{"id":"https://openalex.org/W7148246335","doi":"https://doi.org/10.1093/bioinformatics/btag156","title":"Protein FID: improved evaluation of protein structure generative models","display_name":"Protein FID: improved evaluation of protein structure generative models","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148246335","doi":"https://doi.org/10.1093/bioinformatics/btag156","pmid":"https://pubmed.ncbi.nlm.nih.gov/41926752"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag156","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag156","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/bioinformatics/btag156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132770071","display_name":"Felix Faltings","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Felix Faltings","raw_affiliation_strings":["CSAIL, MIT , Cambridge, MA 02139,"],"raw_orcid":"https://orcid.org/0009-0002-8424-7467","affiliations":[{"raw_affiliation_string":"CSAIL, MIT , Cambridge, MA 02139,","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132776052","display_name":"Hannes Stark","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannes Stark","raw_affiliation_strings":["CSAIL, MIT , Cambridge, MA 02139,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT , Cambridge, MA 02139,","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048915657","display_name":"Tommi Jaakkola","orcid":"https://orcid.org/0000-0002-2199-0379"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tommi Jaakkola","raw_affiliation_strings":["CSAIL, MIT , Cambridge, MA 02139,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT , Cambridge, MA 02139,","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010124873","display_name":"Regina Barzilay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Regina Barzilay","raw_affiliation_strings":["CSAIL, MIT , Cambridge, MA 02139,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT , Cambridge, MA 02139,","institution_ids":["https://openalex.org/I4210110987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5132770071"],"corresponding_institution_ids":["https://openalex.org/I4210110987"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71769256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.7419999837875366,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.7419999837875366,"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":0.13279999792575836,"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":0.037300001829862595,"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/metric","display_name":"Metric (unit)","score":0.6642000079154968},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6351000070571899},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.630299985408783},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6036999821662903},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank (RCSB PDB)","score":0.5386999845504761},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.532800018787384},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.5088000297546387}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6351000070571899},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.630299985408783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.607699990272522},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6036999821662903},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.532800018787384},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.487199991941452},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40779998898506165},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C119145174","wikidata":"https://www.wikidata.org/wiki/Q7251429","display_name":"Protein Data Bank","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.2605000138282776}],"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":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag156","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag156","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41926752","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41926752","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13092321","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13092321/","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag156","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag156","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2108067237","https://openalex.org/W2161151688","https://openalex.org/W2548003600","https://openalex.org/W2809756846","https://openalex.org/W4296032638","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4383957026","https://openalex.org/W4388694364","https://openalex.org/W4396721167"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Protein":[1],"structure":[2,79,105],"generative":[3,106],"models":[4,36,107],"have":[5,26],"seen":[6],"a":[7,49,61,67],"recent":[8],"surge":[9],"of":[10,21,63,115,119],"interest,":[11],"but":[12],"meaningfully":[13],"evaluating":[14],"them":[15],"computationally":[16],"is":[17,124],"an":[18],"active":[19],"area":[20],"research.":[22],"While":[23],"current":[24,58,103],"metrics":[25],"driven":[27],"useful":[28],"progress,":[29],"they":[30,112],"do":[31],"not":[32],"capture":[33],"how":[34],"well":[35],"sample":[37],"the":[38,43,99,117],"design":[39],"space":[40],"represented":[41],"by":[42],"training":[44],"data.":[45],"We":[46],"argue":[47],"for":[48],"protein":[50,78,86,104],"Frechet":[51],"Inception":[52],"Distance":[53],"(FID)":[54],"metric":[55],"to":[56],"supplement":[57],"evaluations":[59],"with":[60,90,108],"measure":[62],"distributional":[64],"similarity":[65],"in":[66],"semantically":[68],"meaningful":[69],"latent":[70],"space.":[71],"RESULTS:":[72],"Our":[73],"FID":[74,109],"behaves":[75],"desirably":[76],"under":[77],"perturbations":[80],"and":[81,94,98],"correctly":[82],"recapitulates":[83],"similarities":[84],"between":[85],"samples:":[87],"it":[88],"correlates":[89],"optimal":[91],"transport":[92],"distances":[93],"recovers":[95],"FoldSeek":[96],"clusters":[97],"CATH":[100],"hierarchy.":[101],"Evaluating":[102],"shows":[110],"that":[111],"fall":[113],"short":[114],"modeling":[116],"distribution":[118],"PDB":[120],"proteins.":[121],"AVAILABILITY:":[122],"Code":[123],"available":[125],"at:":[126],"https://github.com/ffaltings/protfid.":[127]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2026-04-03T00:00:00"}