{"id":"https://openalex.org/W3034038259","doi":"https://doi.org/10.1093/database/baaa042","title":"Obtaining extremely large and accurate protein multiple sequence alignments from curated hierarchical alignments","display_name":"Obtaining extremely large and accurate protein multiple sequence alignments from curated hierarchical alignments","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3034038259","doi":"https://doi.org/10.1093/database/baaa042","mag":"3034038259","pmid":"https://pubmed.ncbi.nlm.nih.gov/32500917"},"language":"en","primary_location":{"id":"doi:10.1093/database/baaa042","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaa042","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa042/33394075/baaa042.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa042/33394075/baaa042.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010571747","display_name":"Andrew F. Neuwald","orcid":"https://orcid.org/0000-0002-0086-5755"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew F Neuwald","raw_affiliation_strings":["Department of Biochemistry & Molecular Biology, University of Maryland School of Medicine, 670 W. Baltimore Street, Baltimore, MD 21201, USA","Institute for Genome Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry & Molecular Biology, University of Maryland School of Medicine, 670 W. Baltimore Street, Baltimore, MD 21201, USA","institution_ids":["https://openalex.org/I126744593"]},{"raw_affiliation_string":"Institute for Genome Sciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061900671","display_name":"Christopher J. Lanczycki","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J Lanczycki","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Building 38 A, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Building 38 A, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109903805","display_name":"Theresa K. Hodges","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Theresa K Hodges","raw_affiliation_strings":["Institute for Genome Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genome Sciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026383671","display_name":"Aron Marchler\u2010Bauer","orcid":"https://orcid.org/0000-0003-1516-0712"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aron Marchler-Bauer","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Building 38 A, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Building 38 A, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010571747"],"corresponding_institution_ids":["https://openalex.org/I126744593"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.4473,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.58075529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2020","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":0.9998000264167786,"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":0.9998000264167786,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9973999857902527,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446280717849731},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.6088486909866333},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5986809134483337},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5014348030090332},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48563137650489807},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47475340962409973},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4456499218940735},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.42384177446365356},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4166232645511627},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21337991952896118},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.17414969205856323},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.14338669180870056},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11157605051994324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446280717849731},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.6088486909866333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5986809134483337},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5014348030090332},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48563137650489807},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47475340962409973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4456499218940735},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.42384177446365356},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4166232645511627},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21337991952896118},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.17414969205856323},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14338669180870056},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11157605051994324},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/baaa042","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaa042","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa042/33394075/baaa042.