{"id":"https://openalex.org/W4400678881","doi":"https://doi.org/10.1093/bioinformatics/btae447","title":"Enhancing predictions of protein stability changes induced by single mutations using MSA-based language models","display_name":"Enhancing predictions of protein stability changes induced by single mutations using MSA-based language models","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4400678881","doi":"https://doi.org/10.1093/bioinformatics/btae447","pmid":"https://pubmed.ncbi.nlm.nih.gov/39012369"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae447","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae447","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/7/btae447/58644482/btae447.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/40/7/btae447/58644482/btae447.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008581467","display_name":"Francesca Cuturello","orcid":"https://orcid.org/0000-0001-7242-7298"},"institutions":[{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Francesca Cuturello","raw_affiliation_strings":["Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy"],"raw_orcid":"https://orcid.org/0000-0001-7242-7298","affiliations":[{"raw_affiliation_string":"Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082814796","display_name":"Marco Celoria","orcid":"https://orcid.org/0000-0003-1406-7129"},"institutions":[{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]},{"id":"https://openalex.org/I4210119786","display_name":"Cineca","ror":"https://ror.org/02f013h18","country_code":"IT","type":"other","lineage":["https://openalex.org/I4210119786"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Celoria","raw_affiliation_strings":["HPC Department, , CINECA National Supercomputing Center , Bologna 40033, Italy","Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1406-7129","affiliations":[{"raw_affiliation_string":"HPC Department, , CINECA National Supercomputing Center , Bologna 40033, Italy","institution_ids":["https://openalex.org/I4210119786"]},{"raw_affiliation_string":"Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083733233","display_name":"Alessio Ansuini","orcid":"https://orcid.org/0000-0002-3117-3532"},"institutions":[{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Ansuini","raw_affiliation_strings":["Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3117-3532","affiliations":[{"raw_affiliation_string":"Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005920708","display_name":"Alberto Cazzaniga","orcid":"https://orcid.org/0000-0001-6271-3303"},"institutions":[{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Cazzaniga","raw_affiliation_strings":["Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6271-3303","affiliations":[{"raw_affiliation_string":"Research and Technology Institute, , AREA Science Park , Trieste 34149, Italy","institution_ids":["https://openalex.org/I2801626668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008581467"],"corresponding_institution_ids":["https://openalex.org/I2801626668"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.0158,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86651433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"40","issue":"7","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":0.2930000126361847,"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":0.2930000126361847,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.17080000042915344,"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":0.11540000140666962,"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/overfitting","display_name":"Overfitting","score":0.8246911764144897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686302661895752},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.665446400642395},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5021975040435791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4537050127983093},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4383336305618286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3347667455673218}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8246911764144897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686302661895752},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.665446400642395},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5021975040435791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4537050127983093},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4383336305618286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3347667455673218},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btae447","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae447","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/7/btae447/58644482/btae447.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:39012369","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39012369","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11269464","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11269464","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11269464/pdf/btae447.pdf","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae447","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae447","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/7/btae447/58644482/btae447.