{"id":"https://openalex.org/W7140198213","doi":"https://doi.org/10.1093/bioinformatics/btag139","title":"Pretraining improves prediction of genomic datasets across species","display_name":"Pretraining improves prediction of genomic datasets across species","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7140198213","doi":"https://doi.org/10.1093/bioinformatics/btag139","pmid":"https://pubmed.ncbi.nlm.nih.gov/41872014"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag139","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag139","pdf_url":null,"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://doi.org/10.1093/bioinformatics/btag139","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fangrui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangrui Huang","raw_affiliation_strings":["Boston University Department of Computer Science, , Boston, MA, 02215,","Stanford University Department of Computer Science, , Stanford, CA, 94305,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University Department of Computer Science, , Boston, MA, 02215,","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I33434090"]},{"raw_affiliation_string":"Stanford University Department of Computer Science, , Stanford, CA, 94305,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yitong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yitong Wang","raw_affiliation_strings":["Boston University Department of Computer Science, , Boston, MA, 02215,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University Department of Computer Science, , Boston, MA, 02215,","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I33434090"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ashok Cutkosky","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashok Cutkosky","raw_affiliation_strings":["Boston University Department of Electrical and Computer Engineering, , Boston, MA, 02215,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University Department of Electrical and Computer Engineering, , Boston, MA, 02215,","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":null,"display_name":"Janet H T Song","orcid":"https://orcid.org/0000-0002-7898-0227"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]},{"id":"https://openalex.org/I4210109333","display_name":"Evolutionary Genomics (United States)","ror":"https://ror.org/021z7gb33","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109333"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Janet H T Song","raw_affiliation_strings":["Harvard University Department of Human Evolutionary Biology, , Cambridge, MA, 02138,"],"raw_orcid":"https://orcid.org/0000-0002-7898-0227","affiliations":[{"raw_affiliation_string":"Harvard University Department of Human Evolutionary Biology, , Cambridge, MA, 02138,","institution_ids":["https://openalex.org/I4210109333","https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111088046","https://openalex.org/I2801851002","https://openalex.org/I4210109333"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33879084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.2152000069618225,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.2152000069618225,"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/T10885","display_name":"Gene expression and cancer classification","score":0.1168999969959259,"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/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.09179999679327011,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5475999712944031},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3880000114440918},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3314000070095062},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.319599986076355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219000220298767},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5098000168800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44699999690055847},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4092000126838684},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.319599986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25760000944137573}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098410","descriptor_name":"Transfer Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btag139","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag139","pdf_url":null,"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:41872014","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41872014","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag139","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag139","pdf_url":null,"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/G6417972170","display_name":"AF: Small: Advances in Private Optimization","funder_award_id":"2211718","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W2016015848","https://openalex.org/W2048385877","https://openalex.org/W2198606573","https://openalex.org/W2256694280","https://openalex.org/W2952239877","https://openalex.org/W2963341956","https://openalex.org/W3026475692","https://openalex.org/W3042669608","https://openalex.org/W3092091222","https://openalex.org/W3130819465","https://openalex.org/W3203588026","https://openalex.org/W4211030719","https://openalex.org/W4406178430","https://openalex.org/W4410876481"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Recent":[1],"studies":[2],"suggest":[3],"that":[4,57,140,149],"deep":[5],"neural":[6],"network":[7],"models":[8,30,78,120,185],"trained":[9,121],"on":[10,80,95,100,198],"thousands":[11],"of":[12,37,77,90,173],"human":[13,81,96],"genomic":[14,19,82,101],"datasets":[15,36,83,102],"can":[16],"accurately":[17],"predict":[18],"features,":[20],"including":[21,141],"gene":[22],"expression":[23],"and":[24,33,35,65,106,131,148,168,179,190,200],"chromatin":[25],"accessibility.":[26],"However,":[27],"training":[28,63,116,143,174],"these":[29],"is":[31,196],"computation-":[32],"time-intensive,":[34],"comparable":[38],"size":[39],"do":[40],"not":[41,156],"exist":[42],"for":[43,182],"most":[44],"other":[45],"organisms.":[46],"RESULTS:":[47],"Here,":[48],"we":[49,73,138],"identify":[50],"modifications":[51],"to":[52,84,87,119],"an":[53],"existing":[54],"state-of-the-art":[55],"model":[56,59,71,146,163],"improve":[58],"accuracy":[60,112],"while":[61,113],"reducing":[62,115],"time":[64,117],"computational":[66],"cost.":[67],"Using":[68],"this":[69,150],"streamlined":[70],"architecture,":[72,164],"investigate":[74],"the":[75,171],"ability":[76],"pretrained":[79,94,166],"transfer":[85],"performance":[86,147],"a":[88],"variety":[89],"different":[91],"tasks.":[92],"Models":[93],"data":[97,187],"but":[98,155],"fine-tuned":[99],"from":[103,122],"diverse":[104],"tissues":[105],"species":[107],"achieved":[108],"significantly":[109,114],"higher":[110],"prediction":[111],"compared":[118],"scratch,":[123],"with":[124],"Pearson":[125],"correlation":[126],"coefficients":[127],"between":[128],"experimental":[129],"results":[130],"predictions":[132],"as":[133,135],"high":[134],"0.8.":[136],"Further,":[137],"found":[139],"excessive":[142],"tasks":[144,175],"decreased":[145],"decrease":[151],"could":[152],"be":[153,177],"partially":[154],"completely":[157],"rescued":[158],"by":[159],"fine-tuning.":[160],"Thus,":[161],"simplifying":[162],"applying":[165],"models,":[167],"carefully":[169],"considering":[170],"number":[172],"may":[176],"effective":[178],"economical":[180],"techniques":[181],"building":[183],"new":[184],"across":[186],"types,":[188],"tissues,":[189],"species.":[191],"AVAILABILITY":[192],"AND":[193],"IMPLEMENTATION:":[194],"Code":[195],"available":[197],"GitHub":[199],"Figshare:":[201],"https://github.com/optimizedlearning/genomicsML,":[202],"https://doi.org/10.6084/m9.figshare.31796116.":[203]},"counts_by_year":[],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2026-03-25T00:00:00"}