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:32500917","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32500917","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7297217","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7297217","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baaa042","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaa042","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa042/33394075/baaa042.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2804373536","display_name":null,"funder_award_id":"GM125878","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7847268881","display_name":null,"funder_award_id":"R01 GM125878","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G8823736224","display_name":null,"funder_award_id":"R01 GM125878","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034038259.pdf","grobid_xml":"https://content.openalex.org/works/W3034038259.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1982583124","https://openalex.org/W2008545402","https://openalex.org/W2013425283","https://openalex.org/W2050738924","https://openalex.org/W2051545676","https://openalex.org/W2061042699","https://openalex.org/W2069458148","https://openalex.org/W2092672051","https://openalex.org/W2114340287","https://openalex.org/W2139754669","https://openalex.org/W2140771555","https://openalex.org/W2153544371","https://openalex.org/W2158714788","https://openalex.org/W2163507574","https://openalex.org/W2166701319","https://openalex.org/W2167133711","https://openalex.org/W2170249492","https://openalex.org/W2402064298","https://openalex.org/W2559191318","https://openalex.org/W2574496196","https://openalex.org/W2605442816","https://openalex.org/W2783201045","https://openalex.org/W2792034759","https://openalex.org/W2801109052","https://openalex.org/W2809358639","https://openalex.org/W2895532240","https://openalex.org/W2898402099","https://openalex.org/W2951239856","https://openalex.org/W2963640180","https://openalex.org/W4236459334"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2149492307","https://openalex.org/W1985408726","https://openalex.org/W2141411672"],"abstract_inverted_index":{"For":[0],"optimal":[1],"performance,":[2],"machine":[3],"learning":[4],"methods":[5],"for":[6,108,139,217,222,243,262],"protein":[7,80],"sequence/structural":[8],"analysis":[9],"typically":[10,85],"require":[11],"as":[12,29,44,106,192,241],"input":[13,107,242],"a":[14,41,45,120,129,150,160,190,193],"large":[15,144,230],"multiple":[16],"sequence":[17,43],"alignment":[18],"(MSA),":[19],"which":[20,188],"is":[21,183,239],"often":[22,68],"created":[23],"using":[24,40],"query-based":[25],"iterative":[26],"programs,":[27],"such":[28],"PSI-BLAST":[30],"or":[31,52],"JackHMMER.":[32],"However,":[33,95],"because":[34],"these":[35,114,142],"programs":[36,67,138,251],"align":[37,71,169,196],"database":[38,202],"sequences":[39,57,72,103,203],"query":[42,194],"template,":[46],"they":[47],"may":[48,53],"fail":[49,69],"to":[50,55,60,70,75,99,104,168,180,195,207,259],"detect":[51],"tend":[54,98],"misalign":[56],"distantly":[58],"related":[59],"the":[61,76,90,177,184,210,218,234],"query.":[62],"More":[63],"generally,":[64],"automated":[65],"MSA":[66,172],"correctly":[73],"due":[74],"unpredictable":[77],"nature":[78],"of":[79,92,122,131,149,152,209,228],"evolution.":[81],"Addressing":[82],"this":[83,181,215,237],"problem":[84],"requires":[86],"manual":[87],"curation":[88],"in":[89,236],"light":[91],"structural":[93],"data.":[94],"curated":[96,124,211],"MSAs":[97,126,155,165,174,231],"contain":[100],"too":[101],"few":[102],"serve":[105],"statistically":[109],"based":[110],"methods.":[111],"We":[112,213],"address":[113],"shortcomings":[115],"by":[116],"making":[117],"publicly":[118],"available":[119,240,268],"set":[121,151,227],"252":[123],"hierarchical":[125],"(hiMSAs),":[127],"containing":[128],"total":[130],"26":[132],"212":[133],"066":[134],"sequences,":[135],"along":[136,162],"with":[137,163,204],"generating":[140],"from":[141,233],"extremely":[143,229],"MSAs.":[145],"Each":[146],"hiMSA":[147,191],"consists":[148],"hierarchically":[153],"arranged":[154],"representing":[156],"individual":[157],"subgroups":[158],"within":[159],"superfamily":[161,220],"template":[164],"specifying":[166],"how":[167],"each":[170],"subgroup":[171],"against":[173],"higher":[175],"up":[176],"hierarchy.":[178],"Central":[179],"approach":[182],"MAPGAPS":[185],"search":[186],"program,":[187],"uses":[189],"(potentially":[197],"vast":[198],"numbers":[199],"of)":[200],"matching":[201],"accuracy":[205],"comparable":[206],"that":[208],"hiMSA.":[212],"illustrate":[214],"process":[216],"exonuclease-endonuclease-phosphatase":[219],"and":[221,255,257],"pleckstrin":[223],"homology":[224],"domains.":[225],"A":[226],"generated":[232],"hiMSAs":[235],"way":[238],"deep":[244],"learning,":[245],"big":[246],"data":[247,265],"analyses.":[248],"MAPGAPS,":[249],"auxiliary":[250],"CDD2MGS,":[252],"AddPhylum,":[253],"PurgeMSA":[254],"ConvertMSA":[256],"links":[258],"National":[260],"Center":[261],"Biotechnology":[263],"Information":[264],"files":[266],"are":[267],"at":[269],"https://www.igs.umaryland.edu/labs/neuwald/software/mapgaps/.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}