{"id":"https://openalex.org/W3088605613","doi":"https://doi.org/10.1093/bioinformatics/btaa823","title":"Text mining for modeling of protein complexes enhanced by machine learning","display_name":"Text mining for modeling of protein complexes enhanced by machine learning","publication_year":2020,"publication_date":"2020-09-09","ids":{"openalex":"https://openalex.org/W3088605613","doi":"https://doi.org/10.1093/bioinformatics/btaa823","mag":"3088605613","pmid":"https://pubmed.ncbi.nlm.nih.gov/32960948"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa823","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa823","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/4/497/37757539/btaa823.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/37/4/497/37757539/btaa823.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037324499","display_name":"Varsha D. Badal","orcid":"https://orcid.org/0000-0001-7281-9136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varsha D Badal","raw_affiliation_strings":["Computational Biology Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Program","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050411996","display_name":"Petras J. Kundrotas","orcid":"https://orcid.org/0000-0001-5080-1664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petras J Kundrotas","raw_affiliation_strings":["Computational Biology Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Program","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013394507","display_name":"Ilya A. Vakser","orcid":"https://orcid.org/0000-0002-5743-2934"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilya A Vakser","raw_affiliation_strings":["Computational Biology Program","The University of Kansas Department of Molecular Biosciences, , Lawrence, KS 66045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Program","institution_ids":[]},{"raw_affiliation_string":"The University of Kansas Department of Molecular Biosciences, , Lawrence, KS 66045, USA","institution_ids":["https://openalex.org/I146416000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.2501,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54595372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"37","issue":"4","first_page":"497","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8737000226974487,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8737000226974487,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.06849999725818634,"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":0.01640000008046627,"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":0.7506639957427979},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7388378381729126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7003962993621826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6551382541656494},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5164639949798584},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5138238072395325},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.4845253825187683},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45121362805366516},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32398220896720886},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.08316835761070251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506639957427979},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7388378381729126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7003962993621826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6551382541656494},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5164639949798584},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5138238072395325},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4845253825187683},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45121362805366516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32398220896720886},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.08316835761070251},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btaa823","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa823","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/4/497/37757539/btaa823.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:32960948","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32960948","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:europepmc.org:7343393","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8088328","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8088328","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8088328","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaa823","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa823","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/4/497/37757539/btaa823.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2665170876","display_name":null,"funder_award_id":"DBI1917263","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5676354075","display_name":null,"funder_award_id":"DBI1565107","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9237260","display_name":null,"funder_award_id":"R01GM074255","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3088605613.pdf","grobid_xml":"https://content.openalex.org/works/W3088605613.