{"id":"https://openalex.org/W7204898840","doi":"https://doi.org/10.1186/s12864-026-13470-8","title":"Annotation-aware multidomain validation of NucS and MutS-MutL across 23,435 prokaryotic reference genomes","display_name":"Annotation-aware multidomain validation of NucS and MutS-MutL across 23,435 prokaryotic reference genomes","publication_year":2026,"publication_date":"2026-10-15","ids":{"openalex":"https://openalex.org/W7204898840","doi":"https://doi.org/10.1186/s12864-026-13470-8"},"language":"en","primary_location":{"id":"doi:10.1186/s12864-026-13470-8","doi":"https://doi.org/10.1186/s12864-026-13470-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-026-13470-8","pdf_url":null,"source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Genomics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12864-026-13470-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041233259","display_name":"Kiarash Sadeghian Esfahani","orcid":"https://orcid.org/0000-0002-1844-0675","observed_orcids":["https://orcid.org/0000-0002-1844-0675"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kiarash Sadeghian Esfahani","raw_affiliation_strings":["Independent researcher, Isfahan, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent researcher, Isfahan, Iran","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5041233259"],"corresponding_institution_ids":[],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50869252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6654999852180481,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6654999852180481,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10123","display_name":"DNA Repair Mechanisms","score":0.2849000096321106,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.022099999710917473,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nuc","display_name":"nuc","score":0.972000002861023},{"id":"https://openalex.org/keywords/muts","display_name":"MutS","score":0.8309999704360962},{"id":"https://openalex.org/keywords/mutl","display_name":"MutL","score":0.9990000128746033},{"id":"https://openalex.org/keywords/dna-mismatch-repair","display_name":"DNA mismatch repair","score":0.7730000019073486},{"id":"https://openalex.org/keywords/prokaryotic-genomes","display_name":"prokaryotic genomes","score":0.7369999885559082},{"id":"https://openalex.org/keywords/protein-domain-architecture","display_name":"protein domain architecture","score":0.5720000267028809},{"id":"https://openalex.org/keywords/halobacteria","display_name":"halobacteria","score":0.6909999847412109},{"id":"https://openalex.org/keywords/archaea","display_name":"archaea","score":0.6830000281333923},{"id":"https://openalex.org/keywords/actinobacteria","display_name":"actinobacteria","score":0.8379999995231628},{"id":"https://openalex.org/keywords/phylogenomics","display_name":"phylogenomics","score":0.5450000166893005},{"id":"https://openalex.org/keywords/genome-contamination","display_name":"genome contamination","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.736299991607666},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6902999877929688},{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.5181999802589417},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5002999901771545},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.47369998693466187},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C160798450","wikidata":"https://www.wikidata.org/wiki/Q4230870","display_name":"Concordance","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C2993175405","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Bacterial protein","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s12864-026-13470-8","doi":"https://doi.org/10.1186/s12864-026-13470-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-026-13470-8","pdf_url":null,"source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Genomics","raw_type":"journal-article"},{"id":"doi:10.21203/rs.3.rs-10711921/v1","doi":"https://doi.org/10.21203/rs.3.rs-10711921/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10711921/v1","pdf_url":"https://www.researchsquare.com/article/rs-10711921/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1186/s12864-026-13470-8","doi":"https://doi.org/10.1186/s12864-026-13470-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-026-13470-8","pdf_url":null,"source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Genomics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204898840.pdf","grobid_xml":"https://content.openalex.org/works/W7204898840.