{"id":"https://openalex.org/W4220952154","doi":"https://doi.org/10.1093/bib/bbab502","title":"Accurate protein function prediction via graph attention networks with predicted structure information","display_name":"Accurate protein function prediction via graph attention networks with predicted structure information","publication_year":2021,"publication_date":"2021-11-05","ids":{"openalex":"https://openalex.org/W4220952154","doi":"https://doi.org/10.1093/bib/bbab502","pmid":"https://pubmed.ncbi.nlm.nih.gov/34882195"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbab502","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab502","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8898000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037445285","display_name":"Ben Lai","orcid":"https://orcid.org/0000-0002-4201-6786"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boqiao Lai","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, IL 60637, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, IL 60637, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019398608","display_name":"Jinbo Xu","orcid":"https://orcid.org/0000-0001-7111-4839"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinbo Xu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, IL 60637, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, IL 60637, USA","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019398608"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":6.1676,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.97674636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"23","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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":0.9965999722480774,"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":0.669092059135437},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.5561587810516357},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.525736927986145},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.48518234491348267},{"id":"https://openalex.org/keywords/information-structure","display_name":"Information structure","score":0.47721463441848755},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.46983715891838074},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.4519462585449219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4472426772117615},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42869487404823303},{"id":"https://openalex.org/keywords/network-structure","display_name":"Network structure","score":0.4210568070411682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3372553586959839},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.29367268085479736},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25802701711654663},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08102434873580933},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07652813196182251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669092059135437},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.5561587810516357},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.525736927986145},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.48518234491348267},{"id":"https://openalex.org/C2779954242","wikidata":"https://www.wikidata.org/wiki/Q6031227","display_name":"Information structure","level":2,"score":0.47721463441848755},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.46983715891838074},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.4519462585449219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472426772117615},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42869487404823303},{"id":"https://openalex.org/C2988224531","wikidata":"https://www.wikidata.org/wiki/Q20830730","display_name":"Network structure","level":2,"score":0.4210568070411682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3372553586959839},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.29367268085479736},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25802701711654663},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08102434873580933},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07652813196182251},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","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":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, 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":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbab502","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab502","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34882195","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34882195","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8898000","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8898000","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8898000","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8898000","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2229035017","display_name":null,"funder_award_id":"R01GM089753","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W637153065","https://openalex.org/W1484548732","https://openalex.org/W1583837637","https://openalex.org/W1662382123","https://openalex.org/W2023790301","https://openalex.org/W2055043387","https://openalex.org/W2073587387","https://openalex.org/W2092053194","https://openalex.org/W2100383158","https://openalex.org