant microbiome. Furthermore, finding an open pan-genome and large-scale variation at lipopolysaccharide biosynthetic locus indicates a significant role of the NPX community in host adaptation. The findings and high-quality genomic resources of NPX species and the strains will allow further systematic molecular and host-associated microbial community studies for plant health.},
}

@article {pmid39155697,
year = {2024},
author = {Mederos, MA and Court, CM and Dipardo, BJ and Pisegna, JR and Dawson, DW and Joe Hines, O and Donahue, TR and Graeber, TG and Girgis, MD and Tomlinson, JS},
title = {Oncogenic pathway signatures predict the risk of progression and recurrence in well-differentiated pancreatic neuroendocrine tumors.},
journal = {Journal of surgical oncology},
volume = {},
number = {},
pages = {},
doi = {10.1002/jso.27830},
pmid = {39155697},
issn = {1096-9098},
support = {P01CA168585//NCI/NIH/ ; R01CA222877//NCI/NIH/ ; R01CA227089//NCI/NIH/ ; P50CA092131//NCI/NIH/ ; //W.M. Keck Foundation/ ; //Hirshberg Foundation for Pancreatic Research/ ; },
abstract = {BACKGROUND: Pancreatic neuroendocrine tumors (pNETs) are genomically diverse tumors. The management of newly diagnosed well-differentiated pNETs is limited by a lack of sensitivity of existing biomarkers for prognostication. Our goal was to investigate the potential utility of genetic markers as a predictor of progression-free survival (PFS) and recurrence-free survival (RFS).

METHODS: Whole-exome sequencing of resected well-differentiated, low and intermediate-grade (G1 and G2) pNETs and normal adjacent tissue from patients who underwent resection from 2005 to 2015 was performed. Genetic alterations were classified using pan-genomic and oncogenic pathway classifications. Additional samples with genetic and clinicopathologic data available were obtained from the publicly available International Cancer Genome Consortium (ICGC) database and included in the analysis. The prognostic relevance of these genomic signatures on PFS and RFS was analyzed.

RESULTS: Thirty-one patients who underwent resection for pNET were identified. Genomic analysis of mutational, copy number, cytogenetic, and complex phenomena revealed similar patterns to prior studies of pNETs with relatively few somatic gene mutations but numerous instances of copy number changes. Analysis of genomic and clinicopathologic outcomes using the combined data from our study as well as the ICGC pNET cohort (n = 124 patients) revealed that the recurrent pattern of whole chromosome loss (RPCL) and metastatic disease were independently associated with disease progression. When evaluating patients with local disease at the time of resection, RPCL and alterations in the TGFβ oncogenic pathway were independently associated with the risk of recurrence.

CONCLUSIONS: Well-differentiated pNETs are genomically diverse tumors. Pathway signatures may be prognostic for predicting disease progression and recurrence.},
}

@article {pmid39151939,
year = {2024},
author = {Woodhouse, MR and Cannon, EK and Portwood, JL and Gardiner, JM and Hayford, RK and Haley, O and Andorf, CM},
title = {Tools and Resources at the Maize Genetics and Genomics Database (MaizeGDB).},
journal = {Cold Spring Harbor protocols},
volume = {},
number = {},
pages = {},
doi = {10.1101/pdb.over108430},
pmid = {39151939},
issn = {1559-6095},
abstract = {The Maize Genetics and Genomics Database (MaizeGDB) is the community resource for maize researchers, offering a suite of tools, informatics resources, and curated data sets to support maize genetics, genomics, and breeding research. Here, we provide an overview of the key resources available at MaizeGDB, including maize genomes, comparative genomics, and pan-genomics tools. This review aims to familiarize users with the range of options available for maize research and highlights the importance of MaizeGDB as a central hub for the maize research community. By providing a detailed snapshot of the database's capabilities, we hope to enable researchers to make use of MaizeGDB's resources, ultimately assisting them to better study the evolution and diversity of maize.},
}

@article {pmid39149335,
year = {2024},
author = {Ma, W and Chaisson, MJ},
title = {High-resolution global diversity copy number variation maps and association with ctyper.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.08.11.607269},
pmid = {39149335},
issn = {2692-8205},
abstract = {Genetic analysis of copy number variations (CNVs), especially in complex regions, is challenging due to reference bias and ambiguous alignment of Next-Generation Sequencing (NGS) reads to repetitive DNA. Consequently, aggregate copy numbers are typically analyzed, overlooking variation between gene copies. Pangenomes contain diverse sequences of gene copies and enable the study of sequence-resolved CNVs. We developed a method, ctyper, to discover sequence-resolved CNVs in NGS data by leveraging CNV genes from pangenomes. From 118 public assemblies, we constructed a database of 3,351 CNV genes, distinguishing each gene copy as a resolved allele. We used phylogenetic trees to organize alleles into highly similar allele-types that revealed events of linked small variants due to stratification, structural variation, conversion, and duplication. Saturation analysis showed that new samples share an average of 97.8% CNV alleles with the database. The ctyper method traces individual gene copies in NGS data to their nearest alleles in the database and identifies allele-specific copy numbers using multivariate linear regression on k-mer counts and phylogenetic clustering. Applying ctyper to 1000 Genomes Project (1kgp) samples showed Hardy-Weinberg Equilibrium on 99.3% of alleles and a 97.6% F1 score on genotypes based on 641 1kgp trios. Leave-one-out analysis on 39 assemblies matched to 1kgp samples showed that 96.5% of variants in query sequences match the genotyped allele. Genotyping 1kgp data revealed 226 population-specific CNVs, including a conversion on SMN2 to SMN1, potentially impacting Spinal Muscular Atrophy diagnosis in Africans. Our results revealed two models of CNV: recent CNVs due to ongoing duplications and polymorphic CNVs from ancient paralogs missing from the reference. To measure the functional impact of CNVs, after merging allele-types, we conducted genome-wide Quantitative Trait Locus analysis on 451 1kgp samples with Geuvadis rRNA-seqs. Using a linear mixed model, our genotyping enables the inference of relative expression levels of paralogs within a gene family. In a global evolutionary context, 150 out of 1,890 paralogs (7.94%) and 546 out of 16,628 orthologs (3.28%) had significantly different expression levels, suggesting divergent expression from original genes. Specific examples include lower expression on the converted SMN and increased expression on translocated AMY2B (GTEx pancreas data). Our method enables large cohort studies on complex CNVs to uncover hidden health impacts and overcome reference bias.},
}

@article {pmid39147372,
year = {2024},
author = {Jara-Servin, A and Mejia, G and Romero, MF and Peimbert, M and Alcaraz, LD},
title = {Unravelling the genomic and environmental diversity of the ubiquitous Solirubrobacter.},
journal = {Environmental microbiology},
volume = {26},
number = {8},
pages = {e16685},
doi = {10.1111/1462-2920.16685},
pmid = {39147372},
issn = {1462-2920},
support = {CVU 725278//Consejo Nacional de Ciencia y Tecnología/ ; IN206824//Universidad Nacional Autónoma de México, DGAPA-PAPIIT-UNAM/ ; },
mesh = {*Soil Microbiology ; *Phylogeny ; *Genome, Bacterial ; *RNA, Ribosomal, 16S/genetics ; Rhizosphere ; Genomics ; Metagenomics ; Genetic Variation ; },
abstract = {Solirubrobacter, though widespread in soils and rhizospheres, has been relatively unexplored despite its ubiquity. Previously acknowledged as a common soil bacterium, our research explores its phylogenomics, pangenomics, environmental diversity, and interactions within bacterial communities. By analysing seven genomic sequences, we have identified a pangenome consisting of 19,645 protein families, of which 2644 are shared across all studied genomes, forming the core genome. Interestingly, despite the non-motility of reported isolates, we discovered genes for flagellin and a partial flagellum assembly pathway. Examining the 16S ribosomal RNA genes of Solirubrobacter revealed substantial diversity, with 3166 operational taxonomic units identified in Mexican soils. Co-occurrence network analysis further demonstrated its significant integration within bacterial communities. Through phylogenomic scrutiny, we conclusively excluded the NCBI's GCA_009993245.1 genome from being classified as a Solirubrobacter. Our research into the metagenomic diversity of Solirubrobacter across various environments confirmed its presence in rhizospheres and certain soils, underscoring its adaptability. The geographical ubiquity of Solirubrobacter in rhizospheres raises intriguing questions regarding its potential interactions with plant hosts and the biotic and abiotic factors influencing its presence in soil. Given its ecological significance and genetic diversity, Solirubrobacter warrants further investigation as a potentially crucial yet underappreciated keystone species.},
}

*Soil Microbiology
*Phylogeny
*Genome, Bacterial
*RNA, Ribosomal, 16S/genetics
Rhizosphere
Genomics
Metagenomics
Genetic Variation

@article {pmid39144212,
year = {2024},
author = {Gtari, M and Maaoui, R and Ghodhbane-Gtari, F and Ben Slama, K and Sbissi, I},
title = {MAGs-centric crack: how long will, spore-positive Frankia and most Protofrankia, microsymbionts remain recalcitrant to axenic growth?.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1367490},
pmid = {39144212},
issn = {1664-302X},
abstract = {Nearly 50 years after the ground-breaking isolation of the primary Comptonia peregrina microsymbiont under axenic conditions, efforts to isolate a substantial number of Protofrankia and Frankia strains continue with enduring challenges and complexities. This study aimed to streamline genomic insights through comparative and predictive tools to extract traits crucial for isolating specific Frankia in axenic conditions. Pangenome analysis unveiled significant genetic diversity, suggesting untapped potential for cultivation strategies. Shared metabolic strategies in cellular components, central metabolic pathways, and resource acquisition traits offered promising avenues for cultivation. Ecological trait extraction indicated that most uncultured strains exhibit no apparent barriers to axenic growth. Despite ongoing challenges, potential caveats, and errors that could bias predictive analyses, this study provides a nuanced perspective. It highlights potential breakthroughs and guides refined cultivation strategies for these yet-uncultured strains. We advocate for tailored media formulations enriched with simple carbon sources in aerobic environments, with atmospheric nitrogen optionally sufficient to minimize contamination risks. Temperature adjustments should align with strain preferences-28-29°C for Frankia and 32-35°C for Protofrankia-while maintaining an alkaline pH. Given potential extended incubation periods (predicted doubling times ranging from 3.26 to 9.60 days, possibly up to 21.98 days), patience and rigorous contamination monitoring are crucial for optimizing cultivation conditions.},
}

