{"id":"https://openalex.org/W4403547222","doi":"https://doi.org/10.1101/2024.10.15.618510","title":"Training deep learning models on personalized genomic sequences improves variant effect prediction","display_name":"Training deep learning models on personalized genomic sequences improves variant effect prediction","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403547222","doi":"https://doi.org/10.1101/2024.10.15.618510","pmid":"https://pubmed.ncbi.nlm.nih.gov/39463940","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11507713"},"language":"en","primary_location":{"id":"doi:10.1101/2024.10.15.618510","doi":"https://doi.org/10.1101/2024.10.15.618510","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.10.15.618510","pdf_url":null,"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","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1101/2024.10.15.618510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126496422","display_name":"Adam Youlin He","orcid":"https://orcid.org/0000-0003-2084-6970","observed_orcids":["https://orcid.org/0000-0003-2084-6970"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Y He","raw_affiliation_strings":["Cornell University, Ithaca, NY 14850","Cornell University"],"raw_orcid":"https://orcid.org/0000-0003-2084-6970","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY 14850","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114325285","display_name":"Nathan P Palamuttam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan P Palamuttam","raw_affiliation_strings":["Cornell University, Ithaca, NY 14850","Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY 14850","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024923108","display_name":"Charles G. Danko","orcid":"https://orcid.org/0000-0002-1999-7125","observed_orcids":["https://orcid.org/0000-0002-1999-7125"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Charles G Danko","raw_affiliation_strings":["Cornell University, Ithaca, NY 14850","Cornell University"],"raw_orcid":"https://orcid.org/0000-0002-1999-7125","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY 14850","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024923108"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.6137999892234802,"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"}},"topics":[{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.6137999892234802,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.20250000059604645,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0333000011742115,"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/variant-effect-prediction","display_name":"variant effect prediction","score":0.9919999837875366},{"id":"https://openalex.org/keywords/functional-genomic-data","display_name":"functional genomic data","score":0.8700000047683716},{"id":"https://openalex.org/keywords/cellular-context","display_name":"cellular context","score":0.4959999918937683}],"concepts":[{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6537767648696899},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.6331765651702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6002050638198853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5824054479598999},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5654199123382568},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5646670460700989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.531877875328064},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.498030424118042},{"id":"https://openalex.org/C2993967602","wikidata":"https://www.wikidata.org/wiki/Q5532932","display_name":"Genetic variants","level":4,"score":0.4870796501636505},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.4778004288673401},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4632384181022644},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4547599256038666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4355739653110504},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4348648488521576},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.41288521885871887},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3414533734321594},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.26745301485061646},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23191902041435242},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1313531994819641},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.07311388850212097},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06595098972320557},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1101/2024.10.15.618510","doi":"https://doi.org/10.1101/2024.10.15.618510","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.10.15.618510","pdf_url":null,"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"},{"id":"pmid:39463940","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39463940","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,"listed_in":[],"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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11507713","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11507713","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,"listed_in":[],"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":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1101/2024.10.15.618510","doi":"https://doi.org/10.1101/2024.10.15.618510","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.10.15.618510","pdf_url":null,"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":[{"score":0.4000000059604645,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2868921350","display_name":"Research and Career Training in Vertebrate Developmental Genomics","funder_award_id":"T32HD057854","funder_id":"https://openalex.org/F4320337611","funder_display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development"},{"id":"https://openalex.org/G4110359441","display_name":"Evolution of Chromatin Architecture and Transcriptional Regulation in Mammals","funder_award_id":"5r01hg010346-04","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337611","display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","ror":"https://ror.org/04byxyr05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2015845481","https://openalex.org/W2091533196","https://openalex.org/W2107596936","https://openalex.org/W2412481123","https://openalex.org/W2883945062","https://openalex.org/W2897250433","https://openalex.org/W2906884244","https://openalex.org/W2988126442","https://openalex.org/W3010608652","https://openalex.org/W3087265072","https://openalex.org/W3107875361","https://openalex.org/W3130819465","https://openalex.org/W3203588026","https://openalex.org/W4213336556","https://openalex.org/W4220820191","https://openalex.org/W4280512834","https://openalex.org/W4361001523","https://openalex.org/W4389174422","https://openalex.org/W4389174423","https://openalex.org/W4389613138","https://openalex.org/W4389613185","https://openalex.org/W4395447546"],"related_works":["https://openalex.org/W4414567003","https://openalex.org/W7125967877","https://openalex.org/W4404570578","https://openalex.org/W4410717731","https://openalex.org/W4394681169","https://openalex.org/W7203650487","https://openalex.org/W7166328984","https://openalex.org/W4399297436","https://openalex.org/W4411441294","https://openalex.org/W6906761392"],"abstract_inverted_index":{"Sequence-to-function":[0],"models":[1,28,53],"have":[2,14,63],"broad":[3],"applications":[4],"in":[5,20],"interpreting":[6,66],"the":[7],"molecular":[8],"impact":[9],"of":[10],"genetic":[11,68],"variation,":[12],"yet":[13],"been":[15],"criticized":[16],"for":[17,65],"poor":[18],"performance":[19,39],"this":[21],"task.":[22],"Here":[23],"we":[24],"show":[25],"that":[26],"training":[27],"on":[29],"functional":[30],"genomic":[31],"data":[32],"with":[33],"matched":[34],"personal":[35],"genomes":[36],"improves":[37],"their":[38],"at":[40],"variant":[41],"effect":[42,45],"prediction.":[43],"Variant":[44],"representations":[46],"are":[47],"retained":[48],"even":[49],"when":[50],"fine":[51],"tuning":[52],"to":[54],"unseen":[55],"cellular":[56],"contexts":[57],"and":[58],"experimental":[59],"readouts.":[60],"Our":[61],"results":[62],"implications":[64],"trait-associated":[67],"variation.":[69]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2024-10-19T00:00:00"}
