{"id":"https://openalex.org/W7162313978","doi":"https://doi.org/10.1093/bib/bbag243","title":"Out-of-distribution generalization enhances protein function annotation for low-homology sequences","display_name":"Out-of-distribution generalization enhances protein function annotation for low-homology sequences","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7162313978","doi":"https://doi.org/10.1093/bib/bbag243","pmid":"https://pubmed.ncbi.nlm.nih.gov/42184116"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbag243","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag243","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":true,"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":"gold","oa_url":"https://doi.org/10.1093/bib/bbag243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136926295","display_name":"Yiwei Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yiwei Fu","raw_affiliation_strings":["School of Mathematical Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003278343","display_name":"Jiaxiao Chen","orcid":"https://orcid.org/0000-0001-8409-7126"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxiao Chen","raw_affiliation_strings":["Center for Quantitative Biology, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Quantitative Biology, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062583953","display_name":"Haoyu Lin","orcid":"https://orcid.org/0000-0002-6664-6985"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Lin","raw_affiliation_strings":["Center for Quantitative Biology, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Quantitative Biology, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044318086","display_name":"Zhonghui Gu","orcid":"https://orcid.org/0000-0001-6142-4358"},"institutions":[{"id":"https://openalex.org/I2802444338","display_name":"King Center","ror":"https://ror.org/03nxex423","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802444338"]},{"id":"https://openalex.org/I4210160507","display_name":"Center for Life Sciences","ror":"https://ror.org/05kje8j93","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570","https://openalex.org/I4210160507","https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhonghui Gu","raw_affiliation_strings":["Peking-Tsinghua Center for Life Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking-Tsinghua Center for Life Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I2802444338","https://openalex.org/I4210160507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027022795","display_name":"Qingqing Long","orcid":"https://orcid.org/0009-0003-7105-361X"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Qingqing Long","raw_affiliation_strings":["School of Computer Science, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136910302","display_name":"Hui Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hui Wan","raw_affiliation_strings":["School of Mathematical Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136924871","display_name":"Xiao Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Luo","raw_affiliation_strings":["Department of Statistics, University of Wisconsin\u2013Madison , 1205 University Avenue, Madison, WI 53706,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Wisconsin\u2013Madison , 1205 University Avenue, Madison, WI 53706,","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136919958","display_name":"Minghua Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Minghua Deng","raw_affiliation_strings":["Center for Quantitative Biology, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","Center for Statistical Science, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","School of Mathematical Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Quantitative Biology, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Statistical Science, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Mathematical Sciences, Peking University , No. 5, Yiheyuan Road, Haidian District, Beijing 100871,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56739413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"3","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":0.7483000159263611,"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":0.7483000159263611,"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":0.0982000008225441,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.050200000405311584,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/interpretability","display_name":"Interpretability","score":0.8338000178337097},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6439999938011169},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.47290000319480896},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4675000011920929},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4212000072002411},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3846000134944916},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.37720000743865967},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.33959999680519104}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8338000178337097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966000199317932},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5950999855995178},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.47290000319480896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.37720000743865967},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.33070001006126404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2989108626","wikidata":"https://www.wikidata.org/wiki/Q904407","display_name":"Drug