@article {pmid39141833,
year = {2024},
author = {Fortin, SG and Sun, X and Jayakumar, A and Ward, BB},
title = {Nitrite-oxidizing bacteria adapted to low oxygen conditions dominate nitrite oxidation in marine oxygen minimum zones.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wrae160},
pmid = {39141833},
issn = {1751-7370},
abstract = {Nitrite is a central molecule in the nitrogen cycle because nitrite oxidation to nitrate (an aerobic process) retains fixed nitrogen in a system and its reduction to dinitrogen gas (anaerobic) reduces the fixed nitrogen inventory. Despite its acknowledged requirement for oxygen, nitrite oxidation is observed in oxygen-depleted layers of the ocean's oxygen minimum zones (OMZs), challenging the current understanding of OMZ nitrogen cycling. Previous attempts to determine whether nitrite-oxidizing bacteria in the anoxic layer differ from known nitrite oxidizers in the open ocean were limited by cultivation difficulties and sequencing depth. Here, we construct 31 draft genomes of nitrite-oxidizing bacteria from global OMZs. The distribution of nitrite oxidation rates, abundance and expression of nitrite oxidoreductase genes, and relative abundance of nitrite-oxidizing bacterial draft genomes from the same samples all show peaks in the core of the oxygen-depleted zone (ODZ) and are all highly correlated in depth profiles within the major ocean oxygen minimum zones. The ODZ nitrite oxidizers are not found in the Tara Oceans global dataset (the most complete oxic ocean dataset), and the major nitrite oxidizers found in the oxygenated ocean do not occur in ODZ waters. A pangenomic analysis shows the ODZ nitrite oxidizers have distinct gene clusters compared to oxic nitrite oxidizers and are microaerophilic. These findings all indicate the existence of nitrite oxidizers whose niche is oxygen-deficient seawater. Thus, specialist nitrite-oxidizing bacteria are responsible for fixed nitrogen retention in marine oxygen minimum zones, with implications for control of the ocean's fixed nitrogen inventory.},
}

@article {pmid39141228,
year = {2024},
author = {Jouffe, C and Dyar, KA and Uhlenhaut, NH},
title = {Chromatin Immunoprecipitation in Adipose Tissue and Adipocytes: How to Proceed and Optimize the Protocol for Transcription Factor DNA Binding.},
journal = {Methods in molecular biology (Clifton, N.J.)},
volume = {2846},
number = {},
pages = {35-45},
pmid = {39141228},
issn = {1940-6029},
mesh = {*Adipocytes/metabolism/cytology ; *Adipose Tissue/metabolism/cytology ; *Chromatin Immunoprecipitation/methods ; *DNA/metabolism/genetics ; *Transcription Factors/metabolism ; Humans ; Animals ; Protein Binding ; Chromatin/metabolism/genetics ; },
abstract = {Chromatin immunoprecipitation (ChIP) coupled to qPCR or sequencing is a crucial experiment to determine direct transcriptional regulation under the control of specific transcriptional factors or co-regulators at loci-specific or pan-genomic levels.Here we provide a reliable method for processing ChIP from adipocytes or frozen adipose tissue collection, isolation of nuclei, cross-linking of protein-DNA complexes, chromatin shearing, immunoprecipitation, and DNA purification. We also discuss critical steps for optimizing the experiment to perform a successful ChIP in lipid-rich cells/tissues.},
}

*Adipocytes/metabolism/cytology
*Adipose Tissue/metabolism/cytology
*Chromatin Immunoprecipitation/methods
*DNA/metabolism/genetics
*Transcription Factors/metabolism
Humans
Animals
Protein Binding
Chromatin/metabolism/genetics

@article {pmid39140725,
year = {2024},
author = {Lemieux, JE},
title = {Analysis of the Borreliaceae Pangenome Reveals a Distinct Genomic Architecture Conserved Across Phylogenetic Scales.},
journal = {The Journal of infectious diseases},
volume = {230},
number = {Supplement_1},
pages = {S51-S61},
doi = {10.1093/infdis/jiae256},
pmid = {39140725},
issn = {1537-6613},
support = {K99/R00AI148604/NH/NIH HHS/United States ; },
mesh = {*Genome, Bacterial ; *Phylogeny ; Humans ; Borrelia/genetics/classification ; Genomics ; Lyme Disease/microbiology ; },
abstract = {The family Borreliaceae contains arthropod-borne spirochetes that cause two widespread human diseases, Lyme disease and relapsing fever. Lyme disease is a subacute, progressive illness with variable stage and tissue manifestations. Relapsing fever is an acute febrile illness with prominent bacteremia that may recur and disseminate, particularly to the nervous system. Clinical heterogeneity is a hallmark of both diseases. While human clinical manifestations are influenced by a wide variety of factors, including immune status and host genetic susceptibility, there is evidence that Borreliaceae microbial factors influence the clinical manifestations of human disease caused by this family of spirochetes. Despite these associations, the spirochete genes that influence the severity and manifestations of human disease are, for the most part, unknown. Recent work has identified lineage-specific expansions of lipoproteome-rich accessory genome elements in virulent clones of Borrelia burgdorferi. Using publicly available genome assemblies, it is shown that all Borreliaceae lineages for which sufficient sequence data are available harbor a similar pattern of strongly structured, lineage-specific expansions in their accessory genomes, particularly among lipoproteins, and that this pattern holds across phylogenetic scales including genera, species, and genotypes. The relationships among pangenome elements suggest that infrequent episodes of marked genomic change followed by clonal expansion in geographically and enzootically structured populations may account for the unique lineage structure of Borreliaceae. This analysis informs future genotype-phenotype studies among Borreliaceae and lays a foundation for studies of individual gene function guided by phylogenetic patterns of conservation, diversification, gain, and/or loss.},
}

*Genome, Bacterial
*Phylogeny
Humans
Borrelia/genetics/classification
Genomics
Lyme Disease/microbiology

@article {pmid39138795,
year = {2024},
author = {Perrin, C and Coutts, M and Dadone-Montaudié, B},
title = {Subungual melanoma: molecular analysis of 31 cases from early stage to invasive melanoma.},
journal = {Histopathology},
volume = {},
number = {},
pages = {},
doi = {10.1111/his.15297},
pmid = {39138795},
issn = {1365-2559},
abstract = {AIMS: The distinction between the benign subungual melanocytic lesions and an early lesion of subungual melanoma (SUM) remains a diagnostic challenge. We evaluated the routine diagnostic utility of array Comparative Genomic Hybridization (aCGH) to detect whole-genome copy number variations (CNV) as well as targeted next-generation sequencing (NGS) in SUM.

METHODS AND RESULTS: This retrospective study included 20 cases of in situ SUM and 11 cases of invasive SUM. Analysis by aCGH detected common oncogene amplifications in all but one case of invasive SUM (n = 10) and in all cases of in situ SUM with a melanocyte count (MC) >45/mm (n = 4 true positive) and the average number of CNV was 8.5. Thirteen remaining cases of in situ SUM gave false negative results (n = 13), owing to a lack of sufficient melanocytes to analyse (median MC of 35.35; range: 10.16-39.5). Molecular analysis failed in four cases (three in situ SUM and one invasive SUM) due to insufficient amounts of DNA. Across the whole cohort, the sensitivity of aCGH was 52%, but when adjusting the cutoff to MC >45/mm, the sensitivity was 93%. Targeted NGS was less informative than aCGH analyses in our series of SUM.

CONCLUSION: To distinguish malignant from benign lesions, especially in situ SUM versus atypical lentiginous melanocytic proliferations, aCGH analysis should be performed when the MC is above 45 melanocytes per linear millimetre. This pangenomic method can detect oncogene amplifications, as well as a number of CNV >3, which strongly support the diagnosis of malignancy.},
}

@article {pmid39137112,
year = {2024},
author = {Feng, Y and Yang, Y and Hu, Y and Xiao, Y and Xie, Y and Wei, L and Wen, H and Zhang, L and McNally, A and Zong, Z},
title = {Population genomics uncovers global distribution, antimicrobial resistance, and virulence genes of the opportunistic pathogen Klebsiella aerogenes.},
journal = {Cell reports},
volume = {43},
number = {8},
pages = {114602},
doi = {10.1016/j.celrep.2024.114602},
pmid = {39137112},
issn = {2211-1247},
abstract = {Klebsiella aerogenes is an understudied and clinically important pathogen. We therefore investigate its population structure by genome analysis aligned with metadata. We sequence 130 non-duplicated K. aerogenes clinical isolates and identify two inter-patient transmission events. We then retrieve all publicly available K. aerogenes genomes (n = 1,026, accessed by January 1, 2023) and analyze them with our 130 genomes. We develop a core-genome multi-locus sequence-typing scheme. We find that K. aerogenes is a species complex comprising four phylogroups undergoing evolutionary divergence, likely forming three species. We delineate remarkable clonal diversity and identify three worldwide-distributed carbapenemase-encoding clonal clusters, representing high-risk lineages. We uncover that K. aerogenes has an open genome equipped by a large arsenal of antimicrobial resistance genes. We identify two genetic regions specific for K. aerogenes, encoding a type VI secretion system and flagella/chemotaxis for motility, respectively, both contributing to the virulence. These results provide much-needed insights into the population structure and pan-genomes of K. aerogenes.},
}

@article {pmid39134411,
year = {2024},
author = {Kuronen, J and Horsfield, ST and Pöntinen, AK and Mallawaarachchi, S and Arredondo-Alonso, S and Thorpe, H and Gladstone, RA and Willems, RJL and Bentley, SD and Croucher, NJ and Pensar, J and Lees, JA and Tonkin-Hill, G and Corander, J},
title = {Pangenome-spanning epistasis and coselection analysis via de Bruijn graphs.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.278485.123},
pmid = {39134411},
issn = {1549-5469},
abstract = {Studies of bacterial adaptation and evolution are hampered by the difficulty of measuring traits such as virulence, drug resistance, and transmissibility in large populations. In contrast, it is now feasible to obtain high-quality complete assemblies of many bacterial genomes thanks to scalable high-accuracy long-read sequencing technologies. To exploit this opportunity, we introduce a phenotype- and alignment-free method for discovering coselected and epistatically interacting genomic variation from genome assemblies covering both core and accessory parts of genomes. Our approach uses a compact colored de Bruijn graph to approximate the intragenome distances between pairs of loci for a collection of bacterial genomes to account for the impacts of linkage disequilibrium (LD). We demonstrate the versatility of our approach to efficiently identify associations between loci linked with drug resistance and adaptation to the hospital niche in the major human bacterial pathogens Streptococcus pneumoniae and Enterococcus faecalis.},
}

