{"id":"https://openalex.org/W7225118949","doi":"https://doi.org/10.64898/2026.10.24.761590","title":"scRM: A single-cell foundation model trained on scRNA-seq reads","display_name":"scRM: A single-cell foundation model trained on scRNA-seq reads","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225118949","doi":"https://doi.org/10.64898/2026.10.24.761590"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.24.761590","doi":"https://doi.org/10.64898/2026.10.24.761590","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761590","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/02/2026.10.24.761590.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","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/02/2026.10.24.761590.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053741557","display_name":"Dongze He","orcid":"https://orcid.org/0000-0001-8259-7434","observed_orcids":["https://orcid.org/0000-0001-8259-7434"]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongze He","raw_affiliation_strings":["Altos Labs"],"raw_orcid":"https://orcid.org/0000-0001-8259-7434","affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014584023","display_name":"Rob Patro","orcid":"https://orcid.org/0000-0001-8463-1675","observed_orcids":["https://orcid.org/0000-0001-8463-1675"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Patro","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":"https://orcid.org/0000-0001-8463-1675","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046140934","display_name":"Marcel Nassar","orcid":"https://orcid.org/0000-0002-7628-8819","observed_orcids":["https://orcid.org/0000-0002-7628-8819"]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcel Nassar","raw_affiliation_strings":["Altos Labs"],"raw_orcid":"https://orcid.org/0000-0002-7628-8819","affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160385275","display_name":"Haiyu Wu","orcid":"https://orcid.org/0000-0002-0070-9058","observed_orcids":["https://orcid.org/0000-0002-0070-9058"]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyu Wu","raw_affiliation_strings":["Altos Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067740612","display_name":"Qi Jiang Yan","orcid":"https://orcid.org/0000-0003-4418-123X","observed_orcids":["https://orcid.org/0000-0003-4418-123X"]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Yan","raw_affiliation_strings":["Altos Labs"],"raw_orcid":"https://orcid.org/0000-0003-4418-123X","affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160347433","display_name":"Glenn Xu","orcid":"https://orcid.org/0009-0008-3818-5756","observed_orcids":["https://orcid.org/0009-0008-3818-5756"]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Glenn Xu","raw_affiliation_strings":["Altos Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160336627","display_name":"Kristof Torkenczy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristof Torkenczy","raw_affiliation_strings":["Altos Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058394036","display_name":"Jamin Liu","orcid":"https://orcid.org/0000-0001-6386-3709","observed_orcids":["https://orcid.org/0000-0001-6386-3709"]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamin Liu","raw_affiliation_strings":["Altos Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079425446","display_name":"Stefka Tyanova","orcid":"https://orcid.org/0000-0002-1974-5876","observed_orcids":["https://orcid.org/0000-0002-1974-5876"]},"institutions":[{"id":"https://openalex.org/I4387153853","display_name":"Altos Labs","ror":"https://ror.org/05467hx49","country_code":"US","type":"company","lineage":["https://openalex.org/I4387153853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefka Tyanova","raw_affiliation_strings":["Altos Labs"],"raw_orcid":"https://orcid.org/0000-0002-1974-5876","affiliations":[{"raw_affiliation_string":"Altos Labs","institution_ids":["https://openalex.org/I4387153853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053741557"],"corresponding_institution_ids":["https://openalex.org/I4387153853"],"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/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/T10885","display_name":"Gene expression and cancer classification","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/T10015","display_name":"Genomics and Phylogenetic Studies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/single-cell-foundation-models","display_name":"single-cell foundation models","score":0.7699999809265137},{"id":"https://openalex.org/keywords/single-cell-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.7310000061988831},{"id":"https://openalex.org/keywords/count-data-modeling","display_name":"count data models","score":0.3070000112056732},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.49399998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233000159263611},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.321399986743927},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.24.761590","doi":"https://doi.org/10.64898/2026.10.24.761590","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761590","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/02/2026.10.24.761590.