{"id":"https://openalex.org/W7225654064","doi":"https://doi.org/10.64898/2026.11.06.764933","title":"Amino acid clustering and epistasis guide sequence-based prediction of phenotype modulation","display_name":"Amino acid clustering and epistasis guide sequence-based prediction of phenotype modulation","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225654064","doi":"https://doi.org/10.64898/2026.11.06.764933"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.06.764933","doi":"https://doi.org/10.64898/2026.11.06.764933","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.06.764933","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.06.764933.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"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/2026/11/09/2026.11.06.764933.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029293020","display_name":"Ayelen Sebastiana Hernandez Berthet","orcid":"https://orcid.org/0000-0002-0115-3215","observed_orcids":["https://orcid.org/0000-0002-0115-3215"]},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Ayelen S. Hernandez Berthet","raw_affiliation_strings":["Universidad de Buenos Aires, Facultad de Ciencias Exactas y Naturales, Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Quimica Biologica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN).;"],"raw_orcid":"https://orcid.org/0000-0002-0115-3215","affiliations":[{"raw_affiliation_string":"Universidad de Buenos Aires, Facultad de Ciencias Exactas y Naturales, Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Quimica Biologica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN).;","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022329235","display_name":"Ignacio Enrique Sanchez","orcid":"https://orcid.org/0000-0003-4284-9013","observed_orcids":["https://orcid.org/0000-0003-4284-9013"]},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Ignacio E. Sanchez","raw_affiliation_strings":["Universidad de Buenos Aires. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Quimica Biologica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN). Facultad de Ciencias Exactas y Naturales. Lab. de Fisiologia de Proteinas.;"],"raw_orcid":"https://orcid.org/0000-0003-4284-9013","affiliations":[{"raw_affiliation_string":"Universidad de Buenos Aires. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Quimica Biologica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN). Facultad de Ciencias Exactas y Naturales. Lab. de Fisiologia de Proteinas.;","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050224551","display_name":"Martin Ezequiel Noguera","orcid":"https://orcid.org/0000-0001-5868-3834","observed_orcids":["https://orcid.org/0000-0001-5868-3834"]},"institutions":[{"id":"https://openalex.org/I138504249","display_name":"National University of Quilmes","ror":"https://ror.org/01r53hz59","country_code":"AR","type":"education","lineage":["https://openalex.org/I138504249"]},{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210149401","display_name":"Instituto de Qu\u00edmica y Fisicoqu\u00edmica Biol\u00f3gicas","ror":"https://ror.org/0469ejq24","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4210149401","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Martin E. Noguera","raw_affiliation_strings":["Consejo Nacional de Investigaciones Cientificas y Tecnicas, Instituto de Quimica y Fisicoquimica Biologicas, Buenos Aires, Argentina.  Departamento de Ciencia y Tecnologia, Universidad Nacional de Quilmes"],"raw_orcid":"https://orcid.org/0000-0001-5868-3834","affiliations":[{"raw_affiliation_string":"Consejo Nacional de Investigaciones Cientificas y Tecnicas, Instituto de Quimica y Fisicoquimica Biologicas, Buenos Aires, Argentina.  Departamento de Ciencia y Tecnologia, Universidad Nacional de Quilmes","institution_ids":["https://openalex.org/I138504249","https://openalex.org/I151201029","https://openalex.org/I4210149401"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090825211","display_name":"Ernesto A. Rom\u00e1n","orcid":"https://orcid.org/0000-0001-9840-4115","observed_orcids":["https://orcid.org/0000-0001-9840-4115"]},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Ernesto A. Roman","raw_affiliation_strings":["Universidad de Buenos Aires, Facultad de Ciencias Exactas y Naturales, Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Quimica Biologica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN).;"],"raw_orcid":"https://orcid.org/0000-0001-9840-4115","affiliations":[{"raw_affiliation_string":"Universidad de Buenos Aires, Facultad de Ciencias Exactas y Naturales, Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Quimica Biologica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN).;","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090825211"],"corresponding_institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"],"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":0.7207000255584717,"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":0.7207000255584717,"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":0.13220000267028809,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.05139999836683273,"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/epistasis","display_name":"epistasis","score":0.9940000176429749},{"id":"https://openalex.org/keywords/hydrophobicity","display_name":"hydrophobicity","score":0.8840000033378601},{"id":"https://openalex.org/keywords/protein-evolution","display_name":"protein evolution","score":0.39100000262260437},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.843999981880188},{"id":"https://openalex.org/keywords/functional-sites","display_name":"functional