{"id":"https://openalex.org/W4308589354","doi":"https://doi.org/10.1186/s12859-022-05031-z","title":"Collectively encoding protein properties enriches protein language models","display_name":"Collectively encoding protein properties enriches protein language models","publication_year":2022,"publication_date":"2022-11-08","ids":{"openalex":"https://openalex.org/W4308589354","doi":"https://doi.org/10.1186/s12859-022-05031-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/36348281"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-022-05031-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-05031-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05031-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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 Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05031-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049500026","display_name":"Jingmin An","orcid":null},"institutions":[{"id":"https://openalex.org/I169572211","display_name":"Northeast Agricultural University","ror":"https://ror.org/0515nd386","country_code":"CN","type":"education","lineage":["https://openalex.org/I169572211"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210167311","display_name":"Institute of Zoology","ror":"https://ror.org/05skxkv18","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210167311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingmin An","raw_affiliation_strings":["School of Life Sciences, Northeast Agricultural University, Harbin, 150030, China","State Key Laboratory of Membrane Biology, Institute of Zoology, Chinese Academy of Sciences, Beijing, 100101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Life Sciences, Northeast Agricultural University, Harbin, 150030, China","institution_ids":["https://openalex.org/I169572211"]},{"raw_affiliation_string":"State Key Laboratory of Membrane Biology, Institute of Zoology, Chinese Academy of Sciences, Beijing, 100101, China","institution_ids":["https://openalex.org/I4210167311","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006924408","display_name":"Xiaogang Weng","orcid":"https://orcid.org/0000-0002-7474-8447"},"institutions":[{"id":"https://openalex.org/I169572211","display_name":"Northeast Agricultural University","ror":"https://ror.org/0515nd386","country_code":"CN","type":"education","lineage":["https://openalex.org/I169572211"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaogang Weng","raw_affiliation_strings":["School of Life Sciences, Northeast Agricultural University, Harbin, 150030, China. wengxg@neau.edu.cn","School of Life Sciences, Northeast Agricultural University, Harbin, 150030, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Life Sciences, Northeast Agricultural University, Harbin, 150030, China. wengxg@neau.edu.cn","institution_ids":["https://openalex.org/I169572211"]},{"raw_affiliation_string":"School of Life Sciences, Northeast Agricultural University, Harbin, 150030, China","institution_ids":["https://openalex.org/I169572211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006924408"],"corresponding_institution_ids":["https://openalex.org/I169572211"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.9233,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7280051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"23","issue":"1","first_page":"467","last_page":"467"},"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9991000294685364,"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":0.9987000226974487,"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":0.741518497467041},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5692559480667114},{"id":"https://openalex.org/keywords/decipher","display_name":"DECIPHER","score":0.5084108710289001},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5053189396858215},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5024900436401367},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4906710386276245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4838908612728119},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4830915927886963},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.46187615394592285},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.190883606672287},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1686442494392395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741518497467041},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5692559480667114},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.5084108710289001},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5053189396858215},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5024900436401367},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4906710386276245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4838908612728119},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4830915927886963},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.46187615394592285},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.190883606672287},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1686442494392395},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"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}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-022-05031-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-05031-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05031-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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 Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36348281","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36348281","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:0012c74acfe549088035875117bb19c7","is_oa":true,"landing_page_url":"https://doaj.org/article/0012c74acfe549088035875117bb19c7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 