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1984467885","https://openalex.org/W2006099600","https://openalex.org/W2112364185","https://openalex.org/W2138122982","https://openalex.org/W2173732482","https://openalex.org/W2326157936","https://openalex.org/W2533162091","https://openalex.org/W2581696898","https://openalex.org/W2805286581","https://openalex.org/W3048090444","https://openalex.org/W3095583226","https://openalex.org/W3164534528","https://openalex.org/W4392516083","https://openalex.org/W4400353742"],"related_works":["https://openalex.org/W2581696898","https://openalex.org/W4321617076","https://openalex.org/W7096137682","https://openalex.org/W2098424996","https://openalex.org/W2009203187","https://openalex.org/W7098564260","https://openalex.org/W2766648240","https://openalex.org/W4230268928","https://openalex.org/W2913287858","https://openalex.org/W4390042481"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"EndoMS/NucS":[2],"mediates":[3],"a":[4,42,124,173,178,235,290],"non-canonical":[5],"mismatch-repair":[6],"pathway":[7],"in":[8,31,41,187,251],"several":[9],"archaeal":[10],"and":[11,21,33,65,79,97,117,134,154,170,228,243,285],"actinobacterial":[12],"lineages.":[13],"A":[14,90,105,129],"2017":[15,252],"phylogenomic":[16],"survey":[17],"reported":[18,250],"that":[19],"NucS":[20,92,148,186,216,226],"canonical":[22,106],"MutS-MutL":[23],"were":[24,68,77,82,165,168,262],"largely":[25],"mutually":[26],"exclusive,":[27],"with":[28,84,177,197,246],"coexistence":[29,144,238],"concentrated":[30,237],"Halobacteria":[32,242],"Deinococcus-Thermus.":[34],"The":[35,182],"present":[36],"study":[37],"reassessed":[38],"this":[39,150],"distribution":[40],"substantially":[43],"expanded":[44],"reference-genome":[45],"collection":[46],"while":[47],"distinguishing":[48],"annotation":[49],"labels":[50],"from":[51,58,209],"multidomain":[52],"protein-profile":[53],"evidence.":[54],"Results":[55],"GFF3":[56],"annotations":[57,193,213],"23,435":[59],"NCBI":[60],"reference":[61,257],"genomes":[62,206,261],"(22,606":[63],"Bacteria":[64],"829":[66],"Archaea)":[67],"screened,":[69],"exact":[70],"RefSeq":[71],"protein":[72,122],"accessions":[73],"for":[74],"annotation-positive":[75],"candidates":[76],"retrieved,":[78],"candidate":[80,103],"architectures":[81],"evaluated":[83],"Pfam":[85],"profile":[86],"hidden":[87],"Markov":[88],"models.":[89],"two-domain":[91,147,185,199,225],"call":[93,108,131],"required":[94,109,132],"NucS_N":[95],"(PF21003)":[96],"NucS_C":[98],"(PF01939)":[99],"on":[100,119],"the":[101,120,155,198,247,254,269,277],"same":[102,121],"protein.":[104],"MutS":[107,111],"five":[110],"profiles":[112,217],"(PF01624,":[113],"PF05188,":[114],"PF05192,":[115],"PF05190":[116],"PF00488)":[118],"without":[123],"same-protein":[125],"PF01713":[126],"(SMR)":[127],"warning.":[128,181],"MutL":[130],"PF01119":[133],"PF08676;":[135],"PF13589":[136],"was":[137,172],"supplementary.":[138],"Annotation-only":[139,220],"screening":[140,291],"yielded":[141,159],"1,145":[142],"apparent":[143,224,229],"genomes.":[145,161,189],"Requiring":[146],"reduced":[149],"set":[151],"to":[152],"473,":[153],"combined":[156],"NucS/MutS/MutL":[157],"criteria":[158],"470":[160],"Of":[162],"these,":[163],"421":[164],"Halobacteria,":[166],"48":[167],"Deinococcota":[169],"one":[171],"Lysobacter":[174],"korlensis":[175],"assembly":[176],"severe":[179],"contamination":[180],"screen":[183],"recovered":[184,234,275],"5,367":[188],"Explicit":[190],"nucS":[191],"gene":[192,298],"showed":[194],"99.63%":[195],"concordance":[196],"criterion":[200],"(5,361/5,381),":[201],"whereas":[202],"only":[203],"0.73%":[204],"of":[205,296],"classified":[207],"solely":[208],"generic":[210],"\u201cNucS":[211],"domain-containing\u201d":[212],"passed":[214],"both":[215],"(5/682).":[218],"Conclusions":[219],"discovery":[221],"markedly":[222],"inflated":[223],"occurrence":[227],"NucS/MutS-MutL":[230],"coexistence.":[231],"Profile":[232],"validation":[233],"taxonomically":[236],"pattern":[239,249],"dominated":[240],"by":[241,266,276],"Deinococcota,":[244],"consistent":[245],"qualitative":[248],"despite":[253],"much":[255],"larger":[256],"collection.":[258],"Because":[259],"annotation-negative":[260],"not":[263],"exhaustively":[264],"assessed":[265],"translated-genome":[267],"searches,":[268],"profile-positive":[270],"counts":[271],"represent":[272],"validated":[273],"positives":[274],"annotation-first":[278],"workflow":[279],"rather":[280,293],"than":[281,294],"exhaustive":[282],"prevalence":[283],"estimates,":[284],"non-detection":[286],"is":[287],"treated":[288],"as":[289],"outcome":[292],"evidence":[295],"biological":[297],"loss.":[299]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-02T00:00:00"}
