{"id":"https://openalex.org/W7006469199","doi":null,"title":"Training, Evaluating, and Understanding Evolutionary Models for Protein Sequences","display_name":"Training, Evaluating, and Understanding Evolutionary Models for Protein Sequences","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W7006469199"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt56r3b8dn","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/56r3b8dn","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035441206","display_name":"Roshan Rao","orcid":"https://orcid.org/0000-0003-4412-3742","observed_orcids":["https://orcid.org/0000-0003-4412-3742"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rao, Roshan Maruthi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5035441206"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":true,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8148999810218811,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8148999810218811,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.17329999804496765,"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":0.0012000000569969416,"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-language-models","display_name":"protein language models","score":0.9779999852180481},{"id":"https://openalex.org/keywords/protein-contact-prediction","display_name":"protein contact prediction","score":0.7699999809265137},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.7710000276565552},{"id":"https://openalex.org/keywords/protein-design","display_name":"protein design","score":0.4690000116825104},{"id":"https://openalex.org/keywords/protein-evolution","display_name":"protein evolution","score":0.4020000100135803},{"id":"https://openalex.org/keywords/model-scaling","display_name":"model scaling","score":0.5429999828338623},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.7670000195503235},{"id":"https://openalex.org/keywords/training-hyperparameters","display_name":"training hyperparameters","score":0.8529999852180481},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.5690000057220459},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.5049999952316284},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"protein function prediction","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5479000210762024},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5388000011444092},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4828999936580658},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C2992240565","wikidata":"https://www.wikidata.org/wiki/Q856529","display_name":"Protein evolution","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30140000581741333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2924000024795532},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C200307862","wikidata":"https://www.wikidata.org/wiki/Q7797175","display_name":"Threading (protein sequence)","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt56r3b8dn","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/56r3b8dn","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3133458480","https://openalex.org/W4412881098","https://openalex.org/W3193589100","https://openalex.org/W4307068738","https://openalex.org/W4387251420","https://openalex.org/W6980336079","https://openalex.org/W3166142427","https://openalex.org/W6910654408","https://openalex.org/W4319061788","https://openalex.org/W4413290922"],"abstract_inverted_index":{"Novel":[0],"protein":[1,110,119,147,185],"sequences":[2,162],"arise":[3],"through":[4],"mutation.":[5],"These":[6],"mutations":[7],"may":[8],"be":[9,37,95],"deleterious,":[10],"beneficial,":[11],"or":[12],"neutral;":[13],"the":[14,56,68,76,129,141,177],"effect":[15],"of":[16,58,72,78,131,143,160,179,181],"a":[17,42,84,89,98,123],"mutation":[18],"on":[19,122,140,157,172],"an":[20,28,108],"organism\u2019s":[21],"evolutionary":[22,52],"fitness":[23],"is":[24,163,187],"reflected":[25],"in":[26,41,55,184],"whether":[27],"organism":[29],"survives":[30],"long":[31,47],"enough":[32],"for":[33],"its":[34],"proteins":[35],"to":[36,49,63,67,102,115,145,168],"sampled":[38],"and":[39,70,81,117,137,166],"deposited":[40],"sequence":[43],"database.":[44],"Bioinformatics":[45],"has":[46],"sought":[48],"use":[50],"this":[51,112],"signal,":[53],"commonly":[54],"form":[57],"Multiple":[59],"Sequence":[60],"Alignments":[61],"(MSAs),":[62],"make":[64],"inferences":[65],"as":[66],"structure":[69],"function":[71],"novel":[73,154],"proteins.":[74],"With":[75],"advent":[77],"neural":[79,92],"networks":[80],"self-supervised":[82],"pretraining,":[83],"different":[85],"approach":[86],"emerged,":[87],"where":[88],"large":[90],"scale":[91],"network":[93],"could":[94],"pretrained":[96],"using":[97],"language":[99,120],"modeling":[100],"objective":[101],"automatically":[103],"produce":[104],"informative":[105],"features":[106],"from":[107],"input":[109],"sequence.In":[111],"work,":[113],"methods":[114,183],"train":[116],"evaluate":[118],"models":[121],"common":[124],"benchmark":[125],"are":[126,151],"introduced.":[127],"Subsequently,":[128],"effects":[130],"increased":[132],"model":[133],"scaling,":[134],"dataset":[135],"preprocessing":[136],"training":[138],"hyperparameters":[139],"ability":[142],"transformers":[144],"learn":[146],"contacts":[148],"without":[149],"supervision":[150],"explored.":[152],"A":[153],"method":[155],"operating":[156],"MSAs":[158],"instead":[159],"single":[161],"then":[164],"presented,":[165],"shown":[167],"achieve":[169],"state-of-the-art":[170],"performance":[171],"several":[173],"downstream":[174],"tasks.":[175],"Finally,":[176],"utility":[178],"all":[180],"these":[182],"design":[186],"discussed.":[188]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}