23, Iss 1, Pp 1-18 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9641823","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9641823","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-022-05031-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-05031-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05031-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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 Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7975594787","display_name":null,"funder_award_id":"No. 54941012","funder_id":"https://openalex.org/F4320325186","funder_display_name":"Northeast Agricultural University"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320325186","display_name":"Northeast Agricultural University","ror":"https://ror.org/0515nd386"},{"id":"https://openalex.org/F4320335645","display_name":"Institute of Zoology, Chinese Academy of Sciences","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308589354.pdf","grobid_xml":"https://content.openalex.org/works/W4308589354.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W2029476353","https://openalex.org/W2041495858","https://openalex.org/W2058833671","https://openalex.org/W2059136964","https://openalex.org/W2064675550","https://openalex.org/W2085277871","https://openalex.org/W2104467962","https://openalex.org/W2104972430","https://openalex.org/W2108067237","https://openalex.org/W2110485445","https://openalex.org/W2120615054","https://openalex.org/W2130479394","https://openalex.org/W2137965757","https://openalex.org/W2156269526","https://openalex.org/W2156798505","https://openalex.org/W2161072217","https://openalex.org/W2472351724","https://openalex.org/W2549976854","https://openalex.org/W2550969987","https://openalex.org/W2772848669","https://openalex.org/W2789251334","https://openalex.org/W2789876780","https://openalex.org/W2804822363","https://openalex.org/W2808950571","https://openalex.org/W2889498145","https://openalex.org/W2898402099","https://openalex.org/W2911349016","https://openalex.org/W2913820882","https://openalex.org/W2920837834","https://openalex.org/W2941112903","https://openalex.org/W2949159188","https://openalex.org/W2950374603","https://openalex.org/W2951433247","https://openalex.org/W2951621517","https://openalex.org/W2963457143","https://openalex.org/W2963854351","https://openalex.org/W2970971581","https://openalex.org/W2971227267","https://openalex.org/W2979826702","https://openalex.org/W2980708516","https://openalex.org/W2983113805","https://openalex.org/W2984761660","https://openalex.org/W2993794083","https://openalex.org/W3022629704","https://openalex.org/W3037888463","https://openalex.org/W3040739508","https://openalex.org/W3126639583","https://openalex.org/W3129155125","https://openalex.org/W3141797743","https://openalex.org/W3146944767","https://openalex.org/W3163390259","https://openalex.org/W3164453494","https://openalex.org/W3165163830","https://openalex.org/W3166142427","https://openalex.org/W3177828909","https://openalex.org/W3198971594","https://openalex.org/W3207838037","https://openalex.org/W4200158771","https://openalex.org/W4205773061","https://openalex.org/W4210836354","https://openalex.org/W4225891318","https://openalex.org/W4234552385","https://openalex.org/W4245888765","https://openalex.org/W4254491045","https://openalex.org/W4255421341","https://openalex.org/W4283278367","https://openalex.org/W4297243376","https://openalex.org/W6600195515","https://openalex.org/W6600704668","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2115350162","https://openalex.org/W2330145053","https://openalex.org/W4249875204","https://openalex.org/W2416520078","https://openalex.org/W4242620632","https://openalex.org/W4256069380","https://openalex.org/W4379618494","https://openalex.org/W2113606293","https://openalex.org/W2344924242","https://openalex.org/W2409656713"],"abstract_inverted_index":{"Pre-trained":[0],"natural":[1,8,89],"language":[2,9,32,90],"processing":[3],"models":[4,33],"on":[5,28,86,121],"a":[6,47,87],"large":[7,88],"corpus":[10],"can":[11,109],"naturally":[12],"transfer":[13],"learned":[14],"knowledge":[15,103],"to":[16,53,95,113],"protein":[17,31,37,41,66,80,97,134],"domains":[18],"by":[19,34],"fine-tuning":[20],"specific":[21],"in-domain":[22],"tasks.":[23,42],"However,":[24],"few":[25],"studies":[26],"focused":[27],"enriching":[29],"such":[30],"jointly":[35],"learning":[36,49],"properties":[38],"from":[39,60],"strongly-correlated":[40],"Here":[43],"we":[44,82],"elaborately":[45],"designed":[46],"multi-task":[48],"(MTL)":[50],"architecture,":[51],"aiming":[52],"decipher":[54],"implicit":[55],"structural":[56],"and":[57,69,79],"evolutionary":[58],"information":[59],"three":[61],"sequence-level":[62],"classification":[63],"tasks":[64,117],"for":[65],"family,":[67],"superfamily":[68],"fold.":[70],"Considering":[71],"the":[72,101,106],"co-existing":[73],"contextual":[74],"relevance":[75],"between":[76],"human":[77],"words":[78],"language,":[81],"employed":[83],"BERT,":[84],"pre-trained":[85],"corpus,":[91],"as":[92],"our":[93,128],"backbone":[94],"handle":[96],"sequences.":[98],"More":[99],"importantly,":[100],"encoded":[102],"obtained":[104],"in":[105,137],"MTL":[107],"stage":[108],"be":[110],"well":[111],"transferred":[112],"more":[114],"fine-grained":[115],"downstream":[116],"of":[118],"TAPE.":[119],"Experiments":[120],"structure-":[122],"or":[123],"evolution-related":[124],"applications":[125],"demonstrate":[126],"that":[127],"approach":[129],"outperforms":[130],"many":[131],"state-of-the-art":[132],"Transformer-based":[133],"models,":[135],"especially":[136],"remote":[138],"homology":[139],"detection.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
