{"id":"https://openalex.org/W4392575276","doi":"https://doi.org/10.48550/arxiv.2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","display_name":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","publication_year":2024,"publication_date":"2024-03-05","ids":{"openalex":"https://openalex.org/W4392575276","doi":"https://doi.org/10.48550/arxiv.2403.03234","pmid":"https://pubmed.ncbi.nlm.nih.gov/40567809"},"language":"en","primary_location":{"id":"pmid:40567809","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40567809","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":"Proceedings of machine learning research","raw_type":"Journal Article"},"volume":null,"type":"article","indexed_in":["arxiv","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.03234","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024311601","display_name":"Yair Schiff","orcid":"https://orcid.org/0000-0003-0748-3706","observed_orcids":["https://orcid.org/0000-0003-0748-3706"]},"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":"Schiff, Yair","raw_affiliation_strings":["Department of Computer Science , Cornell University , New York , NY USA","Department of Computer Science, Cornell University, New York, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Cornell University , New York , NY USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell University, New York, NY USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027761291","display_name":"Chia-Hsiang Kao","orcid":"https://orcid.org/0009-0006-1956-5265","observed_orcids":["https://orcid.org/0009-0006-1956-5265"]},"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":"Kao, Chia-Hsiang","raw_affiliation_strings":["Department of Computer Science , Cornell University , New York , NY USA","Department of Computer Science, Cornell University, New York, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Cornell University , New York , NY USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell University, New York, NY USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029160764","display_name":"Aaron Gokaslan","orcid":"https://orcid.org/0000-0002-3575-2961","observed_orcids":["https://orcid.org/0000-0002-3575-2961"]},"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":"Gokaslan, Aaron","raw_affiliation_strings":["Department of Computer Science , Cornell University , New York , NY USA","Department of Computer Science, Cornell University, New York, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Cornell University , New York , NY USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell University, New York, NY USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091734792","display_name":"Tri Dao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dao, Tri","raw_affiliation_strings":["Department of Computer Science , Princeton Uni- versity , Princeton , NJ USA","Department of Computer Science, Princeton University, Princeton, NJ USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Princeton Uni- versity , Princeton , NJ USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton, NJ USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025386668","display_name":"Albert Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu, Albert","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University , Pittsburgh , PA USA","School of Computer Science Carnegie Mellon University, Pittsburgh, PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University , Pittsburgh , PA USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University, Pittsburgh, PA USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021338648","display_name":"Volodymyr Kuleshov","orcid":"https://orcid.org/0000-0002-5150-3308","observed_orcids":["https://orcid.org/0000-0002-5150-3308","https://orcid.org/0000-0003-2270-2823"]},"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":"Kuleshov, Volodymyr","raw_affiliation_strings":["Department of Computer Science , Cornell University , New York , NY USA","Department of Computer Science, Cornell University, New York, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Cornell University , New York , NY USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell University, New York, NY USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9199,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97832145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"235","issue":null,"first_page":"43632","last_page":"43648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.79830002784729,"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":0.79830002784729,"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":0.10180000215768814,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.03180000185966492,"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/dna-sequence-modeling","display_name":"DNA sequence modeling","score":0.9409999847412109},{"id":"https://openalex.org/keywords/long-range-interactions","display_name":"long-range interactions","score":0.6539999842643738},{"id":"https://openalex.org/keywords/equivariance","display_name":"equivariance","score":0.8939999938011169},{"id":"https://openalex.org/keywords/protein-dna-interactions","display_name":"protein-DNA interactions","score":0.5559999942779541},{"id":"https://openalex.org/keywords/deep-learning-for-genomics","display_name":"deep learning for genomics","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6089188456535339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5303130149841309},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4817347824573517},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4164929986000061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3913677930831909},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3498322367668152},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.33609312772750854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21279525756835938},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19973799586296082},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07413092255592346},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmid:40567809","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40567809","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":"Proceedings of machine learning research","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2403.03234","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03234","pdf_url":"https://arxiv.org/pdf/2403.03234","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":"pmh:oai:pubmedcentral.nih.gov:12189541","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12189541","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12189541/pdf/nihms-2005895.pdf","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Mach Learn Res","raw_type":"Text"},{"id":"pmh:oai:europepmc.org:10997963","doi":null,"is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12189541","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.48550/arxiv.2403.03234","doi":"https://doi.org/10.48550/arxiv.2403.03234","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.03234","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.03234","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03234","pdf_url":"https://arxiv.org/pdf/2403.03234","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":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7308129950","display_name":"CAREER: Modeling Genetic Variation Using Deep Generative Neural Networks","funder_award_id":"2145577","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8130174209","display_name":"Next-Generation Algorithms in Statistical Genetics Based on Modern Machine Learning","funder_award_id":"1r35gm151243-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392575276.pdf","grobid_xml":"https://content.openalex.org/works/W4392575276.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1721907504"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2372403409","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W2847365777","https://openalex.org/W4242726756","https://openalex.org/W3128025644","https://openalex.org/W2355048207","https://openalex.org/W2750422482","https://openalex.org/W3125827053"],"abstract_inverted_index":{"larger":[0],"models":[1],"that":[2],"do":[3],"not":[4],"leverage":[5],"bi-directionality":[6],"or":[7],"equivariance.":[8],"Code":[9],"to":[10],"reproduce":[11],"our":[12],"experiments":[13],"is":[14],"available":[15],"here.":[16]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":12}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2024-03-08T00:00:00"}