{"id":"https://openalex.org/W7130591261","doi":"https://doi.org/10.1371/journal.pcbi.1013996","title":"Controllable protein design via autoregressive direct coupling analysis conditioned on principal components","display_name":"Controllable protein design via autoregressive direct coupling analysis conditioned on principal components","publication_year":2026,"publication_date":"2026-02-19","ids":{"openalex":"https://openalex.org/W7130591261","doi":"https://doi.org/10.1371/journal.pcbi.1013996","pmid":"https://pubmed.ncbi.nlm.nih.gov/41712668"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1013996","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013996","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1013996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082888774","display_name":"F. Caredda","orcid":"https://orcid.org/0009-0009-2175-8084"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Francesco Caredda","raw_affiliation_strings":["Department of Applied Science and Technology, Politecnico di Torino, Torino, Italy"],"raw_orcid":"https://orcid.org/0009-0009-2175-8084","affiliations":[{"raw_affiliation_string":"Department of Applied Science and Technology, Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126412328","display_name":"Lisa Gennai","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lisa Gennai","raw_affiliation_strings":["Institute of Physics, School of Basic Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne - EPFL, Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-6156-5804","affiliations":[{"raw_affiliation_string":"Institute of Physics, School of Basic Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne - EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055873619","display_name":"Paolo De Los Rios","orcid":"https://orcid.org/0000-0002-5394-5062"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paolo De Los Rios","raw_affiliation_strings":["Institute of Bioengineering, School of Basic Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne - EPFL, Lausanne, Switzerland","Institute of Physics, School of Basic Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne - EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Bioengineering, School of Basic Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne - EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Institute of Physics, School of Basic Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne - EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011435835","display_name":"Andrea Pagnani","orcid":"https://orcid.org/0000-0002-6509-0807"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]},{"id":"https://openalex.org/I4210099850","display_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Torino","ror":"https://ror.org/01vj6ck58","country_code":"IT","type":"facility","lineage":["https://openalex.org/I160013858","https://openalex.org/I4210099850"]},{"id":"https://openalex.org/I4210123319","display_name":"Italian institute for Genomic Medicine","ror":"https://ror.org/036054d36","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210123319"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Pagnani","raw_affiliation_strings":["Department of Applied Science and Technology, Politecnico di Torino, Torino, Italy","INFN, Sezione di Torino, Torino, Italy","Italian Institute for Genomic Medicine, IRCCS Candiolo, Candiolo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Science and Technology, Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"INFN, Sezione di Torino, Torino, Italy","institution_ids":["https://openalex.org/I4210099850"]},{"raw_affiliation_string":"Italian Institute for Genomic Medicine, IRCCS Candiolo, Candiolo, Italy","institution_ids":["https://openalex.org/I4210123319"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082888774"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":9.4061,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9622385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"22","issue":"2","first_page":"e1013996","last_page":"e1013996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.807699978351593,"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":0.807699978351593,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.028200000524520874,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.027000000700354576,"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/interpretability","display_name":"Interpretability","score":0.8628000020980835},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6485000252723694},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5820000171661377},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5641999840736389},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5238999724388123},{"id":"https://openalex.org/keywords/functional-data-analysis","display_name":"Functional data analysis","score":0.4674000144004822},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4221999943256378}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8628000020980835},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5626999735832214},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708999991416931},{"id":"https://openalex.org/C51820054","wikidata":"https://www.wikidata.org/wiki/Q5508814","display_name":"Functional data analysis","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4221999943256378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.359499990940094},{"id":"https://openalex.org/C71176878","wikidata":"https://www.wikidata.org/wiki/Q17014987","display_name":"Functional principal component