{"id":"https://openalex.org/W7213515926","doi":"https://doi.org/10.64898/2026.09.16.751972","title":"Modeling Protein Sequence Evolution as an Ornstein-Uhlenbeck Process in a Latent Space","display_name":"Modeling Protein Sequence Evolution as an Ornstein-Uhlenbeck Process in a Latent Space","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213515926","doi":"https://doi.org/10.64898/2026.09.16.751972"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.16.751972","doi":"https://doi.org/10.64898/2026.09.16.751972","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.16.751972","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.16.751972.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.16.751972.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093130928","display_name":"Matteo De Leonardis","orcid":"https://orcid.org/0000-0003-4082-4170","observed_orcids":["https://orcid.org/0000-0003-4082-4170"]},"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":"Matteo De Leonardis","raw_affiliation_strings":["DISAT, Politecnico di Torino, Corso Duca degli Abruzzi, 10129 Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4082-4170","affiliations":[{"raw_affiliation_string":"DISAT, Politecnico di Torino, Corso Duca degli Abruzzi, 10129 Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011435835","display_name":"Andrea Pagnani","orcid":"https://orcid.org/0000-0002-6509-0807","observed_orcids":["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":["DISAT, Politecnico di Torino, Corso Duca degli Abruzzi, 10129 Torino, Italy","INFN, Sezione di Torino, Via Pietro Giuria 1, Torino 10125, Italy","Italian Institute for Genomic Medicine, IRCCS Candiolo, SP-142, 10060 Candiolo, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6509-0807","affiliations":[{"raw_affiliation_string":"DISAT, Politecnico di Torino, Corso Duca degli Abruzzi, 10129 Torino, Italy","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"INFN, Sezione di Torino, Via Pietro Giuria 1, Torino 10125, Italy","institution_ids":["https://openalex.org/I4210099850"]},{"raw_affiliation_string":"Italian Institute for Genomic Medicine, IRCCS Candiolo, SP-142, 10060 Candiolo, Italy","institution_ids":["https://openalex.org/I4210123319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093130928"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9067000150680542,"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":0.9067000150680542,"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.0364999994635582,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.01510000042617321,"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/protein-sequence-evolution","display_name":"protein sequence evolution","score":0.9850000143051147},{"id":"https://openalex.org/keywords/ornstein-uhlenbeck-process","display_name":"Ornstein-Uhlenbeck process","score":0.9950000047683716},{"id":"https://openalex.org/keywords/latent-space","display_name":"latent space","score":0.8679999709129333},{"id":"https://openalex.org/keywords/directed-evolution","display_name":"directed evolution","score":0.8679999709129333},{"id":"https://openalex.org/keywords/contact-prediction","display_name":"contact prediction","score":0.6769999861717224},{"id":"https://openalex.org/keywords/potts-model","display_name":"Potts model","score":0.828000009059906},{"id":"https://openalex.org/keywords/evolutionary-coupling","display_name":"evolutionary coupling","score":0.5720000267028809},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.6520000100135803},{"id":"https://openalex.org/keywords/beta-lactamase","display_name":"beta-lactamase","score":0.7319999933242798},{"id":"https://openalex.org/keywords/dihydrofolate-reductase","display_name":"dihydrofolate reductase","score":0.9990000128746033},{"id":"https://openalex.org/keywords/long-range-contacts","display_name":"long-range contacts","score":0.5490000247955322}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7062000036239624},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C30711495","wikidata":"https://www.wikidata.org/wiki/Q289411","display_name":"Sequence space","level":3,"score":0.5960000157356262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5728999972343445},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105999708175659},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C72010251","wikidata":"https://www.wikidata.org/wiki/Q5265688","display_name":"Determinantal point process","level":4,"score":0.2842999994754791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.2761000096797943},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2711000144481659},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C176066374","wikidata":"https://www.wikidata.org/wiki/Q629118","display_name":"Fitness function","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.16.751972","doi":"https://doi.org/10.64898/2026.09.16.751972","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.16.751972","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.16.751972.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.16.751972","doi":"https://doi.org/10.64898/2026.09.16.751972","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.16.751972","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.16.751972.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213515926.pdf","grobid_xml":"https://content.openalex.org/works/W7213515926.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3004909540","https://openalex.org/W7166730467","https://openalex.org/W7128594600","https://openalex.org/W7223549727","https://openalex.org/W4394839854","https://openalex.org/W2137566700","https://openalex.org/W1497117862","https://openalex.org/W3214001634","https://openalex.org/W2995361046","https://openalex.org/W4306670519"],"abstract_inverted_index":{"Abstract":[0],"High-throughput":[1],"directed":[2],"evolution":[3],"produces":[4],"longitudinal":[5],"sequence":[6,56,91],"libraries":[7],"that":[8,33,68],"are":[9],"ideal":[10],"for":[11,19],"probing":[12],"local":[13],"fitness":[14],"neighborhoods":[15],"but":[16],"often":[17],"underpowered":[18],"global":[20,102],"inference":[21,31],"tasks":[22],"such":[23],"as":[24,63],"contact":[25,98],"prediction.":[26],"We":[27,42],"present":[28],"an":[29,64,86],"unsupervised":[30],"model":[32,59,89],"integrates":[34],"directed-evolution":[35],"sequencing":[36],"time":[37],"series":[38],"with":[39,107,138],"natural":[40,54,133],"homologs.":[41],"project":[43],"sequences":[44],"into":[45],"a":[46,80],"low-dimensional":[47],"latent":[48,74],"space":[49],"[1]":[50],"learned":[51],"from":[52,105],"the":[53,60,73,120],"multiple":[55],"alignment":[57],"and":[58,76,116,143],"experimental":[61,135],"process":[62],"Ornstein\u2013Uhlenbeck":[65],"dynamics":[66],"in":[67,90,141],"space.":[69,92],"Maximum-likelihood":[70],"estimation":[71],"of":[72],"drift":[75],"noise":[77],"parameters":[78],"determines":[79],"stationary":[81],"Gaussian":[82],"distribution,":[83],"which":[84],"induces":[85],"effective":[87],"Potts":[88],"The":[93],"inferred":[94],"couplings":[95],"improve":[96],"structural":[97],"prediction":[99],"by":[100,129],"combining":[101],"evolutionary":[103],"constraints":[104],"nature":[106],"local,":[108],"experiment-specific":[109],"signals.":[110],"Experiments":[111],"on":[112],"PSE1":[113],"\u03b2":[114],"-lactamase":[115],"dihydrofolate":[117],"reductase":[118],"demonstrate":[119],"ability":[121],"to":[122],"identify":[123],"correct":[124],"complementary":[125],"contacts":[126],"not":[127],"recovered":[128],"methods":[130],"using":[131],"either":[132],"or":[134],"data":[136],"alone,":[137],"gains":[139],"concentrated":[140],"intermediate-":[142],"long-range":[144],"contacts.":[145]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-18T00:00:00"}