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1479703980","https://openalex.org/W1498436455","https://openalex.org/W1970689298","https://openalex.org/W2016928406","https://openalex.org/W2027943492","https://openalex.org/W2051689038","https://openalex.org/W2057042085","https://openalex.org/W2057240659","https://openalex.org/W2058190388","https://openalex.org/W2064030835","https://openalex.org/W2065108361","https://openalex.org/W2075322787","https://openalex.org/W2084543313","https://openalex.org/W2094344445","https://openalex.org/W2096525273","https://openalex.org/W2097898123","https://openalex.org/W2098679902","https://openalex.org/W2122763686","https://openalex.org/W2122904379","https://openalex.org/W2127976940","https://openalex.org/W2147154106","https://openalex.org/W2147489358","https://openalex.org/W2148696992","https://openalex.org/W2149684865","https://openalex.org/W2153579005","https://openalex.org/W2155796229","https://openalex.org/W2158505321","https://openalex.org/W2163922914","https://openalex.org/W2168905447","https://openalex.org/W2187089797","https://openalex.org/W2193085234","https://openalex.org/W2376200357","https://openalex.org/W2410487015","https://openalex.org/W2481381417","https://openalex.org/W2505312721","https://openalex.org/W2573117738","https://openalex.org/W2734608416","https://openalex.org/W2741809807","https://openalex.org/W2750875483","https://openalex.org/W2786693834","https://openalex.org/W2794764013","https://openalex.org/W2884165257","https://openalex.org/W2891474722","https://openalex.org/W2919115771","https://openalex.org/W2951934944","https://openalex.org/W2952253955","https://openalex.org/W2962769333","https://openalex.org/W2964828309","https://openalex.org/W2969397082","https://openalex.org/W2978461222","https://openalex.org/W4230784961","https://openalex.org/W4294170691","https://openalex.org/W4312960235","https://openalex.org/W6682005813","https://openalex.org/W6682691769","https://openalex.org/W6731865481","https://openalex.org/W6753335390"],"related_works":["https://openalex.org/W4389670110","https://openalex.org/W2187546663","https://openalex.org/W2429057255","https://openalex.org/W148745890","https://openalex.org/W2611942503","https://openalex.org/W2899790217","https://openalex.org/W1576092969","https://openalex.org/W4315621326","https://openalex.org/W2598865957","https://openalex.org/W2524154428"],"abstract_inverted_index":{"MOTIVATION:":[0],"Procedures":[1],"for":[2,44,95],"structural":[3],"modeling":[4],"of":[5,13,34,40,54,61,65,74,76,82,89,98,106,159,182],"protein-protein":[6,66],"complexes":[7],"(protein":[8],"docking)":[9],"produce":[10],"a":[11,86],"number":[12,88],"models":[14,125,184],"which":[15,201],"need":[16,194],"to":[17,139,154,195],"be":[18,25],"further":[19],"analyzed":[20],"and":[21,120,152,170,228,254],"scored.":[22],"Scoring":[23],"can":[24],"based":[26],"on":[27,31,63,147,174,178],"independently":[28],"determined":[29,218],"constraints":[30],"the":[32,35,45,77,83,90,96,99,107,134,140,148,160,164,180,207,220,226,229,233,237,246,255],"structure":[33],"complex,":[36],"such":[37,70,189],"as":[38,85],"knowledge":[39],"amino":[41],"acids":[42],"essential":[43],"protein":[46],"interaction.":[47],"Previously,":[48],"we":[49],"showed":[50,132],"that":[51,133,213],"text":[52,248],"mining":[53],"residues":[55,79,91,109,161],"in":[56,163,188,222,225,236,240,245,258],"freely":[57],"available":[58,262,270],"PubMed":[59,165],"abstracts":[60,238],"papers":[62],"studies":[64],"interactions":[67],"may":[68],"generate":[69],"constraints.":[71],"However,":[72],"absence":[73],"post-processing":[75],"spotted":[78,162],"reduced":[80],"usability":[81],"constraints,":[84],"significant":[87],"were":[92],"not":[93],"relevant":[94],"binding":[97],"specific":[100],"proteins.":[101],"RESULTS:":[102],"We":[103],"explored":[104],"filtering":[105],"irrelevant":[108],"by":[110,219],"two":[111],"machine":[112],"learning":[113],"approaches,":[114],"Deep":[115],"Recursive":[116],"Neural":[117],"Network":[118],"(DRNN)":[119],"Support":[121],"Vector":[122],"Machine":[123],"(SVM)":[124],"with":[126],"different":[127,242],"training/testing":[128],"schemes.":[129],"The":[130,210,252],"results":[131],"DRNN":[135,199],"model":[136,142],"is":[137,145,172,185,192,202,212,216],"superior":[138],"SVM":[141,214],"when":[143],"training":[144,169,208,227],"performed":[146,173],"PMC-OA":[149],"full-text":[150,175],"articles":[151,176],"applied":[153],"classification":[155],"(interface":[156],"or":[157,177],"non-interface)":[158],"abstracts.":[166],"When":[167],"both":[168],"testing":[171,230],"abstracts,":[179],"performance":[181],"these":[183],"similar.":[186],"Thus,":[187],"cases,":[190],"there":[191],"no":[193],"utilize":[196],"computationally":[197,203],"demanding":[198],"approach,":[200],"expensive":[204],"especially":[205],"at":[206,263,271],"stage.":[209],"reason":[211],"success":[215],"often":[217],"similarity":[221],"data/text":[223],"patterns":[224],"sets,":[231],"whereas":[232],"sentence":[234],"structures":[235],"are,":[239],"general,":[241],"from":[243],"those":[244],"full":[247],"articles.":[249],"AVAILABILITYAND":[250],"IMPLEMENTATION:":[251],"code":[253],"datasets":[256],"generated":[257],"this":[259],"study":[260],"are":[261,269],"https://gitlab.ku.edu/vakser-lab-public/text-mining/-/tree/2020-09-04.":[264],"SUPPLEMENTARY":[265],"INFORMATION:":[266],"Supplementary":[267],"data":[268],"Bioinformatics":[272],"online.":[273]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