/W2101220662","https://openalex.org/W2102461176","https://openalex.org/W2107327414","https://openalex.org/W2117486996","https://openalex.org/W2133564696","https://openalex.org/W2148711203","https://openalex.org/W2160848247","https://openalex.org/W2163605009","https://openalex.org/W2170672962","https://openalex.org/W2170747616","https://openalex.org/W2198606573","https://openalex.org/W2227395312","https://openalex.org/W2345512687","https://openalex.org/W2514044079","https://openalex.org/W2558272290","https://openalex.org/W2558748708","https://openalex.org/W2615066396","https://openalex.org/W2807567459","https://openalex.org/W2900359059","https://openalex.org/W2908510526","https://openalex.org/W2913820882","https://openalex.org/W2922674004","https://openalex.org/W2949867299","https://openalex.org/W2950954328","https://openalex.org/W2951282333","https://openalex.org/W2951731136","https://openalex.org/W2952218450","https://openalex.org/W2956569764","https://openalex.org/W2963457143","https://openalex.org/W2964015378","https://openalex.org/W2966590054","https://openalex.org/W2967606876","https://openalex.org/W2971759641","https://openalex.org/W2972411752","https://openalex.org/W2979255327","https://openalex.org/W2980789587","https://openalex.org/W2989608901","https://openalex.org/W2997234557","https://openalex.org/W2999044305","https://openalex.org/W3003790283","https://openalex.org/W3010387158","https://openalex.org/W3016221692","https://openalex.org/W3023746197","https://openalex.org/W3036197410","https://openalex.org/W3049692992","https://openalex.org/W3091918580","https://openalex.org/W3110823473","https://openalex.org/W3146944767","https://openalex.org/W3163965514","https://openalex.org/W3164046276","https://openalex.org/W3184540805","https://openalex.org/W4225256479","https://openalex.org/W4233120011","https://openalex.org/W4236358448","https://openalex.org/W4236965008","https://openalex.org/W4239849280","https://openalex.org/W4288419263","https://openalex.org/W4295312788","https://openalex.org/W4297733535","https://openalex.org/W6620673361","https://openalex.org/W6637178625","https://openalex.org/W6679434410","https://openalex.org/W6684191040","https://openalex.org/W6726873649","https://openalex.org/W6760603089","https://openalex.org/W6773671450","https://openalex.org/W6774110404","https://openalex.org/W6776411304","https://openalex.org/W6783678571","https://openalex.org/W6793629291"],"related_works":["https://openalex.org/W2094822546","https://openalex.org/W4388708026","https://openalex.org/W1969080446","https://openalex.org/W2593264178","https://openalex.org/W3108941781","https://openalex.org/W2091809126","https://openalex.org/W4304588620","https://openalex.org/W1578069856","https://openalex.org/W2134206588","https://openalex.org/W2470147982"],"abstract_inverted_index":{"Experimental":[0],"protein":[1,18,29,45,49,65,74],"function":[2,30,66],"annotation":[3],"does":[4,151],"not":[5,37,152],"scale":[6],"with":[7],"the":[8,85,94,98,119,127,137,158,162,183,197],"fast-growing":[9],"sequence":[10,75,105],"databases.":[11],"Only":[12],"a":[13,55],"tiny":[14],"fraction":[15],"(<0.1%)":[16],"of":[17],"sequences":[19],"has":[20,206],"experimentally":[21],"determined":[22],"functional":[23],"annotations.":[24],"Computational":[25],"methods":[26],"may":[27,62],"predict":[28],"very":[31,38],"quickly,":[32],"but":[33],"their":[34],"accuracy":[35],"is":[36],"satisfactory.":[39],"Based":[40],"upon":[41],"recent":[42],"breakthroughs":[43],"in":[44],"structure":[46,71,155,173],"prediction":[47,67],"and":[48,73,88,100,116,145,164,190,211],"language":[50],"models,":[51],"we":[52],"develop":[53],"GAT-GO,":[54],"graph":[56],"attention":[57],"network":[58],"(GAT)":[59],"method":[60,139,199],"that":[61,81,150,201],"substantially":[63],"improve":[64],"by":[68],"leveraging":[69],"predicted":[70,172],"information":[72],"embedding.":[76],"Our":[77],"experimental":[78,203],"results":[79],"show":[80],"GAT-GO":[82,108,176],"greatly":[83],"outperforms":[84],"latest":[86],"sequence-":[87],"structure-based":[89],"deep":[90],"learning":[91],"methods.":[92],"On":[93,157],"PDB-mmseqs":[95],"testset":[96,160],"where":[97,161],"train":[99],"test":[101,165],"proteins":[102,166],"share":[103],"<15%":[104],"identity,":[106],"our":[107,175],"yields":[109],"Fmax":[110,178,207],"(maximum":[111],"F-score)":[112],"0.508,":[113],"0.416,":[114],"0.501,":[115,180],"area":[117],"under":[118],"precision-recall":[120],"curve":[121],"(AUPRC)":[122],"0.427,":[123],"0.253,":[124],"0.411":[125],"for":[126,182],"MFO,":[128,184],"BPO,":[129,185],"CCO":[130,186],"ontology":[131,187],"domains,":[132,188],"respectively,":[133,189],"much":[134],"better":[135],"than":[136],"homology-based":[138],"BLAST":[140],"(Fmax":[141],"0.117,":[142],"0.121,":[143],"0.207":[144],"AUPRC":[146,191,212],"0.120,":[147,148],"0.163)":[149],"use":[153],"any":[154],"information.":[156],"PDB-cdhit":[159],"training":[163],"are":[167],"more":[168],"similar,":[169],"although":[170],"using":[171],"information,":[174],"obtains":[177],"0.637,":[179],"0.542":[181],"0.662,":[192],"0.384,":[193],"0.481,":[194],"significantly":[195],"exceeding":[196],"just-published":[198],"DeepFRI":[200],"uses":[202],"structures,":[204],"which":[205],"0.542,":[208],"0.425,":[209],"0.424":[210],"only":[213],"0.313,":[214],"0.159,":[215],"0.193.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}