{"id":"https://openalex.org/W4387954723","doi":"https://doi.org/10.1021/acs.jcim.3c01202","title":"Accurate and Fast Prediction of Intrinsically Disordered Protein by Multiple Protein Language Models and Ensemble Learning","display_name":"Accurate and Fast Prediction of Intrinsically Disordered Protein by Multiple Protein Language Models and Ensemble Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387954723","doi":"https://doi.org/10.1021/acs.jcim.3c01202","pmid":"https://pubmed.ncbi.nlm.nih.gov/37883249"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c01202","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01202","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037030426","display_name":"Shijie Xu","orcid":"https://orcid.org/0000-0001-6974-353X"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shijie Xu","raw_affiliation_strings":["Graduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6974-353X","affiliations":[{"raw_affiliation_string":"Graduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051697045","display_name":"Akira Onoda","orcid":"https://orcid.org/0000-0002-5791-4386"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akira Onoda","raw_affiliation_strings":["Faculty of Environmental Earth Science, Hokkaido University, Sapporo 060-0810, Japan","Graduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5791-4386","affiliations":[{"raw_affiliation_string":"Faculty of Environmental Earth Science, Hokkaido University, Sapporo 060-0810, Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Graduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051697045"],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":3.3636,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92880424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"64","issue":"7","first_page":"2901","last_page":"2911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","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/T12254","display_name":"Machine Learning in Bioinformatics","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/T10044","display_name":"Protein Structure and Dynamics","score":0.9994999766349792,"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":0.996399998664856,"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/ensemble-learning","display_name":"Ensemble learning","score":0.6212775111198425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4645497500896454},{"id":"https://openalex.org/keywords/intrinsically-disordered-proteins","display_name":"Intrinsically disordered proteins","score":0.4359610974788666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40676072239875793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33292287588119507},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.31206077337265015},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.09535405039787292}],"concepts":[{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6212775111198425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4645497500896454},{"id":"https://openalex.org/C2778815515","wikidata":"https://www.wikidata.org/wiki/Q3408242","display_name":"Intrinsically disordered proteins","level":2,"score":0.4359610974788666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40676072239875793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33292287588119507},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.31206077337265015},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.09535405039787292}],"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":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.3c01202","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01202","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:37883249","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37883249","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1966626972","https://openalex.org/W1989511016","https://openalex.org/W2003503651","https://openalex.org/W2008332643","https://openalex.org/W2008708467","https://openalex.org/W2060592742","https://openalex.org/W2097606916","https://openalex.org/W2101926813","https://openalex.org/W2102461176","https://openalex.org/W2116382231","https://openalex.org/W2126099124","https://openalex.org/W2148853951","https://openalex.org/W2154642048","https://openalex.org/W2366093519","https://openalex.org/W2420922808","https://openalex.org/W2510934692","https://openalex.org/W2530581165","https://openalex.org/W2567587907","https://openalex.org/W2571643507","https://openalex.org/W2806884808","https://openalex.org/W2888495466","https://openalex.org/W2896457183","https://openalex.org/W2900078410","https://openalex.org/W2908510526","https://openalex.org/W2909008825","https://openalex.org/W2949342052","https://openalex.org/W2953008890","https://openalex.org/W2955418283","https://openalex.org/W2962684441","https://openalex.org/W2964121744","https://openalex.org/W2986282324","https://openalex.org/W2995514860","https://openalex.org/W2997630430","https://openalex.org/W3007616265","https://openalex.org/W3043901899","https://openalex.org/W3082709982","https://openalex.org/W3111119124","https://openalex.org/W3111174583","https://openalex.org/W3117811820","https://openalex.org/W3146944767","https://openalex.org/W3156051371","https://openalex.org/W3184265853","https://openalex.org/W3214870576","https://openalex.org/W4200540728","https://openalex.org/W4211054902","https://openalex.org/W4220898475","https://openalex.org/W4281993476","https://openalex.org/W4287724045","https://openalex.org/W4306811769","https://openalex.org/W4309506674","https://openalex.org/W4309765941","https://openalex.org/W4327550249","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Intrinsically":[0],"disordered":[1,104,113,117],"proteins":[2,29],"(IDPs)":[3],"play":[4],"a":[5,31,63,93,198,207],"vital":[6],"role":[7],"in":[8,17,52,77,169],"various":[9],"biological":[10],"processes":[11],"and":[12,33,73,86,116,130,164,183,194,218,229],"have":[13,48,74],"attracted":[14],"increasing":[15],"attention":[16],"the":[18,25,102,145,174],"past":[19],"few":[20],"decades.":[21],"Predicting":[22],"IDPs":[23],"from":[24,70,126,155],"primary":[26],"structures":[27],"of":[28,36,84,144,159,171,201],"offers":[30],"rapid":[32],"facile":[34],"means":[35],"protein":[37,56,71,78,118,160,190,202],"analysis":[38],"without":[39],"necessitating":[40],"crystal":[41],"structures.":[42],"In":[43,88],"particular,":[44],"machine":[45],"learning":[46,135],"methods":[47],"demonstrated":[49],"their":[50,82,110],"potential":[51],"this":[53,89],"field.":[54],"Recently,":[55],"language":[57],"models":[58],"(PLMs)":[59],"are":[60,232],"emerging":[61],"as":[62,107,109,192],"promising":[64],"approach":[65],"to":[66,80,100],"extracting":[67],"essential":[68],"information":[69],"sequences":[72,191],"been":[75],"employed":[76],"modeling":[79],"utilize":[81],"advantages":[83],"precision":[85],"efficiency.":[87],"article,":[90],"we":[91],"developed":[92],"novel":[94],"IDP":[95],"prediction":[96],"method":[97,121,146],"named":[98],"IDP-ELM":[99,187],"predict":[101],"intrinsically":[103],"regions":[105],"(IDRs)":[106],"well":[108],"functions":[111],"including":[112],"flexible":[114],"linkers":[115],"binding.":[119],"This":[120],"utilizes":[122],"high-dimensional":[123],"representations":[124],"extracted":[125],"several":[127],"state-of-the-art":[128,212],"PLMs":[129],"predicts":[131],"IDRs":[132],"by":[133],"ensemble":[134],"based":[136],"on":[137,149],"bidirectional":[138],"recurrent":[139],"neural":[140],"networks.":[141],"The":[142,224],"performance":[143],"was":[147],"evaluated":[148],"two":[150],"independent":[151],"test":[152],"data":[153],"sets":[154],"CAID":[156],"(critical":[157],"assessment":[158],"intrinsic":[161],"disorder":[162],"prediction)":[163],"CAID2,":[165],"indicating":[166],"notable":[167],"improvements":[168],"terms":[170],"area":[172],"under":[173],"receiver":[175],"operating":[176],"characteristic":[177],"(AUC),":[178],"Matthew's":[179],"correlation":[180],"coefficient":[181],"(MCC),":[182],"F1":[184],"score.":[185],"Moreover,":[186],"requires":[188],"solely":[189],"inputs":[193],"does":[195],"not":[196],"entail":[197],"time-consuming":[199],"process":[200],"profile":[203],"generation,":[204],"which":[205],"is":[206],"prerequisite":[208],"for":[209,221],"most":[210],"existing":[211],"methods,":[213],"enabling":[214],"an":[215],"accurate,":[216],"fast,":[217],"convenient":[219],"tool":[220],"proteome-level":[222],"analysis.":[223],"corresponding":[225],"reproducible":[226],"source":[227],"code":[228],"model":[230],"weights":[231],"available":[233],"at":[234],"https://github.com/xu-shi-jie/idp-elm.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}