{"id":"https://openalex.org/W4403745771","doi":"https://doi.org/10.21203/rs.3.rs-5277088/v1","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":"2024-10-24","ids":{"openalex":"https://openalex.org/W4403745771","doi":"https://doi.org/10.21203/rs.3.rs-5277088/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-5277088/v1","doi":"https://doi.org/10.21203/rs.3.rs-5277088/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5277088/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-5277088/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":false,"raw_author_name":"Charles Danko","raw_affiliation_strings":["Cornell University"],"raw_orcid":"https://orcid.org/0000-0002-1999-7125","affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","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 He","raw_affiliation_strings":["Cornell University"],"raw_orcid":"https://orcid.org/0000-0003-2084-6970","affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","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 Palamuttam","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"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":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.5946999788284302,"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":0.5946999788284302,"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":0.24660000205039978,"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":0.03400000184774399,"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":0.9909999966621399},{"id":"https://openalex.org/keywords/functional-genomic-data","display_name":"functional genomic data","score":0.7360000014305115},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8930000066757202},{"id":"https://openalex.org/keywords/cellular-context","display_name":"cellular context","score":0.621999979019165},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.7049999833106995}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6246522665023804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5694514513015747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5667015314102173},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5510103702545166},{"id":"https://openalex.org/C142039133","wikidata":"https://www.wikidata.org/wiki/Q3620943","display_name":"Personalized learning","level":5,"score":0.506334662437439},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47454318404197693},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4372447431087494},{"id":"https://openalex.org/C32220436","wikidata":"https://www.wikidata.org/wiki/Q2072214","display_name":"Personalized medicine","level":2,"score":0.4227287471294403},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2410752773284912},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.23004430532455444},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16530290246009827},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13017195463180542},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.09213340282440186},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.0},{"id":"https://openalex.org/C15122004","wikidata":"https://www.wikidata.org/wiki/Q385756","display_name":"Open learning","level":4,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-5277088/v1","doi":"https://doi.org/10.21203/rs.3.rs-5277088/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5277088/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-5277088/v1","doi":"https://doi.org/10.21203/rs.3.rs-5277088/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5277088/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.504800021648407,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"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/W7125967877","https://openalex.org/W4414567003","https://openalex.org/W4404570578","https://openalex.org/W4394681169","https://openalex.org/W7166328984","https://openalex.org/W6906761392","https://openalex.org/W7111539227","https://openalex.org/W7203969884","https://openalex.org/W7203650487","https://openalex.org/W7163911915"],"abstract_inverted_index":{"Abstract":[0],"Sequence-to-function":[1],"models":[2,29,54],"have":[3,15,64],"broad":[4],"applications":[5],"in":[6,21],"interpreting":[7,67],"the":[8],"molecular":[9],"impact":[10],"of":[11],"genetic":[12,69],"variation,":[13],"yet":[14],"been":[16],"criticized":[17],"for":[18,66],"poor":[19],"performance":[20,40],"this":[22],"task.":[23],"Here":[24],"we":[25],"show":[26],"that":[27],"training":[28],"on":[30],"functional":[31],"genomic":[32],"data":[33],"with":[34],"matched":[35],"personal":[36],"genomes":[37],"improves":[38],"their":[39],"at":[41],"variant":[42],"effect":[43,46],"prediction.":[44],"Variant":[45],"representations":[47],"are":[48],"retained":[49],"even":[50],"when":[51],"transfer":[52],"learning":[53],"to":[55],"unseen":[56],"cellular":[57],"contexts":[58],"and":[59],"experimental":[60],"readouts.":[61],"Our":[62],"results":[63],"implications":[65],"trait-associated":[68],"variation.":[70]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2024-10-25T00:00:00"}