@article {pmid39133351,
year = {2024},
author = {Yin, J and He, M and Liu, XX and Ren, CB and Liu, HH and Luo, H and Chen, G and Wang, ZF and Debnath, SC and Wang, PM and Chen, HX and Zheng, DQ},
title = {Peteryoungia algae sp. nov. isolated from seaweeds of Gouqi Island, China, and its unique genetic features among Peteryoungia strains.},
journal = {Antonie van Leeuwenhoek},
volume = {117},
number = {1},
pages = {112},
pmid = {39133351},
issn = {1572-9699},
support = {LDT23D06022D06//National Natural Science Foundation of Zhejiang Province/ ; LDT23D06022D06//National Natural Science Foundation of Zhejiang Province/ ; LDT23D06022D06//National Natural Science Foundation of Zhejiang Province/ ; LDT23D06022D06//National Natural Science Foundation of Zhejiang Province/ ; LDT23D06022D06//National Natural Science Foundation of Zhejiang Province/ ; ZDYF2024SHFZ046//Key Research and Development Program of Hainan Province/ ; ZDYF2024SHFZ046//Key Research and Development Program of Hainan Province/ ; ZDYF2024SHFZ046//Key Research and Development Program of Hainan Province/ ; ZDYF2024SHFZ046//Key Research and Development Program of Hainan Province/ ; ZDYF2024SHFZ046//Key Research and Development Program of Hainan Province/ ; 226-2024-00019//Fundamental Research Funds for the Central Universities/ ; 226-2024-00019//Fundamental Research Funds for the Central Universities/ ; 226-2024-00019//Fundamental Research Funds for the Central Universities/ ; 226-2024-00019//Fundamental Research Funds for the Central Universities/ ; 226-2024-00019//Fundamental Research Funds for the Central Universities/ ; SKJC-2024-02-003//Project of Sanya Yazhou Bay Science and Technology City/ ; },
mesh = {*Phylogeny ; China ; *RNA, Ribosomal, 16S/genetics ; *Seaweed/microbiology ; *DNA, Bacterial/genetics ; *Base Composition ; *Fatty Acids/analysis/chemistry ; Bacterial Typing Techniques ; Genome, Bacterial ; Sequence Analysis, DNA ; Islands ; Nucleic Acid Hybridization ; },
abstract = {A Gram-stain-negative, light khaki, strictly aerobic, rod-shaped, motile via multiple flagella, and catalase- and oxidase-positive bacterium, designated as SSM4.3[T], was isolated from the seaweed of Gouqi Island in the East China Sea. The novel isolate grows at 0-5.0% NaCl concentrations (w/v) (optimum 1%), pH 5.0-9.0 (optimum pH 7.0), and 15-37 °C (optimum 30 °C). The 16S rRNA gene sequences-based phylogeny indicates that the novel marine isolate belongs to the family Rhizobiaceae and that it shared the greatest sequence similarity (98.9%) with Peteryoungia rhizophila CGMCC 1.15691[T]. This classification was also supported by phylogenetic analysis using core genes. The predominant fatty acids (≥ 10%) of the strain were identified as C18:1 ω7c/C18:1 ω6c. Q-10 was identified as the major isoprenoid quinone, with trace levels of Q-9 present. The major polar lipids were identified as diphosphatidylglycerol, phosphatidylethanolamine and phosphatidylglycerol. The complete genome size of strain SSM4.3[T] is 4.39 Mb with a DNA G+C content of 61.3%. The average nucleotide identity, digital DNA-DNA hybridization, and average amino acid identity values between the genomes of strain SSM4.3[T] and its closely related representatives were 74.80-86.93%, 20.00-32.30%, and 70.30-91.52%, respectively. Phylogenetic analysis, grounded on the core genes, reveals the evolutionary relationship between SSM4.3[T] and other Peteryoungia strains. Pan-genomics analysis of 8 previously classified Peteryoungia species and SSM4.3[T] revealed their unique genetic features and functions. Overall, strain SSM4.3[T] was considered to be a new species of the Peteryoungia genus; the name Peteryoungia algae sp. nov. has been proposed, with type strain SSM4.3[T] (= LMG 32561 = MCCC 1K07170).},
}

*Phylogeny
China
*RNA, Ribosomal, 16S/genetics
*Seaweed/microbiology
*DNA, Bacterial/genetics
*Base Composition
*Fatty Acids/analysis/chemistry
Bacterial Typing Techniques
Genome, Bacterial
Sequence Analysis, DNA
Islands
Nucleic Acid Hybridization

@article {pmid39132840,
year = {2024},
author = {Vale, FF and Roberts, RJ and Kobayashi, I and Camargo, MC and Rabkin, CS},
title = {Gene content, phage cycle regulation model and prophage inactivation disclosed by prophage genomics in the Helicobacter pylori Genome Project.},
journal = {Gut microbes},
volume = {16},
number = {1},
pages = {2379440},
doi = {10.1080/19490976.2024.2379440},
pmid = {39132840},
issn = {1949-0984},
mesh = {*Helicobacter pylori/genetics/virology ; *Prophages/genetics/physiology ; *Genome, Bacterial ; Humans ; *Phylogeny ; *Genomics ; Helicobacter Infections/microbiology ; },
abstract = {Prophages can have major clinical implications through their ability to change pathogenic bacterial traits. There is limited understanding of the prophage role in ecological, evolutionary, adaptive processes and pathogenicity of Helicobacter pylori, a widespread bacterium causally associated with gastric cancer. Inferring the exact prophage genomic location and completeness requires complete genomes. The international Helicobacter pylori Genome Project (HpGP) dataset comprises 1011 H. pylori complete clinical genomes enriched with epigenetic data. We thoroughly evaluated the H. pylori prophage genomic content in the HpGP dataset. We investigated population evolutionary dynamics through phylogenetic and pangenome analyses. Additionally, we identified genome rearrangements and assessed the impact of prophage presence on bacterial gene disruption and methylome. We found that 29.5% (298) of the HpGP genomes contain prophages, of which only 32.2% (96) were complete, minimizing the burden of prophage carriage. The prevalence of H. pylori prophage sequences was variable by geography and ancestry, but not by disease status of the human host. Prophage insertion occasionally results in gene disruption that can change the global bacterial epigenome. Gene function prediction allowed the development of the first model for lysogenic-lytic cycle regulation in H. pylori. We have disclosed new prophage inactivation mechanisms that appear to occur by genome rearrangement, merger with other mobile elements, and pseudogene accumulation. Our analysis provides a comprehensive framework for H. pylori prophage biological and genomics, offering insights into lysogeny regulation and bacterial adaptation to prophages.},
}

*Helicobacter pylori/genetics/virology
*Prophages/genetics/physiology
*Genome, Bacterial
Humans
*Phylogeny
*Genomics
Helicobacter Infections/microbiology

@article {pmid39130480,
year = {2024},
author = {Hasnat, S and Hoque, MN and Mahbub, MM and Sakif, TI and Shahinuzzaman, ADA and Islam, T},
title = {Pantothenate kinase: A promising therapeutic target against pathogenic Clostridium species.},
journal = {Heliyon},
volume = {10},
number = {14},
pages = {e34544},
pmid = {39130480},
issn = {2405-8440},
abstract = {Current treatment of clostridial infections includes broad-spectrum antibiotics and antitoxins, yet antitoxins are ineffective against all Clostridiumspecies. Moreover, rising antimicrobial resistance (AMR) threatens treatment effectiveness and public health. This study therefore aimed to discover a common drug target for four pathogenic clostridial species, Clostridium botulinum, C. difficile, C. tetani, and C. perfringens through an in-silico core genomic approach. Using four reference genomes of C. botulinum, C. difficile, C. tetani, and C. perfringens, we identified 1484 core genomic proteins (371/genome) and screened them for potential drug targets. Through a subtractive approach, four core proteins were finally identified as drug targets, represented by type III pantothenate kinase (CoaX) and, selected for further analyses. Interestingly, the CoaX is involved in the phosphorylation of pantothenate (vitamin B5), which is a critical precursor for coenzyme A (CoA) biosynthesis. Investigation of druggability analysis on the identified drug target reinforces CoaX as a promising novel drug target for the selected Clostridium species. During the molecular screening of 1201 compounds, a known agonist drug compound (Vibegron) showed strong inhibitory activity against targeted clostridial CoaX. Additionally, we identified tazobactam, a beta-lactamase inhibitor, as effective against the newly proposed target, CoaX. Therefore, identifying CoaX as a single drug target effective against all four clostridial pathogens presents a valuable opportunity to develop a cost-effective treatment for multispecies clostridial infections.},
}

@article {pmid39120932,
year = {2024},
author = {Krisna, MA and Jolley, KA and Monteith, W and Boubour, A and Hamers, RL and Brueggemann, AB and Harrison, OB and Maiden, MCJ},
title = {Development and implementation of a core genome multilocus sequence typing scheme for Haemophilus influenzae.},
journal = {Microbial genomics},
volume = {10},
number = {8},
pages = {},
doi = {10.1099/mgen.0.001281},
pmid = {39120932},
issn = {2057-5858},
mesh = {*Haemophilus influenzae/genetics/classification ; *Multilocus Sequence Typing/methods ; *Phylogeny ; *Genome, Bacterial ; Humans ; Haemophilus Infections/microbiology ; Genetic Variation ; },
abstract = {Haemophilus influenzae is part of the human nasopharyngeal microbiota and a pathogen causing invasive disease. The extensive genetic diversity observed in H. influenzae necessitates discriminatory analytical approaches to evaluate its population structure. This study developed a core genome multilocus sequence typing (cgMLST) scheme for H. influenzae using pangenome analysis tools and validated the cgMLST scheme using datasets consisting of complete reference genomes (N = 14) and high-quality draft H. influenzae genomes (N = 2297). The draft genome dataset was divided into a development dataset (N = 921) and a validation dataset (N = 1376). The development dataset was used to identify potential core genes, and the validation dataset was used to refine the final core gene list to ensure the reliability of the proposed cgMLST scheme. Functional classifications were made for all the resulting core genes. Phylogenetic analyses were performed using both allelic profiles and nucleotide sequence alignments of the core genome to test congruence, as assessed by Spearman's correlation and ordinary least square linear regression tests. Preliminary analyses using the development dataset identified 1067 core genes, which were refined to 1037 with the validation dataset. More than 70% of core genes were predicted to encode proteins essential for metabolism or genetic information processing. Phylogenetic and statistical analyses indicated that the core genome allelic profile accurately represented phylogenetic relatedness among the isolates (R [2] = 0.945). We used this cgMLST scheme to define a high-resolution population structure for H. influenzae, which enhances the genomic analysis of this clinically relevant human pathogen.},
}

*Haemophilus influenzae/genetics/classification
*Multilocus Sequence Typing/methods
*Phylogeny
*Genome, Bacterial
Humans
Haemophilus Infections/microbiology
Genetic Variation

@article {pmid39116952,
year = {2024},
author = {Khan, MAS and Chaity, SC and Hosen, A and Rahman, SR},
title = {Genomic epidemiology of multidrug-resistant clinical Acinetobacter baumannii in Bangladesh.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105656},
doi = {10.1016/j.meegid.2024.105656},
pmid = {39116952},
issn = {1567-7257},
abstract = {The rising frequency of multidrug-resistant (MDR) Acinetobacter baumannii infections represents a significant public health challenge in Bangladesh. Genomic analysis of bacterial pathogens enhances surveillance and control efforts by providing insights into genetic diversity, antimicrobial resistance (AMR) profiles, and transmission dynamics. In this study, we conducted a comprehensive bioinformatic analysis of 82 whole-genome sequences (WGS) of A. baumannii from Bangladesh to understand their genomic epidemiological characteristics. WGS of the MDR and biofilm-forming A. baumannii strain S1C revealed the presence of 28 AMR genes, predicting its pathogenicity and classification within sequence type ST2. Multi-locus sequence typing (MLST) genotyping suggested heterogeneity in the distribution of clinical A. baumannii strains in Bangladesh, with a predominance of ST575. The resistome diversity was evident from the detection of 82 different AMR genes, with antibiotic inactivation being the most prevalent resistance mechanism. All strains were predicted to be multidrug-resistant. The observed virulence genes were associated with immune evasion, biofilm formation, adherence, nutrient acquisition, effector delivery, and other mechanisms. Mobile genetic elements carrying AMR genes were predicted in 68.29% (N = 56) of the genomes. The "open" state of the pan-genome and a high proportion of accessory genes highlighted the genome plasticity and diversity of A. baumannii in Bangladesh. Additionally, phylogenomic analysis indicated clustering of A. baumannii strains into three separate clades according to sequence type. In summary, our findings offer detailed insights into the genomic landscape of A. baumannii in Bangladesh, contributing to our understanding of its epidemiology and pathogenicity and informing strategies to combat this pathogen.},
}

