{"id":"https://openalex.org/W7130640639","doi":"https://doi.org/10.64898/2026.02.19.705033","title":"Discrete Diffusion for Single-Cell Gene Expression Modeling","display_name":"Discrete Diffusion for Single-Cell Gene Expression Modeling","publication_year":2026,"publication_date":"2026-02-20","ids":{"openalex":"https://openalex.org/W7130640639","doi":"https://doi.org/10.64898/2026.02.19.705033"},"language":"en","primary_location":{"id":"doi:10.64898/2026.02.19.705033","doi":"https://doi.org/10.64898/2026.02.19.705033","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.19.705033","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/20/2026.02.19.705033.1.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"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/2026/02/20/2026.02.19.705033.1.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126479124","display_name":"Sanjukta Bhattacharya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sanjukta Bhattacharya","raw_affiliation_strings":["University of Bristol"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126471051","display_name":"Christian Gensbigler","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Gensbigler","raw_affiliation_strings":["Dartmouth College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126456105","display_name":"Shaamil Karim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaamil Karim","raw_affiliation_strings":["Dartmouth College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029559361","display_name":"Jonathan Lees","orcid":"https://orcid.org/0000-0003-3925-1424","observed_orcids":["https://orcid.org/0000-0003-3925-1424"]},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Lees","raw_affiliation_strings":["University of Bristol"],"raw_orcid":"https://orcid.org/0000-0003-3925-1424","affiliations":[{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5126479124"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9994999766349792,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9994999766349792,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":9.999999747378752e-05,"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/T10885","display_name":"Gene expression and cancer classification","score":0.0,"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/discrete-diffusion","display_name":"discrete diffusion","score":0.6959999799728394},{"id":"https://openalex.org/keywords/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.9089999794960022},{"id":"https://openalex.org/keywords/discrete-cell-model","display_name":"discrete cell model","score":0.8610000014305115},{"id":"https://openalex.org/keywords/conditional-generative-models","display_name":"conditional generative models","score":0.5979999899864197},{"id":"https://openalex.org/keywords/genetic-perturbation","display_name":"gene perturbation","score":0.828000009059906},{"id":"https://openalex.org/keywords/dentate-gyrus","display_name":"dentate gyrus","score":0.7099999785423279},{"id":"https://openalex.org/keywords/latent-representations","display_name":"latent representations","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5370000004768372},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48899999260902405},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C10184394","wikidata":"https://www.wikidata.org/wiki/Q5165491","display_name":"Continuous modelling","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35260000824928284},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.33410000801086426},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.02.19.705033","doi":"https://doi.org/10.64898/2026.02.19.705033","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.19.705033","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/20/2026.02.19.705033.1.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.02.19.705033","doi":"https://doi.org/10.64898/2026.02.19.705033","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.19.705033","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/20/2026.02.19.705033.1.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130640639.pdf","grobid_xml":"https://content.openalex.org/works/W7130640639.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2102212449","https://openalex.org/W2171280873","https://openalex.org/W2561754210","https://openalex.org/W2562947047","https://openalex.org/W2783380616","https://openalex.org/W2901677030","https://openalex.org/W2961177472","https://openalex.org/W2997280954","https://openalex.org/W3002770500","https://openalex.org/W3217508244","https://openalex.org/W4327550249","https://openalex.org/W4375955255","https://openalex.org/W4390872297","https://openalex.org/W4392168151","https://openalex.org/W4401794004","https://openalex.org/W4411757935","https://openalex.org/W7093313664"],"related_works":["https://openalex.org/W7104283769","https://openalex.org/W7127617180","https://openalex.org/W4411996986","https://openalex.org/W4387741161","https://openalex.org/W4414130562","https://openalex.org/W7208735616","https://openalex.org/W7203690326","https://openalex.org/W4404945205","https://openalex.org/W7214574483","https://openalex.org/W2901677030"],"abstract_inverted_index":{"A":[0],"bstract":[1],"Current":[2],"generative":[3],"modeling":[4,52],"of":[5,53,127,155],"single-cell":[6],"transcriptomics":[7],"relies":[8],"on":[9,130,137],"continuous":[10,21,112],"latent":[11],"representations,":[12],"transforming":[13],"inherently":[14],"discrete":[15,39,146],"and":[16,46,71,84,100],"sparse":[17],"gene":[18],"counts":[19],"into":[20],"space.":[22],"We":[23,65],"propose":[24],"Discrete":[25],"Cell":[26],"Models":[27],"(DCM),":[28],"a":[29,93,101,124,149],"diffusion-based":[30],"framework":[31,42],"that":[32,67],"learns":[33],"cellular":[34,156],"representations":[35],"directly":[36],"in":[37,96,105],"the":[38,87,110,117,128],"domain.":[40],"Our":[41],"supports":[43],"both":[44],"unconditional":[45],"conditional":[47,118],"generation,":[48],"allowing":[49],"for":[50,152],"precise":[51],"complex":[54],"biological":[55],"scenarios":[56],"such":[57],"as":[58,148],"cell-type-specific":[59],"transcriptional":[60],"responses":[61],"to":[62],"genetic":[63],"perturbations.":[64],"demonstrate":[66],"DCM":[68,91,122],"scales":[69],"effectively":[70],"achieves":[72,92],"strong":[73],"performance":[74],"against":[75],"current":[76],"state-of-the-art":[77],"methods,":[78],"including":[79],"scVI,":[80],"CPA,":[81],"STATE,":[82],"scGPT,":[83],"scLDM.":[85],"On":[86,116],"Dentate":[88],"Gyrus":[89],"benchmark,":[90,121],"5-fold":[94],"improvement":[95,104],"MMD":[97,138],"2":[98,107,132,139],"RBF":[99,140],"nearly":[102],"2-fold":[103],"W":[106,131],"distance,":[108],"over":[109],"leading":[111],"diffusion":[113,147],"baseline":[114],"(scLDM).":[115],"Replogle":[119],"perturbation":[120],"sets":[123],"new":[125],"state":[126],"art":[129],"distance":[133],"while":[134],"remaining":[135],"competitive":[136],".":[141],"Together,":[142],"these":[143],"results":[144],"establish":[145],"promising":[150],"direction":[151],"foundational":[153],"models":[154],"biology.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-02-20T00:00:00"}
