{"id":"https://openalex.org/W4415315019","doi":"https://doi.org/10.48550/arxiv.2509.12266","title":"Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models","display_name":"Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models","publication_year":2025,"publication_date":"2025-09-13","ids":{"openalex":"https://openalex.org/W4415315019","doi":"https://doi.org/10.48550/arxiv.2509.12266"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.12266","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.12266","pdf_url":"https://arxiv.org/pdf/2509.12266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12266","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111264305","display_name":"Weimin Wu","orcid":"https://orcid.org/0009-0004-5901-0219","observed_orcids":["https://orcid.org/0009-0004-5901-0219"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Weimin","raw_affiliation_strings":["Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024013042","display_name":"Xuefeng Song","orcid":"https://orcid.org/0000-0002-8579-8706","observed_orcids":["https://orcid.org/0000-0002-8579-8706"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song, Xuefeng","raw_affiliation_strings":["Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111002250","display_name":"Yibo Wen","orcid":"https://orcid.org/0009-0008-1111-7235","observed_orcids":["https://orcid.org/0009-0008-1111-7235"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen, Yibo","raw_affiliation_strings":["Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068801401","display_name":"Qing Lin","orcid":"https://orcid.org/0000-0002-9196-5718","observed_orcids":["https://orcid.org/0000-0002-9196-5718"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Qinjie","raw_affiliation_strings":["Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101973691","display_name":"Zhihan Zhou","orcid":"https://orcid.org/0000-0002-1473-9071","observed_orcids":["https://orcid.org/0000-0002-1473-9071"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Zhihan","raw_affiliation_strings":["Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hu, Jerry Yao-Chieh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Jerry Yao-Chieh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038378121","display_name":"Zhong Wang","orcid":"https://orcid.org/0000-0001-9787-7332","observed_orcids":["https://orcid.org/0000-0001-9787-7332"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100349062","display_name":"Han Liu","orcid":"https://orcid.org/0000-0003-1412-4584","observed_orcids":["https://orcid.org/0000-0003-1412-4584"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Han","raw_affiliation_strings":["Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA","Department of Statistics and Data Science , Northwestern University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Gener- ative AI & Department of Computer Science , Northwestern Uni- versity , USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Statistics and Data Science , Northwestern University , USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8838000297546387,"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":0.8838000297546387,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.051100000739097595,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.01979999989271164,"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/genomic-foundation-models","display_name":"genomic foundation models","score":0.9580000042915344},{"id":"https://openalex.org/keywords/dna-sequence-modeling","display_name":"DNA sequence modeling","score":0.5220000147819519},{"id":"https://openalex.org/keywords/python-library","display_name":"Python library","score":0.7170000076293945},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.9319999814033508},{"id":"https://openalex.org/keywords/dna-sequence-generation","display_name":"DNA sequence generation","score":0.6959999799728394},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.746999979019165},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.8519999980926514},{"id":"https://openalex.org/keywords/sparse-autoencoders","display_name":"sparse autoencoders","score":0.8450000286102295},{"id":"https://openalex.org/keywords/dnabert-2","display_name":"DNABERT-2","score":0.9660000205039978},{"id":"https://openalex.org/keywords/model-deployment","display_name":"model deployment","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050999999046326},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6413999795913696},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38260000944137573},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3522000014781952},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3465999960899353},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.12266","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.12266","pdf_url":"https://arxiv.org/pdf/2509.12266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12266","doi":"https://doi.org/10.48550/arxiv.2509.12266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.12266","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.12266","pdf_url":"https://arxiv.org/pdf/2509.12266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3239935462","display_name":"NSF-Simons AI Institute for the Sky (SkAI Institute)","funder_award_id":"2421845","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415315019.pdf","grobid_xml":"https://content.openalex.org/works/W4415315019.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417298855","https://openalex.org/W4403852135","https://openalex.org/W4391833046","https://openalex.org/W4407424297","https://openalex.org/W7204209660","https://openalex.org/W7223242776","https://openalex.org/W7168220399","https://openalex.org/W4409050923","https://openalex.org/W4415407738","https://openalex.org/W7130641325"],"abstract_inverted_index":{"We":[0,107],"introduce":[1],"Genome-Factory,":[2],"the":[3,24,109],"first":[4],"integrated":[5],"Python":[6],"library":[7],"for":[8,26,146],"tuning,":[9,33,55],"deploying,":[10],"and":[11,22,36,50,60,74,85,121],"interpreting":[12],"genomic":[13,27,48,65,148],"foundation":[14],"models.":[15,66],"Our":[16],"core":[17],"contribution":[18],"is":[19],"to":[20,46,90],"simplify":[21],"unify":[23],"workflow":[25],"model":[28,32,54],"development:":[29],"data":[30,39],"collection,":[31,40],"inference,":[34,68],"benchmarking,":[35,79],"interpretability.":[37],"For":[38,53,67,78,94],"Genome-Factory":[41,56,69,96,112],"offers":[42],"an":[43,98],"automated":[44],"pipeline":[45],"download":[47],"sequences":[49],"preprocess":[51],"them.":[52],"supports":[57],"both":[58,71],"full":[59],"parameter-efficient":[61],"fine-tuning":[62,122],"across":[63,113],"diverse":[64,119],"enables":[70],"embedding":[72],"extraction":[73],"DNA":[75],"sequence":[76],"generation.":[77],"we":[80],"include":[81],"two":[82,129],"existing":[83],"benchmarks":[84],"provide":[86],"a":[87,104],"flexible":[88],"interface":[89],"incorporate":[91],"additional":[92],"benchmarks.":[93],"interpretability,":[95],"introduces":[97],"open-source":[99,130],"biological":[100],"interpreter":[101],"based":[102],"on":[103],"sparse":[105],"auto-encoder.":[106],"validate":[108],"utility":[110],"of":[111,135],"three":[114],"dimensions:":[115],"(i)":[116],"Compatibility":[117],"with":[118,138],"models":[120],"methods;":[123],"(ii)":[124],"Benchmarking":[125],"downstream":[126],"performance":[127],"using":[128],"benchmarks;":[131],"(iii)":[132],"Biological":[133],"interpretation":[134],"learned":[136],"representations":[137],"DNABERT-2.":[139],"These":[140],"results":[141],"highlight":[142],"its":[143],"practical":[144],"value":[145],"real-world":[147],"analysis.":[149],"GitHub:":[150],"https://github.com/WeiminWu2000/Genome_Factory.":[151]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-18T00:00:00"}