@article {pmid39116702,
year = {2024},
author = {Singhvi, N and Talwar, C and Nagar, S and Verma, H and Kaur, J and Mahato, NK and Ahmad, N and Mondal, K and Gupta, V and Lal, R},
title = {Insights into the radiation and oxidative stress mechanisms in genus Deinococcus.},
journal = {Computational biology and chemistry},
volume = {112},
number = {},
pages = {108161},
doi = {10.1016/j.compbiolchem.2024.108161},
pmid = {39116702},
issn = {1476-928X},
abstract = {Deinococcus species, noted for their exceptional resistance to DNA-damaging environmental stresses, have piqued scientists' interest for decades. This study dives into the complex mechanisms underpinning radiation resistance in the Deinococcus genus. We have examined the genomes of 82 Deinococcus species and classified radiation-resistance proteins manually into five unique curated categories: DNA repair, oxidative stress defense, Ddr and Ppr proteins, regulatory proteins, and miscellaneous resistance components. This classification reveals important information about the various molecular mechanisms used by these extremophiles which have been less explored so far. We also investigated the presence or lack of these proteins in the context of phylogenetic relationships, core, and pan-genomes, which offered light on the evolutionary dynamics of radiation resistance. This comprehensive study provides a deeper understanding of the genetic underpinnings of radiation resistance in the Deinococcus genus, with potential implications for understanding similar mechanisms in other organisms using an interactomics approach. Finally, this study reveals the complexities of radiation resistance mechanisms, providing a comprehensive understanding of the genetic components that allow Deinococcus species to flourish under harsh environments. The findings add to our understanding of the larger spectrum of stress adaption techniques in bacteria and may have applications in sectors ranging from biotechnology to environmental research.},
}

@article {pmid39116055,
year = {2024},
author = {Rojas-Vargas, J and Rebollar, EA and Sanchez-Flores, A and Pardo-López, L},
title = {A comparative genomic study of a hydrocarbon-degrading marine bacterial consortium.},
journal = {PloS one},
volume = {19},
number = {8},
pages = {e0303363},
doi = {10.1371/journal.pone.0303363},
pmid = {39116055},
issn = {1932-6203},
mesh = {*Biodegradation, Environmental ; *Hydrocarbons/metabolism ; *Phylogeny ; *Genome, Bacterial ; *Genomics/methods ; Microbial Consortia/genetics ; Bacteria/genetics/metabolism/classification ; Seawater/microbiology ; },
abstract = {Ocean oil pollution has a large impact on the environment and the health of living organisms. Bioremediation cleaning strategies are promising eco-friendly alternatives for tackling this problem. Previously, we designed and reported a hydrocarbon (HC) degrading microbial consortium of four marine strains belonging to the species Alloalcanivorax xenomutans, Halopseudomonas aestusnigri, Paenarthrobacter sp., and Pseudomonas aeruginosa. However, the knowledge about the metabolic potential of this bacterial consortium for HC bioremediation is not yet well understood. Here, we analyzed the complete genomes of these marine bacterial strains accompanied by a phylogenetic reconstruction along with 138 bacterial strains. Synteny between complete genomes of the same species or genus, revealed high conservation among strains of the same species, covering over 91% of their genomic sequences. Functional predictions highlighted a high abundance of genes related to HC degradation, which may result in functional redundancy within the consortium; however, unique and complete gene clusters linked to aromatic degradation were found in the four genomes, suggesting substrate specialization. Pangenome gain and loss analysis of genes involved in HC degradation provided insights into the evolutionary history of these capabilities, shedding light on the acquisition and loss of relevant genes related to alkane and aromatic degradation. Our work, including comparative genomic analyses, identification of secondary metabolites, and prediction of HC-degrading genes, enhances our understanding of the functional diversity and ecological roles of these marine bacteria in crude oil-contaminated marine environments and contributes to the applied knowledge of bioremediation.},
}

*Biodegradation, Environmental
*Hydrocarbons/metabolism
*Phylogeny
*Genome, Bacterial
*Genomics/methods
Microbial Consortia/genetics
Bacteria/genetics/metabolism/classification
Seawater/microbiology

@article {pmid39114027,
year = {2024},
author = {Saikat, TA and Sayem Khan, MA and Islam, MS and Tasnim, Z and Ahmed, S},
title = {Characterization and genome mining of Bacillus subtilis BDSA1 isolated from river water in Bangladesh: A promising bacterium with diverse biotechnological applications.},
journal = {Heliyon},
volume = {10},
number = {14},
pages = {e34369},
pmid = {39114027},
issn = {2405-8440},
abstract = {The metabolic versatility of Bacillus subtilis makes it useful for a wide range of applications in biotechnology, from bioremediation to industrially important metabolite production. Understanding the molecular attributes of the biocontrol characteristics of B. subtilis is necessary for its tailored use in the environment and industry. Therefore, the present study aimed to conduct phenotypic characterization and whole genome analysis of the B. subtilis BDSA1 isolated from polluted river water from Dhaka, Bangladesh to explore its biotechnological potential. The chromium reduction capacity at 100 ppm Cr (VI) showed that B. subtilis BDSA1 reduced 40 % of Cr (VI) within 24hrs at 37 °C. Exposure of this bacterium to 200 ppm cadmium resulted in 43 % adsorption following one week of incubation at 37 °C. Molecular detection of chrA and czcC gene confirmed chromium and cadmium resistance characteristics of BDSA1. The size of the genome of the B. subtilis BDSA1 was 4.2 Mb with 43.4 % GC content. Genome annotation detected the presence of numerous genes involved in the degradation of xenobiotics, resistance to abiotic stress, production of lytic enzymes, siderophore formation, and plant growth promotion. The assembled genome also carried chromium, cadmium, copper, and arsenic resistance-related genes, notably cadA, czcD, czrA, arsB etc. Genome mining revealed six biosynthetic gene clusters for bacillaene, bacillibacin, bacilysin, subtilosin, fengycin and surfactin. Importantly, BDSA1 was predicted to be non-pathogenic to humans and had only two acquired antimicrobial resistance genes. The pan-genome analysis showed the openness of the B. subtilis pan-genome. Our findings suggested that B. subtilis BDSA1 might be a promising candidate for diverse biotechnological uses.},
}

@article {pmid39113613,
year = {2024},
author = {Chen, M and Trotter, VV and Walian, PJ and Chen, Y and Lopez, R and Lui, LM and Nielsen, TN and Malana, RG and Thorgersen, MP and Hendrickson, AJ and Carion, H and Deutschbauer, AM and Petzold, CJ and Smith, HJ and Arkin, AP and Adams, MWW and Fields, MW and Chakraborty, R},
title = {Molecular mechanisms and environmental adaptations of flagellar loss and biofilm growth of Rhodanobacter under environmental stress.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wrae151},
pmid = {39113613},
issn = {1751-7370},
abstract = {Biofilms aid bacterial adhesion to surfaces via direct and indirect mechanisms, and formation of biofilms is considered as an important strategy for adaptation and survival in sub-optimal environmental conditions. However, the molecular underpinnings of biofilm formation in subsurface sediment/groundwater ecosystems where microorganisms often experience fluctuations in nutrient input, pH, nitrate or metal concentrations is underexplored. We examined biofilm formation under different nutrient, pH, metal, and nitrate regimes of 16 Rhodanobacter strains isolated from subsurface groundwater wells spanning diverse pH (3.5 to 5) and nitrate levels (13.7 to 146 mM). Eight Rhodanobacter strains demonstrated significant biofilm growth under low pH, suggesting adaptation to survive and grow at low pH. Biofilms intensified under aluminum stress, particularly in strains possessing fewer genetic traits associated with biofilm formation warranting further investigation. Through RB-TnSeq, proteomics, use of specific mutants and transmission electron microscopy analysis, we discovered flagellar loss under aluminum stress, indicating a potential relationship between motility, metal tolerance, and biofilm growth. Comparative genomic analyses revealed absence of flagella and chemotaxis genes, and presence of putative Type VI secretion system in the high biofilm-forming strain FW021-MT20. This study identifies genetic determinants associated with biofilm growth in a predominant environmental genus, Rhodanobacter, under metal stress and identifies traits aiding survival and adaptation to contaminated subsurface environments.},
}

@article {pmid39113147,
year = {2024},
author = {Wang, Z and Wang, M and Du, L},
title = {Public perceptions of international genetic information sharing for biomedical research in China: a case study of the social media debate on the article "A Pangenome Reference of 36 Chinese Populations" published in Nature.},
journal = {Human genomics},
volume = {18},
number = {1},
pages = {86},
pmid = {39113147},
issn = {1479-7364},
support = {MYRG2020-00096-FLL//Universidade de Macau/ ; },
abstract = {BACKGROUND: The international disclosure of Chinese human genetic data continues to be a contentious issue in China, generating public debates in both traditional and social media channels. Concerns have intensified after Chinese scientists' research on pangenome data was published in the prestigious journal Nature.

METHODS: This study scrutinized microblogs posted on Weibo, a popular Chinese social media site, in the two months immediately following the publication (June 14, 2023-August 21, 2023). Content analysis was conducted to assess the nature of public responses, justifications for positive or negative attitudes, and the users' overall knowledge of how Chinese human genetic information is regulated and managed in China.

RESULTS: Weibo users displayed contrasting attitudes towards the article's public disclose of pangenome research data, with 18% positive, 64% negative, and 18% neutral. Positive attitudes came primarily from verified government and media accounts, which praised the publication. In contrast, negative attitudes originated from individual users who were concerned about national security and health risks and often believed that the researchers have betrayed China. The benefits of data sharing highlighted in the commentaries included advancements in disease research and scientific progress. Approximately 16% of the microblogs indicated that Weibo users had misunderstood existing regulations and laws governing data sharing and stewardship.

CONCLUSIONS: Based on the predominantly negative public attitudes toward scientific data sharing established by our study, we recommend enhanced outreach by scientists and scientific institutions to increase the public understanding of developments in genetic research, international data sharing, and associated regulations. Additionally, governmental agencies can alleviate public fears and concerns by being more transparent about their security reviews of international collaborative research involving Chinese human genetic data and its cross-border transfer.},
}

@article {pmid39113037,
year = {2024},
author = {Kuo, WH and Wright, SJ and Small, LL and Olsen, KM},
title = {De novo genome assembly of white clover (Trifolium repens L.) reveals the role of copy number variation in rapid environmental adaptation.},
journal = {BMC biology},
volume = {22},
number = {1},
pages = {165},
pmid = {39113037},
issn = {1741-7007},
support = {IOS-1557770//Directorate for Biological Sciences/ ; DEB-1601641//Division of Environmental Biology/ ; DGE-1143954//Division of Graduate Education/ ; },
abstract = {BACKGROUND: White clover (Trifolium repens) is a globally important perennial forage legume. This species also serves as an eco-evolutionary model system for studying within-species chemical defense variation; it features a well-studied polymorphism for cyanogenesis (HCN release following tissue damage), with higher frequencies of cyanogenic plants favored in warmer locations worldwide. Using a newly generated haplotype-resolved genome and two other long-read assemblies, we tested the hypothesis that copy number variants (CNVs) at cyanogenesis genes play a role in the ability of white clover to rapidly adapt to local environments. We also examined questions on subgenome evolution in this recently evolved allotetraploid species and on chromosomal rearrangements in the broader IRLC legume clade.

