{"id":"https://openalex.org/W3087655841","doi":"https://doi.org/10.1021/acs.jcim.0c00593","title":"De Novo Protein Design for Novel Folds Using Guided Conditional Wasserstein Generative Adversarial Networks","display_name":"De Novo Protein Design for Novel Folds Using Guided Conditional Wasserstein Generative Adversarial Networks","publication_year":2020,"publication_date":"2020-09-18","ids":{"openalex":"https://openalex.org/W3087655841","doi":"https://doi.org/10.1021/acs.jcim.0c00593","mag":"3087655841","pmid":"https://pubmed.ncbi.nlm.nih.gov/32945673","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/7775287"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00593","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7775287","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069807825","display_name":"Mostafa Karimi","orcid":"https://orcid.org/0000-0002-1459-6832"},"institutions":[{"id":"https://openalex.org/I173268674","display_name":"Texas A&M University System","ror":"https://ror.org/0034eay46","country_code":"US","type":"funder","lineage":["https://openalex.org/I173268674"]},{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"funder","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostafa Karimi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States","TEES-AgriLife Center for Bioinformatics and Genomic Systems Engineering, Texas A&M University, College Station, Texas 77840, United States"],"affiliations":[{"raw_affiliation_string":"TEES-AgriLife Center for Bioinformatics and Genomic Systems Engineering, Texas A&M University, College Station, Texas 77840, United States","institution_ids":["https://openalex.org/I173268674"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008603338","display_name":"Shaowen Zhu","orcid":"https://orcid.org/0000-0002-7867-7711"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"funder","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaowen Zhu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593664","display_name":"Yue Cao","orcid":"https://orcid.org/0000-0002-5949-3175"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"funder","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Cao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100716873","display_name":"Yang Shen","orcid":"https://orcid.org/0000-0002-1703-7796"},"institutions":[{"id":"https://openalex.org/I173268674","display_name":"Texas A&M University System","ror":"https://ror.org/0034eay46","country_code":"US","type":"funder","lineage":["https://openalex.org/I173268674"]},{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"funder","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States","TEES-AgriLife Center for Bioinformatics and Genomic Systems Engineering, Texas A&M University, College Station, Texas 77840, United States"],"affiliations":[{"raw_affiliation_string":"TEES-AgriLife Center for Bioinformatics and Genomic Systems Engineering, Texas A&M University, College Station, Texas 77840, United States","institution_ids":["https://openalex.org/I173268674"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77843, United States","institution_ids":["https://openalex.org/I91045830"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100716873"],"corresponding_institution_ids":["https://openalex.org/I173268674","https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":3.632,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.999984,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"60","issue":"12","first_page":"5667","last_page":"5681"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9972,"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":0.9972,"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":0.9657,"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":0.9648,"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/sequence","display_name":"Sequence (biology)","score":0.5798526},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49405864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6042468},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5798526},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.54037863},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49405864},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4717033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45597565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38394243},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35133454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32904238},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11607736},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00593","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7775287","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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://doi.org/10.1101/769919","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/09/14/769919.full.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32945673","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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7775287","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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences","award_id":"R35GM124952"}],"datasets":[],"versions":[],"referenced_works_count":73,"referenced_works":["https://openalex.org/W141681130","https://openalex.org/W1493324970","https://openalex.org/W1587559447","https://openalex.org/W1721447212","https://openalex.org/W1965186869","https://openalex.org/W1975304761","https://openalex.org/W1978447477","https://openalex.org/W1979762151","https://openalex.org/W1996576490","https://openalex.org/W1996733064","https://openalex.org/W2003229787","https://openalex.org/W2013425283","https://openalex.org/W2045777307","https://openalex.org/W2059681116","https://openalex.org/W2101712920","https://openalex.org/W2102245393","https://