target","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2533000111579895},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.2515000104904175}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"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":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"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":"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":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbag243","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag243","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":true,"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42184116","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42184116","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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13200542","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13200542/","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbag243","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag243","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":true,"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6822625037","display_name":null,"funder_award_id":"32270689","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2018661561","https://openalex.org/W2024005354","https://openalex.org/W2031772330","https://openalex.org/W2035585923","https://openalex.org/W2055043387","https://openalex.org/W2055094847","https://openalex.org/W2096358531","https://openalex.org/W2096864392","https://openalex.org/W2103132055","https://openalex.org/W2108134720","https://openalex.org/W2109991441","https://openalex.org/W2140673705","https://openalex.org/W2146620899","https://openalex.org/W2152482858","https://openalex.org/W2161607603","https://openalex.org/W2170146596","https://openalex.org/W2268472773","https://openalex.org/W2592742128","https://openalex.org/W2615066396","https://openalex.org/W2616247523","https://openalex.org/W2753953057","https://openalex.org/W2952218450","https://openalex.org/W3018980093","https://openalex.org/W3028589594","https://openalex.org/W3096561213","https://openalex.org/W3109916301","https://openalex.org/W3129049721","https://openalex.org/W3137270128","https://openalex.org/W3146944767","https://openalex.org/W3164046276","https://openalex.org/W3177828909","https://openalex.org/W3179436811","https://openalex.org/W3206585172","https://openalex.org/W3211795435","https://openalex.org/W4205192056","https://openalex.org/W4214868967","https://openalex.org/W4225264859","https://openalex.org/W4236358448","https://openalex.org/W4242765109","https://openalex.org/W4293046261","https://openalex.org/W4295298624","https://openalex.org/W4312097792","https://openalex.org/W4323348775","https://openalex.org/W4327550249","https://openalex.org/W4360938460","https://openalex.org/W4382198799","https://openalex.org/W4391444806","https://openalex.org/W4391449530","https://openalex.org/W4391821988","https://openalex.org/W4394578942","https://openalex.org/W4396721167","https://openalex.org/W4401585044","https://openalex.org/W4402816271","https://openalex.org/W4403734627","https://openalex.org/W4405228734","https://openalex.org/W4408557607"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"protein":[1,51,77],"functions":[2],"in":[3,62,80],"biological":[4],"processes":[5],"is":[6],"pivotal":[7],"for":[8,57],"disease":[9],"elucidation":[10],"and":[11,30,49,114,124,134,157,165],"drug":[12],"discovery.":[13],"Despite":[14],"notable":[15],"progress,":[16],"existing":[17],"approaches":[18],"primarily":[19],"focus":[20],"on":[21,118],"function":[22,78],"transfer":[23],"under":[24],"in-distribution":[25],"(ID)":[26],"settings,":[27],"where":[28],"training":[29],"test":[31],"proteins":[32],"exhibit":[33],"high":[34],"sequence":[35],"similarity.":[36],"As":[37],"a":[38,54,70,85],"result,":[39],"their":[40],"performance":[41,164],"often":[42],"degrades":[43],"when":[44],"applied":[45],"to":[46,75,112,149],"novel,":[47],"diverse,":[48],"low-homology":[50,115],"sequences,":[52],"posing":[53],"major":[55],"challenge":[56],"out-of-distribution":[58],"(OOD)":[59],"generalization":[60,111],"encountered":[61],"practice.":[63],"Towards":[64],"this":[65],"end,":[66],"we":[67],"develop":[68],"ProteinScore,":[69],"graph":[71],"transformer":[72],"approach":[73],"tailored":[74],"improve":[76],"prediction":[79],"OOD":[81],"settings.":[82],"ProteinScore":[83,109,129,146],"integrates":[84],"label-invariant":[86],"variational":[87],"subgraph":[88],"generator":[89],"with":[90,120],"self-supervised":[91],"contrastive":[92],"learning,":[93],"thereby":[94],"identifying":[95,141],"meaning":[96],"substructures":[97],"within":[98],"proteins.":[99],"By":[100],"highlighting":[101],"informative":[102],"features":[103],"while":[104],"filtering":[105],"out":[106],"redundant":[107],"ones,":[108],"improves":[110],"diverse":[113],"sequences.":[116],"Experiments":[117],"datasets":[119],"both":[121],"experimentally":[122],"resolved":[123],"AlphaFold2-predicted":[125],"structures":[126],"demonstrate":[127],"that":[128],"consistently":[130],"outperforms":[131],"strong":[132],"baselines":[133],"provides":[135],"biologically":[136],"meaningful":[137],"interpretability":[138],"through":[139],"accurately":[140],"binding":[142],"sites.":[143],"In":[144],"addition,":[145],"generalizes":[147],"effectively":[148],"two":[150],"additional":[151],"downstream":[152],"tasks,":[153],"drug-target":[154],"interaction":[155],"classification":[156],"subcellular":[158],"localization":[159],"prediction,":[160],"achieving":[161],"superior":[162],"predictive":[163],"reliable":[166],"interpretability.":[167]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-26T00:00:00"}