RESULTS: Integration of PacBio HiFi, Omni-C, Illumina, and linkage map data yielded a completely de novo genome assembly for white clover (created without a priori sequence assignment to subgenomes). We find that white clover has undergone extensive transposon diversification since its origin but otherwise shows highly conserved genome organization and composition with its diploid progenitors. Unlike some other clover species, its chromosomal structure is conserved with other IRLC legumes. We further find extensive evidence of CNVs at the major cyanogenesis loci; these contribute to quantitative variation in the cyanogenic phenotype and to local adaptation across wild North American populations.

CONCLUSIONS: This work provides a case study documenting the role of CNVs in local adaptation in a plant species, and it highlights the value of pan-genome data for identifying contributions of structural variants to adaptation in nature.},
}

@article {pmid39111568,
year = {2024},
author = {Joishy, TK and Bhattacharya, A and Singh, CT and Mukherjee, AK and Khan, MR},
title = {Probiotic and anti-inflammatory properties of Lactiplantibacillus plantarum MKTJ24 isolated from an artisanal fermented fish of North-east India.},
journal = {New biotechnology},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.nbt.2024.07.005},
pmid = {39111568},
issn = {1876-4347},
abstract = {The study aimed to isolate and characterize lactic acid bacteria from various traditional fermented fish products from North East India, including Xindol, Hentak, and Ngari, which hold significant dietary importance for the indigenous tribes. Additionally, the study sought to examine their untargeted metabolomic profiles. A total of 43 strains of Bacillus, Priestia, Staphylococcus, Pediococcus, and Lactiplantibacillus were isolated, characterized by 16S rRNA gene and tested for probiotic properties. Five strains passed pH and bile salt tests with strain dependent antimicrobial activity, which exhibited moderate autoaggregation and hydrophobicity properties. Lactiplantibacillus plantarum MKTJ24 exhibited the highest hydrophobicity (42%), which was further confirmed by adhesion assay in HT-29 cell lines (100%). Lactiplantibacillus plantarum MKTJ24 treatment in LPS-stimulated HT-29 cells up-regulated expression of mucin genes compared to LPS-treated cells. Treatment of RAW 264.7 cells with Lactiplantibacillus plantarum MKTJ24 decreased LPS-induced reactive oxygen species (ROS) and nitric oxide (NO) productions. Further, genome analysis of Lactiplantibacillus plantarum MKTJ24 revealed the presence of several probiotic markers and immunomodulatory genes. The genome was found to harbour plantaracin operon involved in bacteriocin production. A pangenome analysis using all the publicly available L. plantarum genomes specifically isolated from fermented fish products identified 120 unique genes in Lactiplantibacillus plantarum MKTJ24. Metabolomic analysis indicated dominance of ascorbic acids, pentafluropropionate, cyclopropaneacetic acid, florobenzylamine, and furanonee in Xindol. This study suggests that Lactiplantibacillus plantarum MKTJ24 has potential probiotic and immunomodulatory properties that could be used in processing traditional fermented fish products on an industrial scale to improve their quality and enhance functional properties.},
}

@article {pmid39107305,
year = {2024},
author = {Cortinovis, G and Vincenzi, L and Anderson, R and Marturano, G and Marsh, JI and Bayer, PE and Rocchetti, L and Frascarelli, G and Lanzavecchia, G and Pieri, A and Benazzo, A and Bellucci, E and Di Vittori, V and Nanni, L and Ferreira Fernández, JJ and Rossato, M and Aguilar, OM and Morrell, PL and Rodriguez, M and Gioia, T and Neumann, K and Alvarez Diaz, JC and Gratias, A and Klopp, C and Bitocchi, E and Geffroy, V and Delledonne, M and Edwards, D and Papa, R},
title = {Adaptive gene loss in the common bean pan-genome during range expansion and domestication.},
journal = {Nature communications},
volume = {15},
number = {1},
pages = {6698},
pmid = {39107305},
issn = {2041-1723},
support = {862862//EC | Horizon 2020 Framework Programme (EU Framework Programme for Research and Innovation H2020)/ ; },
mesh = {*Phaseolus/genetics ; *Genome, Plant ; *Domestication ; Adaptation, Physiological/genetics ; Genotype ; Genetic Variation ; Crops, Agricultural/genetics ; Selection, Genetic ; Evolution, Molecular ; Mutation ; Plant Breeding/methods ; },
abstract = {The common bean (Phaseolus vulgaris L.) is a crucial legume crop and an ideal evolutionary model to study adaptive diversity in wild and domesticated populations. Here, we present a common bean pan-genome based on five high-quality genomes and whole-genome reads representing 339 genotypes. It reveals ~234 Mb of additional sequences containing 6,905 protein-coding genes missing from the reference, constituting 49% of all presence/absence variants (PAVs). More non-synonymous mutations are found in PAVs than core genes, probably reflecting the lower effective population size of PAVs and fitness advantages due to the purging effect of gene loss. Our results suggest pan-genome shrinkage occurred during wild range expansion. Selection signatures provide evidence that partial or complete gene loss was a key adaptive genetic change in common bean populations with major implications for plant adaptation. The pan-genome is a valuable resource for food legume research and breeding for climate change mitigation and sustainable agriculture.},
}

*Phaseolus/genetics
*Genome, Plant
*Domestication
Adaptation, Physiological/genetics
Genotype
Genetic Variation
Crops, Agricultural/genetics
Selection, Genetic
Evolution, Molecular
Mutation
Plant Breeding/methods

@article {pmid39106791,
year = {2024},
author = {Gasparini, K and Figueiredo, YG and Araújo, WL and Peres, LE and Zsögön, A},
title = {De novo domestication in the Solanaceae: advances and challenges.},
journal = {Current opinion in biotechnology},
volume = {89},
number = {},
pages = {103177},
doi = {10.1016/j.copbio.2024.103177},
pmid = {39106791},
issn = {1879-0429},
abstract = {The advent of highly efficient genome editing (GE) tools, coupled with high-throughput genome sequencing, has paved the way for the accelerated domestication of crop wild relatives. New crops could thus be rapidly created that are well adapted to cope with drought, flooding, soil salinity, or insect damage. De novo domestication avoids the complexity of transferring polygenic stress resistance from wild species to crops. Instead, new crops can be created by manipulating major genes in stress-resistant wild species. However, the genetic basis of certain relevant domestication-related traits often involve epistasis and pleiotropy. Furthermore, pan-genome analyses show that structural variation driving gene expression changes has been selected during domestication. A growing body of work suggests that the Solanaceae family, which includes crop species such as tomatoes, potatoes, eggplants, peppers, and tobacco, is a suitable model group to dissect these phenomena and operate changes in wild relatives to improve agronomic traits rapidly with GE. We briefly discuss the prospects of this exciting novel field in the interface between fundamental and applied plant biology and its potential impact in the coming years.},
}

@article {pmid39107817,
year = {2024},
author = {Le, DQ and Nguyen, TA and Nguyen, SH and Nguyen, TT and Nguyen, CH and Phung, HT and Ho, TH and Vo, NS and Nguyen, T and Nguyen, HA and Cao, MD},
title = {Efficient inference of large prokaryotic pangenomes with PanTA.},
journal = {Genome biology},
volume = {25},
number = {1},
pages = {209},
pmid = {39107817},
issn = {1474-760X},
support = {VINIF.2019.DA11//VinIF/ ; },
abstract = {Pangenome inference is an indispensable step in bacterial genomics, yet its scalability poses a challenge due to the rapid growth of genomic collections. This paper presents PanTA, a software package designed for constructing pangenomes of large bacterial datasets, showing unprecedented efficiency levels multiple times higher than existing tools. PanTA introduces a novel mechanism to construct the pangenome progressively without rebuilding the accumulated collection from scratch. The progressive mode is shown to consume orders of magnitude less computational resources than existing solutions in managing growing datasets. The software is open source and is publicly available at https://github.com/amromics/panta and at 10.6084/m9.figshare.23724705 .},
}

@article {pmid39102038,
year = {2024},
author = {Olanrewaju, OS and Molale-Tom, LG and Bezuidenhout, CC},
title = {Genomic diversity, antibiotic resistance, and virulence in South African Enterococcus faecalis and Enterococcus lactis isolates.},
journal = {World journal of microbiology & biotechnology},
volume = {40},
number = {10},
pages = {289},
pmid = {39102038},
issn = {1573-0972},
mesh = {South Africa ; *Genome, Bacterial ; *Enterococcus faecalis/genetics/drug effects/pathogenicity/isolation & purification ; Virulence/genetics ; *Genetic Variation ; *Anti-Bacterial Agents/pharmacology ; *Virulence Factors/genetics ; Humans ; Drug Resistance, Bacterial/genetics ; Genomic Islands/genetics ; Gram-Positive Bacterial Infections/microbiology ; Enterococcus/genetics/drug effects/pathogenicity/isolation & purification/classification ; Phylogeny ; Gene Transfer, Horizontal ; Genomics ; Microbial Sensitivity Tests ; },
abstract = {This study presents the empirical findings of an in-depth genomic analysis of Enterococcus faecalis and Enterococcus lactis isolates from South Africa. It offers valuable insights into their genetic characteristics and their significant implications for public health. The study uncovers nuanced variations in the gene content of these isolates, despite their similar GC contents, providing a comprehensive view of the evolutionary diversity within the species. Genomic islands are identified, particularly in E. faecalis, emphasizing its propensity for horizontal gene transfer and genetic diversity, especially in terms of antibiotic resistance genes. Pangenome analysis reveals the existence of a core genome, accounting for a modest proportion of the total genes, with 2157 core genes, 1164 shell genes, and 4638 cloud genes out of 7959 genes in 52 South African E. faecalis genomes (2 from this study, 49 south Africa genomes downloaded from NCBI, and E. faecalis reference genome). Detecting large-scale genomic rearrangements, including chromosomal inversions, underscores the dynamic nature of bacterial genomes and their role in generating genetic diversity. The study uncovers an array of antibiotic resistance genes, with trimethoprim, tetracycline, glycopeptide, and multidrug resistance genes prevalent, raising concerns about the effectiveness of antibiotic treatment. Virulence gene profiling unveils a diverse repertoire of factors contributing to pathogenicity, encompassing adhesion, biofilm formation, stress resistance, and tissue damage. These empirical findings provide indispensable insights into these bacteria's genomic dynamics, antibiotic resistance mechanisms, and virulence potential, underlining the pressing need to address antibiotic resistance and implement robust control measures.},
}

South Africa
*Genome, Bacterial
*Enterococcus faecalis/genetics/drug effects/pathogenicity/isolation & purification
Virulence/genetics
*Genetic Variation
*Anti-Bacterial Agents/pharmacology
*Virulence Factors/genetics
Humans
Drug Resistance, Bacterial/genetics
Genomic Islands/genetics
Gram-Positive Bacterial Infections/microbiology
Enterococcus/genetics/drug effects/pathogenicity/isolation & purification/classification
Phylogeny
Gene Transfer, Horizontal
Genomics
Microbial Sensitivity Tests