sites","score":0.38600000739097595},{"id":"https://openalex.org/keywords/protein-families","display_name":"protein families","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C61727976","wikidata":"https://www.wikidata.org/wiki/Q751748","display_name":"Epistasis","level":3,"score":0.8503999710083008},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.7311000227928162},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5878999829292297},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5539000034332275},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.49810001254081726},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.42590001225471497},{"id":"https://openalex.org/C2993683473","wikidata":"https://www.wikidata.org/wiki/Q30693176","display_name":"Amino acid substitution","level":4,"score":0.42399999499320984},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.40630000829696655},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2994376932","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Amino acid residue","level":4,"score":0.3797999918460846},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.3294000029563904},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C55112680","wikidata":"https://www.wikidata.org/wiki/Q190549","display_name":"Functional analysis","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C53105671","wikidata":"https://www.wikidata.org/wiki/Q14777816","display_name":"Rational design","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.28279998898506165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.06.764933","doi":"https://doi.org/10.64898/2026.11.06.764933","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.06.764933","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.06.764933.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.06.764933","doi":"https://doi.org/10.64898/2026.11.06.764933","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.06.764933","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.06.764933.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323257","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225654064.pdf","grobid_xml":"https://content.openalex.org/works/W7225654064.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2171922350","https://openalex.org/W2979707407","https://openalex.org/W4414466579"],"related_works":["https://openalex.org/W4393971104","https://openalex.org/W2115464835","https://openalex.org/W2086235515","https://openalex.org/W3185823040","https://openalex.org/W4387013720","https://openalex.org/W2967372260","https://openalex.org/W4310758694","https://openalex.org/W4399770380","https://openalex.org/W4205094401","https://openalex.org/W2979256289"],"abstract_inverted_index":{"Protein":[0],"sequences":[1],"encode":[2],"the":[3,127,134,159,204,223],"molecular":[4],"information":[5,92],"necessary":[6],"for":[7,222],"their":[8],"biological":[9],"function.":[10],"As":[11],"functional":[12,29,91,124],"adaptation":[13],"often":[14,94,180],"emerges":[15],"from":[16],"combined":[17],"effects":[18],"of":[19,152,185,198,206,213,228],"multiple":[20],"positions,":[21,133],"understanding":[22,212],"how":[23],"sequence":[24,199],"variation":[25],"gives":[26],"rise":[27],"to":[28,41,49,57,123,168,209],"differences":[30],"remains":[31],"a":[32,74,105,183,195],"central":[33],"challenge.":[34],"Here,":[35],"we":[36],"developed":[37],"an":[38],"improved":[39,86],"strategy":[40],"identify":[42],"phenotype":[43,78,109,113],"modulating":[44,114],"positions":[45,115,148,164],"and":[46,119,190,217,226],"use":[47],"them":[48],"predict":[50],"phenotypes,":[51],"by":[52,96,131,182,194],"relating":[53],"amino":[54,82,99,187],"acid":[55,83,100,188],"identity":[56],"experimentally":[58,146],"measured":[59],"quantitative":[60,177],"properties":[61],"across":[62],"families.":[63],"Using":[64],"family-specific":[65],"sequence-phenotype":[66],"datasets,":[67],"our":[68,207,211],"results":[69,174],"show":[70],"that":[71,89,165,176],"epistasis":[72,139],"plays":[73],"crucial":[75,106],"role":[76,107],"in":[77,108],"modulation.":[79,110],"Position":[80],"specific":[81],"clustering":[84],"further":[85],"performance":[87],"indicating":[88],"key":[90],"is":[93,129,136,140],"captured":[95,130,137],"broad":[97],"physicochemical":[98],"classes,":[101],"with":[102,145],"hydrophobicity":[103],"playing":[104],"Our":[111],"identified":[112,147],"involve":[116],"both":[117],"proximal":[118],"distal":[120],"sites":[121],"relative":[122],"sites.":[125],"While":[126],"former":[128],"individual":[132],"latter":[135],"when":[138],"taken":[141],"into":[142],"account.":[143],"Comparison":[144],"showed":[149],"partial":[150],"recovery":[151],"known":[153],"functionally":[154],"relevant":[155],"residues,":[156],"while":[157],"at":[158],"same":[160],"time":[161],"revealing":[162],"candidate":[163],"may":[166,191],"contribute":[167],"phenotypic":[169],"variation.":[170],"Taken":[171],"together,":[172],"these":[173],"suggest":[175],"phenotypes":[178],"are":[179],"governed":[181],"network":[184],"interacting":[186],"residues":[189],"be":[192],"engineered":[193],"limited":[196],"amount":[197],"modifications.":[200],"This":[201],"finding":[202],"highlights":[203],"potential":[205],"framework":[208],"deepen":[210],"protein":[214,229],"function,":[215],"evolution,":[216],"adaptation,":[218],"providing":[219],"new":[220],"targets":[221],"rational":[224],"modulation":[225],"engineering":[227],"phenotypes.":[230]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
