{"id":"https://openalex.org/W4290927848","doi":"https://doi.org/10.1145/3534678.3539284","title":"SIPF: Sampling Method for Inverse Protein Folding","display_name":"SIPF: Sampling Method for Inverse Protein Folding","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290927848","doi":"https://doi.org/10.1145/3534678.3539284"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539284","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003226543","display_name":"Tianfan Fu","orcid":"https://orcid.org/0000-0002-5574-2541"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianfan Fu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084279065","display_name":"Jimeng Sun","orcid":"https://orcid.org/0000-0003-1512-6426"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimeng Sun","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003226543"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.3237,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79746835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11162","display_name":"Enzyme Structure and Function","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9907000064849854,"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/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.7136884927749634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891995668411255},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6028541326522827},{"id":"https://openalex.org/keywords/protein-folding","display_name":"Protein folding","score":0.5007061958312988},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4724683463573456},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4714582562446594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4651672840118408},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.4588942527770996},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.4479118585586548},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4407177269458771},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39290493726730347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.375425785779953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3743606209754944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34977954626083374},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.3145428001880646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20254620909690857},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.17363086342811584},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15207770466804504},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.07880330085754395}],"concepts":[{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.7136884927749634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891995668411255},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6028541326522827},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.5007061958312988},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4724683463573456},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4714582562446594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4651672840118408},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.4588942527770996},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.4479118585586548},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4407177269458771},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39290493726730347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.375425785779953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3743606209754944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34977954626083374},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3145428001880646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20254620909690857},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.17363086342811584},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15207770466804504},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.07880330085754395},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539284","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1980471666","https://openalex.org/W2108067237","https://openalex.org/W2122851718","https://openalex.org/W2315962322","https://openalex.org/W2740917210","https://openalex.org/W2810332147","https://openalex.org/W2890382137","https://openalex.org/W2953436574","https://openalex.org/W2989058156","https://openalex.org/W2994163036","https://openalex.org/W3010254513","https://openalex.org/W3098128018","https://openalex.org/W3100159300","https://openalex.org/W3125782153","https://openalex.org/W3135130381","https://openalex.org/W3165163830","https://openalex.org/W3177571920","https://openalex.org/W4234609530"],"related_works":["https://openalex.org/W3125971950","https://openalex.org/W1580681286","https://openalex.org/W2175355783","https://openalex.org/W1579866848","https://openalex.org/W3139342328","https://openalex.org/W2622204791","https://openalex.org/W2066716418","https://openalex.org/W1546022168","https://openalex.org/W2905524938","https://openalex.org/W622922062"],"abstract_inverted_index":{"Protein":[0],"engineering":[1],"has":[2],"important":[3],"applications":[4],"in":[5,17,50,152],"drug":[6],"discovery.":[7],"Among":[8],"others,":[9],"inverse":[10,38,71,78],"protein":[11,18,39,59,72,79],"folding":[12,40,73,80],"is":[13],"a":[14,29,67,82,123],"fundamental":[15],"task":[16],"design,":[19],"which":[20],"aims":[21],"at":[22],"generating":[23],"protein's":[24],"amino":[25],"acid":[26],"sequence":[27],"given":[28],"3D":[30],"graph":[31],"structure.":[32],"However,":[33],"most":[34],"existing":[35],"methods":[36],"for":[37,70,114],"are":[41],"based":[42],"on":[43,145],"sequential":[44],"generative":[45],"models":[46],"and":[47,53,85,116,148],"therefore":[48],"limited":[49],"uncertainty":[51],"quantification":[52],"exploration":[54],"ability":[55],"to":[56,111,135,155],"the":[57,63,126,137,156],"entire":[58],"space.":[60],"To":[61,99],"address":[62],"issues,":[64],"we":[65,76,103],"propose":[66],"sampling":[68,83,101,109,115],"method":[69],"(SIPF).":[74],"Specifically,":[75],"formulate":[77],"as":[81,91,122],"problem":[84],"design":[86,105],"two":[87],"pretrained":[88],"neural":[89],"networks":[90],"Markov":[92],"Chain":[93],"Monte":[94],"Carlo":[95],"(MCMC)":[96],"proposal":[97],"distribution.":[98,129],"ensure":[100],"efficiency,":[102],"further":[104],"(i)":[106],"an":[107,118],"adaptive":[108],"scheme":[110],"select":[112],"variables":[113],"(ii)":[117],"approximate":[119],"target":[120,128],"distribution":[121],"surrogate":[124],"of":[125,139],"unavailable":[127],"Empirical":[130],"studies":[131],"have":[132],"been":[133],"conducted":[134],"validate":[136],"effectiveness":[138],"SIPF,":[140],"achieving":[141],"7.4%":[142],"relative":[143,150],"improvement":[144],"recovery":[146],"rate":[147],"6.4%":[149],"reduction":[151],"perplexity":[153],"compared":[154],"best":[157],"baseline.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}