@article {pmid39101619,
year = {2024},
author = {Kileeg, Z and Wang, P and Mott, GA},
title = {Chromosome-scale assembly and annotation of eight Arabidopsis thaliana ecotypes.},
journal = {Genome biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/gbe/evae169},
pmid = {39101619},
issn = {1759-6653},
abstract = {The plant Arabidopsis thaliana is a model system used by researchers through much of plant research. Recent efforts have focused on discovering the genomic variation found in naturally occurring ecotypes isolated from around the world. These ecotypes have come from diverse climates and therefore have faced and adapted to a variety of abiotic and biotic stressors. The sequencing and comparative analysis of these genomes can offer insight into the adaptive strategies of plants. While there are a large number of ecotype genome sequences available, the majority were created using short-read technology. Mapping of short-reads containing structural variation to a reference genome bereft of that variation leads to incorrect mapping of those reads, resulting in a loss of genetic information and introduction of false heterozygosity. For this reason, long-read de novo sequencing of genomes is required to resolve structural variation events. In this paper, we sequenced the genomes of eight natural variants of A. thaliana using nanopore sequencing. This resulted in highly contiguous assemblies with >95% of the genome contained within 5 contigs. The sequencing results from this study include 5 ecotypes from relict and African populations, an area of untapped genetic diversity. With this study, we increase the knowledge of diversity we have across A. thaliana ecotypes and contribute to ongoing production of an A. thaliana pan-genome.},
}

@article {pmid39095952,
year = {2024},
author = {She, H and Liu, Z and Xu, Z and Zhang, H and Wu, J and Cheng, F and Wang, X and Qian, W},
title = {Pan-genome analysis of 13 Spinacia accessions reveals structural variations associated with sex chromosome evolution and domestication traits in spinach.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.14433},
pmid = {39095952},
issn = {1467-7652},
support = {CAAS-ASTIP-IVFCAAS//the Chinese Academy of Agricultural Sciences Innovation Project/ ; IVF-BRF2023002//Central Public-interest Scientific Institution Basal Research Fund/ ; Y2023QC07//Central Public-interest Scientific Institution Basal Research Fund/ ; CARS-23-A-17//China Agricultural Research System/ ; },
abstract = {Structural variations (SVs) are major genetic variants that can be involved in the origin, adaptation and domestication of species. However, the identification and characterization of SVs in Spinacia species are rare due to the lack of a pan-genome. Here, we report eight chromosome-scale assemblies of cultivated spinach and its two wild species. After integration with five existing assemblies, we constructed a comprehensive Spinacia pan-genome and identified 193 661 pan-SVs, which were genotyped in 452 Spinacia accessions. Our pan-SVs enabled genome-wide association study identified signals associated with sex and clarified the evolutionary direction of spinach. Most sex-linked SVs (86%) were biased to occur on the Y chromosome during the evolution of the sex-linked region, resulting in reduced Y-linked gene expression. The frequency of pan-SVs among Spinacia accessions further illustrated the contribution of these SVs to domestication, such as bolting time and seed dormancy. Furthermore, compared with SNPs, pan-SVs act as efficient variants in genomic selection (GS) because of their ability to capture missing heritability information and higher prediction accuracy. Overall, this study provides a valuable resource for spinach genomics and highlights the potential utility of pan-SV in crop improvement and breeding programmes.},
}

@article {pmid39091872,
year = {2024},
author = {Lin, MJ and Langmead, B and Safonova, Y},
title = {IGLoo: Profiling the Immunoglobulin Heavy chain locus in Lymphoblastoid Cell Lines with PacBio High-Fidelity Sequencing reads.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.07.20.604421},
pmid = {39091872},
issn = {2692-8205},
abstract = {New high-quality human genome assemblies derived from lymphoblastoid cell lines (LCLs) provide reference genomes and pangenomes for genomics studies. However, the characteristics of LCLs pose technical challenges to profiling immunoglobulin (IG) genes. IG loci in LCLs contain a mixture of germline and somatically recombined haplotypes, making them difficult to genotype or assemble accurately. To address these challenges, we introduce IGLoo , a software tool that implements novel methods for analyzing sequence data and genome assemblies derived from LCLs. IGLoo characterizes somatic V(D)J recombination events in the sequence data and identifies the breakpoints and missing IG genes in the LCL-based assemblies. Furthermore, IGLoo implements a novel reassembly framework to improve germline assembly quality by integrating information about somatic events and population structural variantions in the IG loci. We applied IGLoo to study the assemblies from the Human Pangenome Reference Consortium, providing new insights into the mechanisms, gene usage, and patterns of V(D)J recombination, causes of assembly fragmentation in the IG heavy chain (IGH) locus, and improved representation of the IGH assemblies.},
}

@article {pmid39088040,
year = {2024},
author = {Nguyen, AK and Schall, PZ and Kidd, JM},
title = {A map of canine sequence variation relative to a Greenland wolf outgroup.},
journal = {Mammalian genome : official journal of the International Mammalian Genome Society},
volume = {},
number = {},
pages = {},
pmid = {39088040},
issn = {1432-1777},
abstract = {For over 15 years, canine genetics research relied on a reference assembly from a Boxer breed dog named Tasha (i.e., canFam3.1). Recent advances in long-read sequencing and genome assembly have led to the development of numerous high-quality assemblies from diverse canines. These assemblies represent notable improvements in completeness, contiguity, and the representation of gene promoters and gene models. Although genome graph and pan-genome approaches have promise, most genetic analyses in canines rely upon the mapping of Illumina sequencing reads to a single reference. The Dog10K consortium, and others, have generated deep catalogs of genetic variation through an alignment of Illumina sequencing reads to a reference genome obtained from a German Shepherd Dog named Mischka (i.e., canFam4, UU_Cfam_GSD_1.0). However, alignment to a breed-derived genome may introduce bias in genotype calling across samples. Since the use of an outgroup reference genome may remove this effect, we have reprocessed 1929 samples analyzed by the Dog10K consortium using a Greenland wolf (mCanLor1.2) as the reference. We efficiently performed remapping and variant calling using a GPU-implementation of common analysis tools. The resulting call set removes the variability in genetic differences seen across samples and breed relationships revealed by principal component analysis are not affected by the choice of reference genome. Using this sequence data, we inferred the history of population sizes and found that village dog populations experienced a 9-13 fold reduction in historic effective population size relative to wolves.},
}

@article {pmid39087631,
year = {2024},
author = {Cong, J and Zhang, S and Zhang, Q and Yu, X and Huang, J and Wei, X and Huang, X and Qiu, J and Zhou, X},
title = {Conserved features and diversity attributes of chimeric RNAs across accessions in four plants.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.14437},
pmid = {39087631},
issn = {1467-7652},
support = {2023ZD04073//National Key Research and Development Program of China/ ; 32370671//National Natural Science Foundation of China/ ; 22ZR1445800//Natural Science Foundation of Shanghai/ ; },
abstract = {As a non-collinear expression form of genetic information, chimeric RNAs increase the complexity of transcriptome in diverse organisms. Although chimeric RNAs have been identified in plants, few common features have been revealed. Here, we systemically explored the landscape of chimeric RNAs across multi-accession and multi-tissue using pan-genome and transcriptome data of four plants: rice, maize, soybean, and Arabidopsis. Among the four species, conserved characteristics of breakpoints and parental genes were discovered. In each species, chimeric RNAs displayed a high level of diversity among accessions, and the clustering of accessions using chimeric events was generally concordant with clustering based on genomic variants, implying a general relationship between genetic variations and chimeric RNAs. Through mass spectrometry, we confirmed a fusion protein OsNDC1-OsGID1L2 and observed its subcellular localization, which differed from the original proteins. Phenotypic cues in transgenic rice suggest the potential functions of OsNDC1-OsGID1L2. Moreover, an intriguing chimeric event Os01g0216500-Os01g0216900, generated by a large deletion in basmati rice, also exists in another accession without the deletion, demonstrating its convergence in evolution. Our results illuminate the characteristics and hint at the evolutionary implications of plant chimeric RNAs, which serve as a supplement to genetic variations, thus expanding our understanding of genetic diversity.},
}

@article {pmid39083619,
year = {2024},
author = {Rose, SA and Robicheau, BM and Tolman, J and Fonseca-Batista, D and Rowland, E and Desai, D and Ratten, JM and Kantor, EJH and Comeau, AM and Langille, MGI and Jerlström-Hultqvist, J and Devred, E and Sarthou, G and Bertrand, EM and LaRoche, J},
title = {Nitrogen fixation in the widely distributed marine γ-proteobacterial diazotroph Candidatus Thalassolituus haligoni.},
journal = {Science advances},
volume = {10},
number = {31},
pages = {eadn1476},
doi = {10.1126/sciadv.adn1476},
pmid = {39083619},
issn = {2375-2548},
mesh = {*Nitrogen Fixation ; *Gammaproteobacteria/genetics/metabolism/isolation & purification/enzymology/classification ; *Phylogeny ; Nitrogenase/metabolism/genetics ; Seawater/microbiology ; Metagenome ; Oxidoreductases ; },
abstract = {The high diversity and global distribution of heterotrophic bacterial diazotrophs (HBDs) in the ocean has recently become apparent. However, understanding the role these largely uncultured microorganisms play in marine N2 fixation poses a challenge due to their undefined growth requirements and the complex regulation of the nitrogenase enzyme. We isolated and characterized Candidatus Thalassolituus haligoni, a member of a widely distributed clade of HBD belonging to the Oceanospirillales. Analysis of its nifH gene via amplicon sequencing revealed the extensive distribution of Cand. T. haligoni across the Pacific, Atlantic, and Arctic Oceans. Pangenome analysis indicates that the isolate shares >99% identity with an uncultured metagenome-assembled genome called Arc-Gamma-03, recently recovered from the Arctic Ocean. Through combined genomic, proteomic, and physiological approaches, we confirmed that the isolate fixes N2 gas. However, the mechanisms governing nitrogenase regulation in Cand. T. haligoni remain unclear. We propose Cand. T. haligoni as a globally distributed, cultured HBD model species within this understudied clade of Oceanospirillales.},
}

*Nitrogen Fixation
*Gammaproteobacteria/genetics/metabolism/isolation & purification/enzymology/classification
*Phylogeny
Nitrogenase/metabolism/genetics
Seawater/microbiology
Metagenome
Oxidoreductases

@article {pmid39079170,
year = {2024},
author = {Kim, JI and Manuele, A and Maguire, F and Zaheer, R and McAllister, TA and Beiko, R},
title = {Identification of key drivers of antimicrobial resistance in Enterococcus using machine learning.},
journal = {Canadian journal of microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1139/cjm-2024-0049},
pmid = {39079170},
issn = {1480-3275},
abstract = {With antimicrobial resistance (AMR) rapidly evolving in pathogens, quick and accurate identification of genetic determinants of phenotypic resistance is essential for improving surveillance, stewardship, and clinical mitigation. Machine learning (ML) models show promise for AMR prediction in diagnostics but require a deep understanding of internal processes to use effectively. Our study utilized AMR gene, pangenomic, and predicted plasmid features from 647 Enterococcus faecium and Enterococcus faecalis genomes across the One Health continuum, along with corresponding resistance phenotypes, to develop interpretive ML classifiers. Vancomycin resistance could be predicted with 99% accuracy with AMR gene features, 98% with pangenome features, and 96% with plasmid clusters. Top pangenome features overlapped with the resistance genes of the vanA operon, which are often laterally transmitted via plasmids. Doxycycline resistance prediction achieved approximately 92% accuracy with pangenome features, with the top feature being elements of Tn916 conjugative transposon, a tet(M) carrier. Erythromycin resistance prediction models achieved about 90% accuracy, but top features were negatively correlated with resistance due to the confounding effect of population structure. This work demonstrates the importance of reviewing ML models' features to discern biological relevance even when achieving high-performance metrics. Our workflow offers the potential to propose hypotheses for experimental testing, enhancing the understanding of AMR mechanisms, which are crucial for combating the AMR crisis.},
}

