{"id":"https://openalex.org/W7203906397","doi":"https://doi.org/10.64898/2026.08.19.745697","title":"A self-supervised DNA foundation model with collapse-resistant multimodal fusion","display_name":"A self-supervised DNA foundation model with collapse-resistant multimodal fusion","publication_year":2026,"publication_date":"2026-08-20","ids":{"openalex":"https://openalex.org/W7203906397","doi":"https://doi.org/10.64898/2026.08.19.745697"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.19.745697","doi":"https://doi.org/10.64898/2026.08.19.745697","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.19.745697","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/20/2026.08.19.745697.full.pdf","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","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/20/2026.08.19.745697.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060201245","display_name":"Yuyan Chen","orcid":"https://orcid.org/0000-0002-4381-486X","observed_orcids":["https://orcid.org/0000-0002-4381-486X"]},"institutions":[{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"id":"https://openalex.org/I4405286254","display_name":"Houston Methodist Research Institute","ror":"https://ror.org/01mcrxx35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1295876152","https://openalex.org/I4405286254"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuyan Chen","raw_affiliation_strings":["Houston Methodist Research Institute, Houston, TX, USA","ModelsLive Inc., Houston, TX, USA","Weill Cornell Medicine, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4381-486X","affiliations":[{"raw_affiliation_string":"Houston Methodist Research Institute, Houston, TX, USA","institution_ids":["https://openalex.org/I4405286254"]},{"raw_affiliation_string":"ModelsLive Inc., Houston, TX, USA","institution_ids":[]},{"raw_affiliation_string":"Weill Cornell Medicine, New York, NY, USA","institution_ids":["https://openalex.org/I4387153466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060201245"],"corresponding_institution_ids":["https://openalex.org/I4387153466","https://openalex.org/I4405286254"],"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9535999894142151,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9535999894142151,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.014999999664723873,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.00430000014603138,"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/multimodal-fusion","display_name":"multimodal fusion","score":0.8119999766349792},{"id":"https://openalex.org/keywords/chromatin-accessibility","display_name":"chromatin accessibility","score":0.902999997138977},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8410000205039978},{"id":"https://openalex.org/keywords/peak-detection","display_name":"peak detection","score":0.6710000038146973},{"id":"https://openalex.org/keywords/collapse-resistance","display_name":"collapse resistance","score":0.4580000042915344},{"id":"https://openalex.org/keywords/global-normalization","display_name":"global normalization","score":0.6980000138282776},{"id":"https://openalex.org/keywords/shared-encoder","display_name":"shared encoder","score":0.5389999747276306},{"id":"https://openalex.org/keywords/expression-quantitative-trait-loci","display_name":"expression quantitative trait loci","score":0.7099999785423279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C83640560","wikidata":"https://www.wikidata.org/wiki/Q180951","display_name":"Chromatin","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37380000948905945},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3587999939918518},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.33219999074935913},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.19.745697","doi":"https://doi.org/10.64898/2026.08.19.745697","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.19.745697","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/20/2026.08.19.745697.full.pdf","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"}],"best_oa_location":{"id":"doi:10.64898/2026.08.19.745697","doi":"https://doi.org/10.64898/2026.08.19.745697","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.19.745697","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/20/2026.08.19.745697.full.pdf","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203906397.pdf","grobid_xml":"https://content.openalex.org/works/W7203906397.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161168281","https://openalex.org/W7165358424","https://openalex.org/W7223242776","https://openalex.org/W7221574431","https://openalex.org/W7152484855","https://openalex.org/W7214731732","https://openalex.org/W4321478299","https://openalex.org/W4416388790","https://openalex.org/W4404821554","https://openalex.org/W4416393023"],"abstract_inverted_index":{"Abstract":[0],"Genomic":[1],"foundation":[2,74],"models":[3,30],"pretrained":[4],"on":[5,134],"DNA":[6,77],"sequence":[7,54,78],"have":[8,56],"achieved":[9],"strong":[10],"performance":[11],"across":[12],"many":[13],"tasks,":[14],"but":[15],"sequence-only":[16],"representations":[17],"cannot":[18],"fully":[19],"capture":[20],"regulatory":[21,50,111,114],"information":[22],"from":[23],"additional":[24],"DNA-centric":[25,72],"modalities.":[26],"Existing":[27],"multimodal":[28,73],"genomic":[29],"are":[31],"optimized":[32],"for":[33],"specific":[34],"prediction":[35],"tasks":[36],"rather":[37],"than":[38],"reusable":[39,92],"embeddings.":[40,94],"Directly":[41],"fusing":[42],"heterogeneous":[43],"modalities":[44],"is":[45],"challenging":[46],"because":[47],"sparse,":[48],"peak-shaped":[49],"signals":[51],"and":[52,82,117,139],"dense":[53],"embeddings":[55,79,109],"markedly":[57],"different":[58],"statistical":[59],"structures,":[60],"making":[61],"naive":[62],"alignment":[63],"prone":[64],"to":[65,90],"near-zero":[66],"solutions.":[67],"We":[68,95],"present":[69],"a":[70,87,123],"self-supervised":[71],"model":[75],"integrating":[76],"with":[80,131],"local":[81],"global":[83,98],"chromatin":[84,118],"accessibility":[85,119],"in":[86],"shared":[88],"encoder":[89],"produce":[91],"window-level":[93],"show":[96],"that":[97],"normalization":[99],"alleviates":[100],"this":[101],"collapse,":[102],"enabling":[103],"effective":[104],"joint":[105],"learning.":[106],"The":[107],"resulting":[108],"improve":[110],"activity":[112],"prediction,":[113],"signal":[115],"ranking":[116],"peak":[120],"detection,":[121],"achieving":[122],"4.6-fold":[124],"AUPRC":[125],"improvement":[126],"over":[127],"the":[128],"DNA-only":[129],"baseline,":[130],"further":[132],"gains":[133],"external":[135],"ClinVar,":[136],"GTEx":[137],"eQTL":[138],"PBMC":[140],"caQTL":[141],"datasets.":[142]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-22T00:00:00"}