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:10.64898/2026.10.24.761590","doi":"https://doi.org/10.64898/2026.10.24.761590","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761590","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/02/2026.10.24.761590.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225118949.pdf","grobid_xml":"https://content.openalex.org/works/W7225118949.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1970156673","https://openalex.org/W1981001162","https://openalex.org/W1986468286","https://openalex.org/W2023887100","https://openalex.org/W2033420737","https://openalex.org/W2105039688","https://openalex.org/W2110776599","https://openalex.org/W2119373999","https://openalex.org/W2154431984","https://openalex.org/W2401404581","https://openalex.org/W2592811885","https://openalex.org/W2616950861","https://openalex.org/W2901677030","https://openalex.org/W2947877009","https://openalex.org/W2951381561","https://openalex.org/W2996140569","https://openalex.org/W3000350302","https://openalex.org/W3041881306","https://openalex.org/W3138479716","https://openalex.org/W3156638396","https://openalex.org/W3170184056","https://openalex.org/W3196414652","https://openalex.org/W4205206193","https://openalex.org/W4220812447","https://openalex.org/W4225981439","https://openalex.org/W4297243391","https://openalex.org/W4378838672","https://openalex.org/W4391554792","https://openalex.org/W4392168151","https://openalex.org/W4396896612","https://openalex.org/W4399387478","https://openalex.org/W4400140845","https://openalex.org/W4403995420","https://openalex.org/W4405433019","https://openalex.org/W4406178430","https://openalex.org/W4409566559","https://openalex.org/W4411472473","https://openalex.org/W4415237911","https://openalex.org/W4415407404","https://openalex.org/W4416338927","https://openalex.org/W7130721914","https://openalex.org/W7163152452","https://openalex.org/W7167668826"],"related_works":["https://openalex.org/W4387866792","https://openalex.org/W7164818621","https://openalex.org/W7118850264","https://openalex.org/W7213291523","https://openalex.org/W7171684003","https://openalex.org/W7134995974","https://openalex.org/W4399387478","https://openalex.org/W7160217592","https://openalex.org/W7171680935","https://openalex.org/W4417334374"],"abstract_inverted_index":{"Abstract":[0],"Single-cell":[1],"foundation":[2,47,121,171],"models":[3,48,122,144,212],"currently":[4],"learn":[5],"from":[6],"gene":[7],"count":[8,58,211],"matrices,":[9],"which":[10],"are":[11],"discretized,":[12],"species-specific":[13],"summaries":[14],"that":[15,45,135,178,197],"discard":[16],"the":[17,27,32,76,140,168,192,215],"RNA":[18],"sequence,":[19],"splice-site":[20],"usage,":[21],"3\u2032":[22],"UTR":[23],"isoform":[24],"identity":[25],"and":[26,91,114,129,148,201,213],"mutational":[28],"information":[29,208],"present":[30],"in":[31,73,111],"underlying":[33],"sequencing":[34,51,175],"reads.":[35],"Here":[36],"we":[37],"introduce":[38],"single-cell":[39,77,120,170],"raw":[40,179],"data":[41,180],"pretraining,":[42],"a":[43,86,100,108,189],"framework":[44,200],"trains":[46],"directly":[49],"on":[50,102,107,145,154,174],"reads,":[52,176],"requiring":[53],"no":[54],"read":[55,78],"alignment":[56],"or":[57],"matrix,":[59],"allowing":[60],"any":[61],"trained":[62,97,173],"model":[63,72,79,138,172],"to":[64,67,210],"be":[65],"applicable":[66],"arbitrary":[68],"species.":[69],"Our":[70,132],"first":[71,169],"this":[74,199],"framework,":[75],"scRM,":[80],"pairs":[81],"two":[82],"transformer":[83],"encoders":[84],"with":[85,123],"hierarchy":[87],"of":[88,125,142,152,191],"attention":[89],"pools":[90],"contains":[92],"1.2":[93],"million":[94],"parameters.":[95],"We":[96,195],"it":[98,116,218],"as":[99],"JEPA":[101],"3,000":[103],"mouse":[104],"neuron":[105],"cells":[106],"single":[109],"H100":[110],"one":[112,151],"hour,":[113],"benchmarked":[115],"zero-shot":[117],"against":[118],"leading":[119],"orders":[124],"magnitude":[126],"more":[127],"parameters":[128],"training":[130],"cells.":[131],"results":[133],"show":[134],"our":[136,164],"lightweight":[137],"reaches":[139],"performance":[141],"existing":[143],"all":[146],"tasks,":[147],"exceeds":[149],"every":[150],"them":[153],"perturbation":[155],"detection":[156,159],"tasks":[157],"whose":[158],"requires":[160],"sequence-level":[161],"detail.":[162],"To":[163],"knowledge,":[165],"scRM":[166],"is":[167,182,225],"demonstrating":[177],"pretraining":[181,217],"not":[183],"only":[184],"feasible":[185],"but":[186],"competitive":[187],"at":[188,227],"fraction":[190],"computational":[193],"cost.":[194],"anticipate":[196],"scaling":[198],"exploring":[202],"alternative":[203],"architectures":[204],"will":[205],"unlock":[206],"biological":[207],"inaccessible":[209],"extend":[214],"dataset-specific":[216],"already":[219],"makes":[220],"possible.":[221],"The":[222],"source":[223],"code":[224],"available":[226],"https://github.com/altos-labs/scRM":[228],".":[229]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-03T00:00:00"}