@article {pmid39073678,
year = {2024},
author = {Gan, S and Ruan, L and Xu, X and Luo, L and Huo, Y and Jiang, J and Zhang, X and Shang, C},
title = {Whole genome sequencing and analysis of Bacillus sp. TTMP2, a tetramethylpyrazine-producing bacterium.},
journal = {Molecular biology reports},
volume = {51},
number = {1},
pages = {863},
pmid = {39073678},
issn = {1573-4978},
support = {AB21220057 and 2021AB27009//Guangxi Key Research and Development Program/ ; },
mesh = {*Bacillus/genetics/metabolism ; *Pyrazines/metabolism ; *Whole Genome Sequencing/methods ; *Genome, Bacterial/genetics ; *Phylogeny ; Metabolic Networks and Pathways/genetics ; Molecular Sequence Annotation ; },
abstract = {BACKGROUND: Tetramethylpyrazine has been extensively studied as an anticancer substance and a flavor substance in the fields of medicine and food industry. A strain with high tetramethylpyrazine production was screened from the fermented grains of Danquan winery. Genome sequencing can reveal the potential roles of bacteria by thoroughly examining the connection between genes and phenotypes from a genomic perspective.

METHODS AND RESULTS: In this study, whole genome of this strain was sequenced and analyzed. This paper summarized the genomic characteristics of strain TTMP2 and analyzed genes related to the synthesis of tetramethylpyrazine. Bacillus sp. TTMP2 has a complete metabolic pathway for acetoin and tetramethylpyrazine metabolism. Gene function was analyzed by COG annotation, GO annotation, KEGG annotation and functional annotations for lipoproteins, carbohydrate-active enzymes, and pathogen-host interactions. Phylogenetic analysis indicated that Bacillus velezensis had the high homology with Bacillus sp. TTMP2. Genomes of 16 Bacillus species cover all genes of Bacillus, suggesting that genus Bacillus has an open pan-genome and can survive in diverse environments.

CONCLUSION: The analysis of genome sequencing data from Bacillus sp. TTMP2 showed that its metabolic characteristics could be deeply understood, indicating that this bacterium had a particular role in tetramethylpyrazine synthesis.},
}

*Bacillus/genetics/metabolism
*Pyrazines/metabolism
*Whole Genome Sequencing/methods
*Genome, Bacterial/genetics
*Phylogeny
Metabolic Networks and Pathways/genetics
Molecular Sequence Annotation

@article {pmid39071359,
year = {2024},
author = {Kim, J and Varki, R and Oliva, M and Boucher, C},
title = {Re [2] Pair: Increasing the Scalability of RePair by Decreasing Memory Usage.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.07.11.603142},
pmid = {39071359},
issn = {2692-8205},
abstract = {UNLABELLED: The RePair compression algorithm produces a context-free grammar by iteratively substituting the most frequently occurring pair of consecutive symbols with a new symbol until all consecutive pairs of symbols appear only once in the compressed text. It is widely used in the settings of bioinformatics, machine learning, and information retrieval where random access to the original input text is needed. For example, in pangenomics, RePair is used for random access to a population of genomes. BigRePair improves the scalability of the original RePair algorithm by using Prefix-Free Parsing (PFP) to preprocess the text prior to building the RePair grammar. Despite the efficiency of PFP on repetitive text, there is a scalability issue with the size of the parse which causes a memory bottleneck in BigRePair. In this paper, we design and implement recursive RePair (denoted as Re [2] Pair), which builds the RePair grammar using recursive PFP. Our novel algorithm faces the challenge of constructing the RePair grammar without direct access to the parse of text, relying solely on the dictionary of the text and the parse and dictionary of the parse of the text. We compare Re [2] Pair to BigRePair using SARS-CoV-2 haplotypes and haplotypes from the 1000 Genomes Project. We show that our method Re [2] Pair achieves over a 40% peak memory reduction and a speed up ranging between 12% to 79% compared to BigRePair when compressing the largest input texts in all experiments. Re [2] Pair is made publicly available under the GNU public license here: https://github.com/jkim210/Recursive-RePair.

Theory of computation → Formal languages and automata theory.},
}

@article {pmid39065181,
year = {2024},
author = {Romanenko, L and Bystritskaya, E and Savicheva, Y and Eremeev, V and Otstavnykh, N and Kurilenko, V and Velansky, P and Isaeva, M},
title = {Description and Whole-Genome Sequencing of Mariniflexile litorale sp. nov., Isolated from the Shallow Sediments of the Sea of Japan.},
journal = {Microorganisms},
volume = {12},
number = {7},
pages = {},
doi = {10.3390/microorganisms12071413},
pmid = {39065181},
issn = {2076-2607},
support = {15.BRK.21.0004 (Contract No. 075-15-2021-1052)//Ministry of Science and Higher Education, Russian Federation/ ; },
abstract = {A Gram-negative, aerobic, rod-shaped, non-motile, yellow-pigmented bacterium, KMM 9835[T], was isolated from the sediment sample obtained from the Amur Bay of the Sea of Japan seashore, Russia. Phylogenetic analyses based on the 16S rRNA gene and whole genome sequences positioned the novel strain KMM 9835[T] in the genus Mariniflexile as a separate line sharing the highest 16S rRNA gene sequence similarities of 96.6% and 96.2% with Mariniflexile soesokkakense RSSK-9[T] and Mariniflexile fucanivorans SW5[T], respectively, and similarity values of <96% to other recognized Mariniflexile species. The average nucleotide identity and digital DNA-DNA hybridization values between strain KMM 9835[T] and M. soesokkakense KCTC 32427[T], Mariniflexile gromovii KCTC 12570[T], M. fucanivorans DSM 18792[T], and M. maritimum M5A1M[T] were 83.0%, 82.5%, 83.4%, and 78.3% and 30.7%, 29.6%, 29.5%, and 24.4%, respectively. The genomic DNA GC content of strain KMM 9835[T] was 32.5 mol%. The dominant menaquinone was MK-6, and the major fatty acids were iso-C15:0, iso-C15:1ω10c, and C15:0. The polar lipids of strain KMM 9835[T] consisted of phosphatidylethanolamine, two unidentified aminolipids, an unidentified phospholipid, and six unidentified lipids. A pan-genome analysis showed that the KMM 9835[T] genome encoded 753 singletons. The annotated singletons were more often related to transport protein systems (SusC), transcriptional regulators (AraC, LytTR, LacI), and enzymes (glycosylases). The KMM 9835[T] genome was highly enriched in CAZyme-encoding genes, the proportion of which reached 7.3%. Moreover, the KMM 9835[T] genome was characterized by a high abundance of CAZyme gene families (GH43, GH28, PL1, PL10, CE8, and CE12), indicating its potential to catabolize pectin. This may represent part of an adaptation strategy facilitating microbial consumption of plant polymeric substrates in aquatic environments near shorelines and freshwater sources. Based on the combination of phylogenetic and phenotypic characterization, the marine sediment strain KMM 9835[T] (=KCTC 92792[T]) represents a novel species of the genus Mariniflexile, for which the name Mariniflexile litorale sp. nov. is proposed.},
}

@article {pmid39065090,
year = {2024},
author = {Tatarenkov, A and Muñoz-Gutiérrez, I and Vargas, I and Behnsen, J and Mota-Bravo, L},
title = {Pangenome Analysis Reveals Novel Contact-Dependent Growth Inhibition System and Phenazine Biosynthesis Operons in Proteus mirabilis BL95 That Are Located in An Integrative and Conjugative Element.},
journal = {Microorganisms},
volume = {12},
number = {7},
pages = {},
doi = {10.3390/microorganisms12071321},
pmid = {39065090},
issn = {2076-2607},
support = {GM136498//National Institute of General Medical Sciences (NIGMS), NIH/ ; },
abstract = {Proteus mirabilis is a leading cause of urinary tract infections and a common commensal of the gastrointestinal tract. Our recent study (JB) showed that P. mirabilis strain BL95 employs a novel contact-dependent killing system against enteric bacteria in the mouse gut and in vitro. To uncover the genetic determinants of this system, we performed whole-genome sequencing of BL95 and compared it with 98 complete genomes of P. mirabilis. BL95 carries 56 coding sequences (CDSs) not found in other P. mirabilis. Over half of these unique genes are located on a novel integrative conjugative element (ICE) named ICEPm2, inserted in tRNA-Phe and exclusive to BL95. ICEPm2 has integration, conjugation, and DNA replication modules nearly identical to ICEPm1 (common in P. mirabilis), but ICEPm2 of BL95 carries two unique operons for P. mirabilis-a phenazine biosynthesis and a contact-dependent growth inhibition (CDI) system. ICEPm2 is absent in the P. mirabilis (AR_0156) closest to BL95 and it is present in the genomes of several Escherichia coli from mouse intestines, indicating its recent horizontal mobilization. BL95 shares over 100 genes of five different secretion systems with other P. mirabilis, mostly poorly studied, making a large pool of candidate genes for the contact-dependent growth inhibition.},
}

