{"id":"https://openalex.org/W4393087546","doi":"https://doi.org/10.1142/s0219720024500069","title":"MoRF_ESM: Prediction of MoRFs in disordered proteins based on a deep transformer protein language model","display_name":"MoRF_ESM: Prediction of MoRFs in disordered proteins based on a deep transformer protein language model","publication_year":2024,"publication_date":"2024-03-22","ids":{"openalex":"https://openalex.org/W4393087546","doi":"https://doi.org/10.1142/s0219720024500069","pmid":"https://pubmed.ncbi.nlm.nih.gov/38812466"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720024500069","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720024500069","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","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/A5004026597","display_name":"Chun Fang","orcid":"https://orcid.org/0000-0002-0161-0412"},"institutions":[{"id":"https://openalex.org/I130541836","display_name":"Beijing Institute of Petrochemical Technology","ror":"https://ror.org/025s55q11","country_code":"CN","type":"education","lineage":["https://openalex.org/I130541836"]},{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["CN","JP"],"is_corresponding":true,"raw_author_name":"Chun Fang","raw_affiliation_strings":["Department of Computer Science and Engineering, Waseda University, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan","Department of Information Engineering, Beijing Institute of Petrochemical Technology, 19 Qingyuan North Road, Daxing District, Beijing 102617, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0002-0161-0412","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Waseda University, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Information Engineering, Beijing Institute of Petrochemical Technology, 19 Qingyuan North Road, Daxing District, Beijing 102617, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I130541836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063783857","display_name":"Jiasheng He","orcid":"https://orcid.org/0009-0005-0894-6815"},"institutions":[{"id":"https://openalex.org/I130541836","display_name":"Beijing Institute of Petrochemical Technology","ror":"https://ror.org/025s55q11","country_code":"CN","type":"education","lineage":["https://openalex.org/I130541836"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiasheng He","raw_affiliation_strings":["Department of Information Engineering, Beijing Institute of Petrochemical Technology, 19 Qingyuan North Road, Daxing District, Beijing 102617, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0005-0894-6815","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Beijing Institute of Petrochemical Technology, 19 Qingyuan North Road, Daxing District, Beijing 102617, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I130541836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031456992","display_name":"Hayato Yamana","orcid":"https://orcid.org/0000-0001-7542-4826"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Yamana","raw_affiliation_strings":["Department of Computer Science and Engineering, Waseda University, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7542-4826","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Waseda University, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004026597"],"corresponding_institution_ids":["https://openalex.org/I130541836","https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.6331,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66345894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"22","issue":"02","first_page":"2450006","last_page":"2450006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11482","display_name":"RNA modifications and cancer","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"}},"topics":[{"id":"https://openalex.org/T11482","display_name":"RNA modifications and cancer","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":0.9993000030517578,"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":0.9993000030517578,"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/transformer","display_name":"Transformer","score":0.6031543612480164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5372687578201294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.495733380317688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39260995388031006},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3261827826499939},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2741095721721649},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15019062161445618},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07945170998573303}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6031543612480164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5372687578201294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.495733380317688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39260995388031006},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3261827826499939},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2741095721721649},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15019062161445618},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07945170998573303},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720024500069","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720024500069","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:38812466","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38812466","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 bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1979079649","https://openalex.org/W2017104289","https://openalex.org/W2053050812","https://openalex.org/W2056449285","https://openalex.org/W2103743266","https://openalex.org/W2110128290","https://openalex.org/W2113985551","https://openalex.org/W2118608964","https://openalex.org/W2148271643","https://openalex.org/W2148349600","https://openalex.org/W2149573413","https://openalex.org/W2168220711","https://openalex.org/W2315787946","https://openalex.org/W2765783049","https://openalex.org/W2780927228","https://openalex.org/W2790001298","https://openalex.org/W2794654572","https://openalex.org/W2902448994","https://openalex.org/W2963923670","https://openalex.org/W2972006361","https://openalex.org/W3011698511","https://openalex.org/W3129155125","https://openalex.org/W3131121088","https://openalex.org/W3146944767","https://openalex.org/W3157437194","https://openalex.org/W3207838037","https://openalex.org/W4308773001","https://openalex.org/W4327550249","https://openalex.org/W4362657509"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Molecular":[0],"recognition":[1],"features":[2,214,226],"(MoRFs)":[3],"are":[4,122],"particular":[5],"functional":[6],"segments":[7],"of":[8,20,57,63,111,116,144,205,239,267],"disordered":[9,37,96],"proteins,":[10],"which":[11,87],"play":[12],"crucial":[13],"roles":[14],"in":[15,29,95,113,228,254],"regulating":[16],"the":[17,34,54,61,114,142,145,150,166,203,236,251,265],"phase":[18],"transition":[19],"membrane-less":[21],"organelles":[22],"and":[23,39,72,132,152,185,207,219,231],"frequently":[24],"serve":[25],"as":[26],"central":[27],"sites":[28],"cellular":[30],"interaction":[31],"networks.":[32],"As":[33],"association":[35],"between":[36],"proteins":[38],"severe":[40],"diseases":[41],"continues":[42],"to":[43,53,75,92,107,148,159,216,261],"be":[44,76,258],"discovered,":[45],"identifying":[46],"MoRFs":[47,94],"has":[48],"gained":[49],"growing":[50],"significance.":[51],"Due":[52],"limited":[55],"number":[56],"experimentally":[58],"validated":[59],"MoRFs,":[60],"performance":[62],"existing":[64],"MoRF's":[65],"prediction":[66,155,237],"algorithms":[67],"is":[68,232,244],"not":[69],"good":[70],"enough":[71],"still":[73],"needs":[74],"improved.":[77],"In":[78,134,157],"this":[79,255],"research,":[80],"we":[81],"present":[82],"a":[83,101,125,245],"model":[84,106,128,147],"named":[85],"MoRF_ESM,":[86],"utilizes":[88],"deep-learning":[89],"protein":[90,104,217,229,248,268],"representations":[91,110,121],"predict":[93],"proteins.":[97],"This":[98],"approach":[99,168],"employs":[100],"pretrained":[102],"ESM-2":[103,206,243],"language":[105,249],"generate":[108,153],"embedding":[109],"residues":[112],"form":[115],"attention":[117],"map":[118],"matrices.":[119],"These":[120,199],"combined":[123],"with":[124,222],"self-learned":[126],"TextCNN":[127,208],"for":[129,235],"feature":[130],"extraction":[131],"prediction.":[133],"addition,":[135],"an":[136],"averaging":[137],"step":[138],"was":[139],"incorporated":[140],"at":[141],"end":[143],"MoRF_ESM":[146,167],"refine":[149],"output":[151],"final":[154],"results.":[156],"comparison":[158],"other":[160,179,193,262],"impressive":[161],"methods":[162,180,194],"on":[163,183,197],"benchmark":[164],"datasets,":[165],"demonstrates":[169],"state-of-the-art":[170],"performance,":[171],"achieving":[172,186],"[Formula:":[173,187],"see":[174,188],"text]":[175,189],"higher":[176,190],"AUC":[177,191],"than":[178,192],"when":[181,195],"tested":[182,196],"TEST1":[184],"TEST2.":[198],"results":[200],"imply":[201],"that":[202,242],"combination":[204],"can":[209,257],"effectively":[210],"extract":[211],"deep":[212],"evolutionary":[213],"related":[215],"structure":[218],"function,":[220],"along":[221],"capturing":[223],"shallow":[224],"pattern":[225],"located":[227],"sequences,":[230],"well":[233],"qualified":[234],"task":[238],"MoRFs.":[240],"Given":[241],"highly":[246],"versatile":[247],"model,":[250],"methodology":[252],"proposed":[253],"study":[256],"readily":[259],"applied":[260],"tasks":[263],"involving":[264],"classification":[266],"sequences.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}