openalex.org/W2102461176","https://openalex.org/W2106775540","https://openalex.org/W2107867854","https://openalex.org/W2114340287","https://openalex.org/W2114850508","https://openalex.org/W2115540209","https://openalex.org/W2120836664","https://openalex.org/W2121627241","https://openalex.org/W2132644745","https://openalex.org/W2136724628","https://openalex.org/W2141795045","https://openalex.org/W2144686793","https://openalex.org/W2145350307","https://openalex.org/W2170471837","https://openalex.org/W2201713963","https://openalex.org/W2252678535","https://openalex.org/W2340987618","https://openalex.org/W2411639680","https://openalex.org/W2432004435","https://openalex.org/W2519539312","https://openalex.org/W2579798392","https://openalex.org/W2605135824","https://openalex.org/W2618625858","https://openalex.org/W2735621019","https://openalex.org/W2739748921","https://openalex.org/W2781256610","https://openalex.org/W2784920021","https://openalex.org/W2785273668","https://openalex.org/W2795569866","https://openalex.org/W2809642602","https://openalex.org/W2809879025","https://openalex.org/W2883583470","https://openalex.org/W2889498145","https://openalex.org/W2891007938","https://openalex.org/W2891185006","https://openalex.org/W2891841439","https://openalex.org/W2895487334","https://openalex.org/W2898392948","https://openalex.org/W2898664946","https://openalex.org/W2899747610","https://openalex.org/W2902353954","https://openalex.org/W2908391177","https://openalex.org/W2949867299","https://openalex.org/W2951282333","https://openalex.org/W2957874522","https://openalex.org/W2960242007","https://openalex.org/W2979389376","https://openalex.org/W2998116736","https://openalex.org/W2999044305","https://openalex.org/W3010339412","https://openalex.org/W3088578860","https://openalex.org/W3098128018","https://openalex.org/W3100751385","https://openalex.org/W3102502733","https://openalex.org/W3105389349","https://openalex.org/W4210861939","https://openalex.org/W4246407778"],"related_works":["https://openalex.org/W4395044357","https://openalex.org/W4391584540","https://openalex.org/W4387506531","https://openalex.org/W4380551139","https://openalex.org/W4365211920","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W3014948380","https://openalex.org/W2967848559","https://openalex.org/W2087346071"],"abstract_inverted_index":{"Although":[0],"massive":[1],"data":[2,141],"is":[3,12,27,236],"quickly":[4],"accumulating":[5],"on":[6,84],"protein":[7,19,42],"sequence":[8,140,226,263],"and":[9,15,40,76,105,124,137,143,171,188,195,228,254,279],"structure,":[10],"there":[11],"a":[13,103,131,149,180,200,244],"small":[14],"limited":[16],"number":[17],"of":[18,108,212,243],"architectural":[20],"types":[21],"(or":[22,122],"structural":[23,49],"folds).":[24],"This":[25],"study":[26],"addressing":[28],"the":[29,54,94,109,113,155,163,241],"following":[30],"question:":[31],"how":[32],"well":[33],"could":[34],"one":[35,208],"reveal":[36],"underlying":[37],"sequence\u2013structure":[38,274],"relationships":[39],"design":[41,78,252,256,266],"sequences":[43],"for":[44,112],"an":[45,118],"arbitrary,":[46],"potentially":[47],"novel,":[48],"fold?":[50],"In":[51,258],"response":[52],"to":[53,133,147,179,239,265],"question,":[55],"we":[56,80],"have":[57,217],"developed":[58],"novel":[59,159,205],"deep":[60],"generative":[61],"models,":[62],"namely,":[63],"semisupervised":[64,150],"gcWGAN":[65,166,191,215,260],"(guided,":[66],"conditional,":[67],"Wasserstein":[68,86,91],"Generative":[69],"Adversarial":[70],"Networks).":[71],"To":[72],"overcome":[73],"training":[74,151,164],"difficulties":[75],"improve":[77],"qualities,":[79],"build":[81],"our":[82],"models":[83,281],"conditional":[85,114],"GAN":[87],"(WGAN)":[88],"that":[89],"uses":[90],"distance":[92],"in":[93,162],"loss":[95,132],"function.":[96],"Our":[97],"major":[98],"contributions":[99],"include":[100],"(1)":[101],"constructing":[102],"low-dimensional":[104],"generalizable":[106,270],"representation":[107],"fold":[110,221],"space":[111,264],"input,":[115],"(2)":[116],"developing":[117],"ultrafast":[119,233],"sequence-to-fold":[120],"predictor":[121,202],"oracle)":[123],"incorporating":[125],"its":[126],"feedback":[127],"into":[128],"WGAN":[129],"as":[130],"guide":[134],"model":[135,235],"training,":[136],"(3)":[138],"exploiting":[139],"with":[142],"without":[144],"paired":[145],"structures":[146],"enable":[148],"strategy.":[152],"Assessed":[153,185,198],"by":[154,186,199,268],"oracle":[156],"over":[157,203],"100":[158],"folds":[160,177],"not":[161,209],"set,":[165],"generates":[167],"more":[168,175,225],"successful":[169],"designs":[170,192,216],"covers":[172],"3.5":[173],"times":[174],"target":[176],"compared":[178],"competing":[181],"data-driven":[182,234],"method":[183,248],"(cVAE).":[184],"sequence-":[187],"structure-based":[189],"predictors,":[190],"are":[193,282],"physically":[194],"biologically":[196],"sound.":[197],"structure":[201],"representative":[204],"folds,":[206,214],"including":[207],"even":[210],"part":[211],"basis":[213],"comparable":[218],"or":[219],"better":[220],"accuracy":[222],"yet":[223],"much":[224],"diversity":[227],"novelty":[229],"than":[230],"cVAE.":[231],"The":[232],"further":[237],"shown":[238],"boost":[240],"success":[242],"principle-driven":[245],"de":[246],"novo":[247],"(RosettaDesign),":[249],"through":[250],"generating":[251],"seeds":[253],"tailoring":[255],"space.":[257],"conclusion,":[259],"explores":[261],"uncharted":[262],"proteins":[267],"learning":[269],"principles":[271],"from":[272],"current":[273],"data.":[275],"Data,":[276],"source":[277],"codes,":[278],"trained":[280],"available":[283],"at":[284],"https://github.com/Shen-Lab/gcWGAN":[285]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3087655841","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":4}],"updated_date":"2025-04-18T13:04:16.922568","created_date":"2020-09-25"}