@article {pmid39059904,
year = {2024},
author = {Peng, J and Xiao, R and Wu, C and Zheng, Z and Deng, Y and Chen, K and Xiang, Y and Xu, C and Zou, L and Liao, M and Zhang, J},
title = {Characterization of the prevalence of Salmonella in different retail chicken supply modes using genome-wide and machine-learning analyses.},
journal = {Food research international (Ottawa, Ont.)},
volume = {191},
number = {},
pages = {114654},
doi = {10.1016/j.foodres.2024.114654},
pmid = {39059904},
issn = {1873-7145},
abstract = {Salmonella is a foodborne pathogen that causes salmonellosis, of which retail chicken meat is a major source. However, the prevalence of Salmonella in different retail chicken supply modes and the threat posed to consumers remains unclear. The prevalence, serotype distribution, antibiotic resistance, and genomic characteristics of Salmonella in three supply modes of retail chicken (live poultry, frozen, and chilled) were investigated using whole-genome sequencing (WGS) and machine learning (ML). In this study, 480 retail chicken samples from live poultry, frozen, and chilled supply modes in Guangzhou from 2020 to 2021, as well as 253 Salmonella isolates (total isolation rate = 53.1 %), were collected. The prevalence of isolates in the live poultry mode (67.5 %, 81/120) was statistically higher than in the frozen (50.0 %, 120/240) and chilled (43.3 %, 52/120) (P < 0.05) modes. Serotype identification showed significant differences in the serotype distribution of Salmonella in different supply modes. S. Enteritis (46.7 %) and S. Indiana (14.2 %) were predominant in the frozen mode. S. Agona (23.5 %) and S. Saintpaul (13.6 %) were predominant in live poultry, while S. Enteritis (40.4 %) and S. Kentucky (17.3 %) were predominant in chilled mode. Antibiotic testing showed that frozen mode isolates were more resistant; the multidrug-resistant (MDR) rate of isolates in the frozen mode reached 91.8 %, significantly higher than in the chilled (86.5 %) and live (74.1 %) (P < 0.05) modes. WGS was performed on 155 top serotypes (S. Enteritidis, S. Kentucky, S. Indiana, and S. Agona). The antibiotic resistance gene analysis showed that the abundance and carrying rate of antibiotic resistance genes of Salmonella in the frozen mode (54 types, 16.1 %) were significantly higher than in other modes (live poultry: 36 types, 9.4 %, P < 0.05; chilled: 31 types, 11.6 %). The blaNDM-1 and blaNDM-9 genes encoding carbapenem resistance were found in frozen mode isolates on a complex transposon consisting of TnAS3-IS26. Virulence factors and plasmid replicons were abundant in the studied frozen mode isolates. In addition, single nucleotide polymorphism (SNP) phylogenetic tree results showed that in the frozen supply mode, the S. Enteritidis clonal clade continued to contaminate retail chicken meat and was homologous to S. Enteritidis strains found in farm chicken embryos, slaughterhouse chicken carcasses, and patients from hospitals in China (SNP 0 = 10). Notably, the pan-genome-based ML model showed that characteristic genes in frozen and live poultry isolates differed. The narZ gene was a key characteristic gene in frozen isolates, encoding nitrate reductase, relating to anaerobic bacterial growth. The ydgJ gene is a key characteristic gene in the live mode and encodes an oxidoreductase related to oxidative function in bacteria. The high prevalence of live poultry mode Salmonella and the transmission of frozen mode MDR Salmonella in this study pose serious risks to food safety and public health, emphasizing the importance of improving disinfection and cold storage measures to reduce Salmonella contamination and transmission. In conclusion, the continued surveillance of Salmonella across different supply models and the development of an epidemiological surveillance system based on WGS is necessary.},
}

@article {pmid39059819,
year = {2024},
author = {Radford, EJ and Whitworth, DE},
title = {The genetic basis of predation by myxobacteria.},
journal = {Advances in microbial physiology},
volume = {85},
number = {},
pages = {1-55},
doi = {10.1016/bs.ampbs.2024.04.001},
pmid = {39059819},
issn = {2162-5468},
abstract = {Myxobacteria (phylum Myxococcota) are abundant and virtually ubiquitous microbial predators. Facultatively multicellular organisms, they are able to form multicellular fruiting bodies and swarm across surfaces, cooperatively hunting for prey. Myxobacterial communities are able to kill a wide range of prey microbes, assimilating their biomass to fuel population growth. Their mechanism of predation is exobiotic - hydrolytic enzymes and toxic metabolites are secreted into the extracellular environment, killing and digesting prey cells from without. However, recent observations of single-cell predation and contact-dependent prey killing challenge the dogma of myxobacterial predation being obligately cooperative. Regardless of their predatory mechanisms, myxobacteria have a broad prey range, which includes Gram-negative bacteria, Gram-positive bacteria and fungi. Pangenome analyses have shown that their extremely large genomes are mainly composed of accessory genes, which are not shared by all members of their species. It seems that the diversity of accessory genes in different strains provides the breadth of activity required to prey upon such a smorgasbord of microbes, and also explains the considerable strain-to-strain variation in predatory efficiency against specific prey. After providing a short introduction to general features of myxobacterial biology which are relevant to predation, this review brings together a rapidly growing body of work into the molecular mechanisms and genetic basis of predation, presenting a summary of current knowledge, highlighting trends in research and suggesting strategies by which we can potentially exploit myxobacterial predation in the future.},
}

@article {pmid39059732,
year = {2024},
author = {Magome, TG and Ochai, SO and Hassim, A and Bezuidenhout, CC and van Heerden, H and Lekota, KE},
title = {A genome-based investigation of the Priestia species isolated from anthrax endemic regions in Kruger National Park.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105649},
doi = {10.1016/j.meegid.2024.105649},
pmid = {39059732},
issn = {1567-7257},
abstract = {Priestia is a genus that was renamed from the genus Bacillus based on the conserved signature indels (CSIs) in protein sequences that separate Priestia species from Bacillus, with the latter only including closely related species to B. subtilis and B. cereus. Diagnosis of anthrax, a zoonotic disease is implicated by tripartite anthrax virulence genes (lef, pagA, and cya) and poly-γ-D-glutamic acid capsular genes (capABCDE) of Bacillus anthracis. Due to the amplification of anthrax virulence genes in Priestia isolates, the search for homologous anthrax virulence genes within the Priestia spp. (n = 9) isolated from animal blood smears was embarked upon through whole genome sequencing. In silico taxonomic identification of the isolates was conducted using genome taxonomy database (GTDB), average nucleotide identity (ANI), and multi-locus sequence typing (MLST), which identified the genomes as P. aryabhattai (n = 5), P. endophytica (n = 2) and P. megaterium (n = 2). A pan-genome analysis was further employed on the Priestia genomes, including the screening of virulence, antibiotic resistance genes and mobile genetic elements on the sequenced genomes. The oligoribonuclease NrnB protein sequences showed that Priestia spp. possess a unique CSI that is absent in other Bacillus species. Furthermore, the CSI in P. endophytica is unique from other Priestia spp. Pan-genomic analysis indicates that P. endophytica clusters separately from P. aryabhattai and P. megaterium. In silico BLASTn genome analysis using the SYBR primers, Taqman probes and primers that target the chromosomal marker (Ba-1), protective antigen (pagA), and lethal factor (lef) on B. anthracis, showed partial binding to Priestia regions encoding for hypothetical proteins, pyridoxine biosynthesis, hydrolase, and inhibitory proteins. The antibiotic resistance genes (ARG) profile of Priestia spp. showed that the genomes contained no more than two ARGs. This included genes conferring resistance to rifamycin and fosfomycin (P. endophytica) as well as clindamycin (P. aryabhattai and P. megaterium). Priestia genomes lacked B. anthracis plasmids and consisted of plasmid replicon types with unknown functions. Furthermore, the amplification of Priestia strains may result in false positives when qPCR is used to detect the virulence genes of B. anthracis in soil, blood smears, and/or environmental samples.},
}

@article {pmid39058093,
year = {2024},
author = {Peñil-Celis, A and Tagg, KA and Webb, HE and Redondo-Salvo, S and Francois Watkins, L and Vielva, L and Griffin, C and Kim, JY and Folster, JP and Garcillan-Barcia, MP and de la Cruz, F},
title = {Mobile genetic elements define the non-random structure of the Salmonella enterica serovar Typhi pangenome.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0036524},
doi = {10.1128/msystems.00365-24},
pmid = {39058093},
issn = {2379-5077},
abstract = {Bacterial relatedness measured using select chromosomal loci forms the basis of public health genomic surveillance. While approximating vertical evolution through this approach has proven exceptionally valuable for understanding pathogen dynamics, it excludes a fundamental dimension of bacterial evolution-horizontal gene transfer. Incorporating the accessory genome is the logical remediation and has recently shown promise in expanding epidemiological resolution for enteric pathogens. Employing k-mer-based Jaccard index analysis, and a novel genome length distance metric, we computed pangenome (i.e., core and accessory) relatedness for the globally important pathogen Salmonella enterica serotype Typhi (Typhi), and graphically express both vertical (homology-by-descent) and horizontal (homology-by-admixture) evolutionary relationships in a reticulate network of over 2,200 U.S. Typhi genomes. This analysis revealed non-random structure in the Typhi pangenome that is driven predominantly by the gain and loss of mobile genetic elements, confirming and expanding upon known epidemiological patterns, revealing novel plasmid dynamics, and identifying avenues for further genomic epidemiological exploration. With an eye to public health application, this work adds important biological context to the rapidly improving ways of analyzing bacterial genetic data and demonstrates the value of the accessory genome to infer pathogen epidemiology and evolution.IMPORTANCEGiven bacterial evolution occurs in both vertical and horizontal dimensions, inclusion of both core and accessory genetic material (i.e., the pangenome) is a logical step toward a more thorough understanding of pathogen dynamics. With an eye to public, and indeed, global health relevance, we couple contemporary tools for genomic analysis with decades of research on mobile genetic elements to demonstrate the value of the pangenome, known and unknown, annotated, and hypothetical, for stratification of Salmonella enterica serovar Typhi (Typhi) populations. We confirm and expand upon what is known about Typhi epidemiology, plasmids, and antimicrobial resistance dynamics, and offer new avenues of exploration to further deduce Typhi ecology and evolution, and ultimately to reduce the incidence of human disease.},
}

@article {pmid39058033,
year = {2024},
author = {Mortimer, TD},
title = {mSphere of Influence: Predicting the evolution of pathogen populations.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0043224},
doi = {10.1128/msphere.00432-24},
pmid = {39058033},
issn = {2379-5042},
abstract = {Tatum D. Mortimer works in the field of pathogen population genomics and evolution. In this mSphere of Influence article, she reflects on how "Frequency-dependent selection can forecast evolution in Streptococcus pneumoniae" by Azarian et al. and "Contingency, repeatability, and predictability in the evolution of a prokaryotic pangenome" by Beavan et al. made an impact on her by highlighting the ways in which genomic data can be used to predict pathogen evolution.},
}

@article {pmid39057398,
year = {2024},
author = {Cui, H and Fan, S and Ding, W and Zhang, W},
title = {Genomic Analysis of Novel Sulfitobacter Bacterial Strains Isolated from Marine Biofilms.},
journal = {Marine drugs},
volume = {22},
number = {7},
pages = {},
doi = {10.3390/md22070289},
pmid = {39057398},
issn = {1660-3397},
mesh = {*Biofilms ; *Phylogeny ; *Genome, Bacterial ; Genomics/methods ; Aquatic Organisms ; Multigene Family ; },
abstract = {Bacteria from the genus Sulfitobacter are distributed across various marine habitats and play a significant role in sulfur cycling. However, the metabolic features of Sulfitobacter inhabiting marine biofilms are still not well understood. Here, complete genomes and paired metatranscriptomes of eight Sulfitobacter strains, isolated from biofilms on subtidal stones, have been analyzed to explore their central energy metabolism and potential of secondary metabolite biosynthesis. Based on average nucleotide identity and phylogenetic analysis, the eight strains were classified into six novel species and two novel strains. The reconstruction of the metabolic pathways indicated that all strains had a complete Entner-Doudoroff pathway, pentose phosphate pathway, and diverse pathways for amino acid metabolism, suggesting the presence of an optimized central carbon metabolism. Pangenome analysis further revealed the differences between the gene cluster distribution patterns among the eight strains, suggesting significant functional variation. Moreover, a total of 47 biosynthetic gene clusters were discovered, which were further classified into 37 gene cluster families that showed low similarity with previously documented clusters. Furthermore, metatranscriptomic analysis revealed the expressions of key functional genes involved in the biosynthesis of ribosomal peptides in in situ marine biofilms. Overall, this study sheds new light on the metabolic features, adaptive strategies, and value of genome mining in this group of biofilm-associated Sulfitobacter bacteria.},
}

*Biofilms
*Phylogeny
*Genome, Bacterial
Genomics/methods
Aquatic Organisms
Multigene Family