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2334606655","display_name":null,"funder_award_id":"IR0000028","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400678881.pdf"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W2003890287","https://openalex.org/W2023490488","https://openalex.org/W2025670719","https://openalex.org/W2031553026","https://openalex.org/W2041476324","https://openalex.org/W2049888624","https://openalex.org/W2051210555","https://openalex.org/W2063274819","https://openalex.org/W2064488723","https://openalex.org/W2085993579","https://openalex.org/W2088409695","https://openalex.org/W2099459640","https://openalex.org/W2099672241","https://openalex.org/W2108067237","https://openalex.org/W2109441358","https://openalex.org/W2111326065","https://openalex.org/W2111878373","https://openalex.org/W2136513422","https://openalex.org/W2151529283","https://openalex.org/W2158714788","https://openalex.org/W2164004777","https://openalex.org/W2207955902","https://openalex.org/W2324374958","https://openalex.org/W2428593791","https://openalex.org/W2557595285","https://openalex.org/W2606439133","https://openalex.org/W2615841538","https://openalex.org/W2735621019","https://openalex.org/W2794503008","https://openalex.org/W2801491392","https://openalex.org/W2916078022","https://openalex.org/W2955704392","https://openalex.org/W2972411752","https://openalex.org/W2995514860","https://openalex.org/W2998716839","https://openalex.org/W3048947632","https://openalex.org/W3083008290","https://openalex.org/W3093556707","https://openalex.org/W3105751341","https://openalex.org/W3109312535","https://openalex.org/W3117622225","https://openalex.org/W3121000782","https://openalex.org/W3136963718","https://openalex.org/W3146944767","https://openalex.org/W3166142427","https://openalex.org/W3171481040","https://openalex.org/W3177828909","https://openalex.org/W3179485843","https://openalex.org/W4200321201","https://openalex.org/W4206007286","https://openalex.org/W4210494137","https://openalex.org/W4223644783","https://openalex.org/W4229331784","https://openalex.org/W4320855461","https://openalex.org/W4327550249","https://openalex.org/W4366392978","https://openalex.org/W4375858802","https://openalex.org/W4376612841","https://openalex.org/W4379600237","https://openalex.org/W4384820649","https://openalex.org/W4385245566","https://openalex.org/W4387540805","https://openalex.org/W4388486442","https://openalex.org/W4391308485","https://openalex.org/W4400878092","https://openalex.org/W4400921915","https://openalex.org/W6739901393","https://openalex.org/W6791955017","https://openalex.org/W6798272402","https://openalex.org/W6850045305"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W2989932438","https://openalex.org/W4387297750","https://openalex.org/W2186333919"],"abstract_inverted_index":{"MOTIVATION:":[0],"Protein":[1,66],"Language":[2,67],"Models":[3],"offer":[4],"a":[5,38,65,80,116,183],"new":[6],"perspective":[7],"for":[8,41],"addressing":[9],"challenges":[10],"in":[11,26,29,164,186,189],"structural":[12],"biology,":[13],"while":[14],"relying":[15],"solely":[16],"on":[17],"sequence":[18],"information.":[19],"Recent":[20],"studies":[21,109],"have":[22],"investigated":[23],"their":[24],"effectiveness":[25],"forecasting":[27],"shifts":[28],"thermodynamic":[30],"stability":[31,191],"caused":[32],"by":[33,52,97],"single":[34],"amino":[35],"acid":[36],"mutations,":[37],"task":[39],"known":[40],"its":[42,157],"complexity":[43],"due":[44],"to":[45,74,89,119,159,182],"the":[46,121,131,140,148,152,169],"sparse":[47],"availability":[48],"of":[49,104,124],"data,":[50],"constrained":[51],"experimental":[53],"limitations.":[54],"To":[55],"tackle":[56],"this":[57],"problem,":[58],"we":[59],"introduce":[60],"two":[61],"key":[62],"novelties:":[63],"leveraging":[64],"Model":[68],"that":[69],"incorporates":[70],"Multiple":[71],"Sequence":[72],"Alignments":[73],"capture":[75],"evolutionary":[76],"information,":[77],"and":[78,110,176,200],"using":[79],"recently":[81],"released":[82],"mega-scale":[83],"dataset":[84],"with":[85,139],"rigorous":[86],"data":[87,125,201],"pre-processing":[88],"mitigate":[90],"overfitting.":[91],"RESULTS:":[92],"We":[93],"ensure":[94],"comprehensive":[95],"comparisons":[96],"fine-tuning":[98],"various":[99],"pre-trained":[100],"models,":[101],"taking":[102],"advantage":[103],"analyses":[105],"such":[106],"as":[107,147],"ablation":[108],"baselines":[111],"evaluation.":[112],"Our":[113],"methodology":[114],"introduces":[115],"stringent":[117],"policy":[118],"reduce":[120],"widespread":[122],"issue":[123],"leakage,":[126],"rigorously":[127],"removing":[128],"sequences":[129],"from":[130,193],"training":[132],"set":[133],"when":[134],"they":[135],"exhibit":[136],"significant":[137],"similarity":[138],"test":[141],"set.":[142],"The":[143],"MSA":[144,171],"Transformer":[145,172],"emerges":[146],"most":[149],"accurate":[150],"among":[151],"models":[153],"under":[154],"investigation,":[155],"given":[156],"capability":[158],"leverage":[160],"co-evolution":[161],"signals":[162],"encoded":[163],"aligned":[165],"homologous":[166],"sequences.":[167],"Moreover,":[168],"optimized":[170],"outperforms":[173],"existing":[174],"methods":[175],"exhibits":[177],"enhanced":[178],"generalization":[179],"power,":[180],"leading":[181],"notable":[184],"improvement":[185],"predicting":[187],"changes":[188],"protein":[190],"resulting":[192],"point":[194],"mutations.":[195],"AVAILABILITY":[196],"AND":[197],"IMPLEMENTATION:":[198],"Code":[199],"at":[202,210],"https://github.com/RitAreaSciencePark/PLM4Muts.":[203],"SUPPLEMENTARY":[204],"INFORMATION:":[205],"Supplementary":[206],"Information":[207],"is":[208],"available":[209],"Bioinformatics":[211],"online.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