analysis","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2946000099182129},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1371/journal.pcbi.1013996","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013996","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:41712668","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41712668","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:doaj.org/article:ce28cc9799274ac6b05775ccf4401d94","is_oa":true,"landing_page_url":"https://doaj.org/article/ce28cc9799274ac6b05775ccf4401d94","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 22, Iss 2, p e1013996 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12935303","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12935303/","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":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1013996","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013996","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5093969019","display_name":null,"funder_award_id":"2022TE5B7X","funder_id":"https://openalex.org/F4320321873","funder_display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca"},{"id":"https://openalex.org/G5278497284","display_name":"Statistical Inference from Multiscale Biological Data: theory, algorithms, applications","funder_award_id":"101131463","funder_id":"https://openalex.org/F4320338438","funder_display_name":"HORIZON EUROPE Marie Sklodowska-Curie Actions"},{"id":"https://openalex.org/G6575207570","display_name":null,"funder_award_id":"IC00I0-227688","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320321873","display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","ror":"https://ror.org/0166hxq48"},{"id":"https://openalex.org/F4320338438","display_name":"HORIZON EUROPE Marie Sklodowska-Curie Actions","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1861406683","https://openalex.org/W1978693516","https://openalex.org/W2008545402","https://openalex.org/W2011343696","https://openalex.org/W2099254366","https://openalex.org/W2125112034","https://openalex.org/W2130479394","https://openalex.org/W2498485322","https://openalex.org/W2568617656","https://openalex.org/W2593641128","https://openalex.org/W2783644078","https://openalex.org/W2890223884","https://openalex.org/W2940885779","https://openalex.org/W3035486570","https://openalex.org/W3044778276","https://openalex.org/W3095583226","https://openalex.org/W3111174583","https://openalex.org/W3114990254","https://openalex.org/W3129222977","https://openalex.org/W3133458480","https://openalex.org/W3135130381","https://openalex.org/W3135175179","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3177828909","https://openalex.org/W3211186415","https://openalex.org/W4308616064","https://openalex.org/W4327550249","https://openalex.org/W4386629205","https://openalex.org/W4388627063","https://openalex.org/W4393249720","https://openalex.org/W4396721167","https://openalex.org/W4406440058","https://openalex.org/W4407194157","https://openalex.org/W4412706726"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"FeatureDCA,":[2],"a":[3,135,203],"statistical":[4,213],"framework":[5],"for":[6,169,208],"protein":[7,90,220],"sequence":[8,50,77,109,114,210],"modeling":[9],"and":[10,52,60,83,120,205,217],"generation":[11],"that":[12,123,184,191],"extends":[13],"Direct":[14],"Coupling":[15],"Analysis":[16],"(DCA)":[17],"with":[18,118,129],"biologically":[19],"meaningful":[20],"conditioning.":[21],"The":[22],"method":[23],"can":[24],"leverage":[25],"different":[26,152],"kinds":[27],"of":[28,76,85,95,103,139,174,185],"information,":[29],"such":[30],"as":[31,39,202],"phylogeny,":[32],"optimal":[33],"growth":[34],"temperature,":[35],"enzymatic":[36],"activity":[37],"or,":[38],"in":[40,106,219],"the":[41,57,64,81,100,140],"case":[42,137],"presented":[43],"here,":[44],"principal":[45,164],"components":[46],"derived":[47],"from":[48],"multiple":[49,89],"alignments,":[51],"use":[53],"it":[54],"to":[55,70,151,183],"improve":[56],"learning":[58],"process":[59],"consequently":[61],"efficiently":[62],"condition":[63],"generative":[65,101],"process.":[66],"FeatureDCA":[67,96,155,192,201],"allows":[68],"sampling":[69],"be":[71],"guided":[72],"toward":[73],"specific":[74],"regions":[75],"space":[78],"while":[79,111],"maintaining":[80],"efficiency":[82],"interpretability":[84,218],"Potts-based":[86],"inference.":[87],"Across":[88],"families,":[91],"our":[92],"autoregressive":[93,187],"implementation":[94],"matches":[97],"or":[98],"surpasses":[99],"accuracy":[102,181],"established":[104],"models":[105],"reproducing":[107],"higher-order":[108],"statistics":[110],"preserving":[112],"substantial":[113],"diversity.":[115],"Structural":[116],"validation":[117],"AlphaFold":[119],"ESMFold":[121],"confirms":[122],"generated":[124],"sequences":[125],"adopt":[126],"folds":[127],"consistent":[128],"their":[130],"intended":[131],"wild-type":[132],"targets.":[133],"In":[134],"detailed":[136],"study":[138],"Response":[141],"Regulator":[142],"family":[143],"(PF00072),":[144],"which":[145],"comprises":[146],"distinct":[147],"structural":[148,171,215],"subclasses":[149],"linked":[150],"DNA-binding":[153],"domains,":[154],"accurately":[156],"reproduces":[157],"class-specific":[158],"architectures":[159],"when":[160],"conditioned":[161],"on":[162],"subtype-specific":[163],"components,":[165],"highlighting":[166],"its":[167],"potential":[168],"fine-grained":[170],"control.":[172],"Predictions":[173],"experimental":[175],"deep":[176],"mutational":[177],"scanning":[178],"data":[179],"show":[180],"comparable":[182],"unconditioned":[186],"Potts":[188],"models,":[189],"indicating":[190],"also":[193],"captures":[194],"local":[195],"functional":[196],"constraints.":[197],"These":[198],"results":[199],"position":[200],"flexible":[204],"transparent":[206],"approach":[207],"targeted":[209],"generation,":[211],"bridging":[212],"fidelity,":[214],"realism,":[216],"design.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-20T00:00:00"}