{"id":"https://openalex.org/W7215123979","doi":"https://doi.org/10.48550/arxiv.2609.38908","title":"CellMSA: Context Modeling for Single-Cell Representation Learning","display_name":"CellMSA: Context Modeling for Single-Cell Representation Learning","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215123979","doi":"https://doi.org/10.48550/arxiv.2609.38908"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38908","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38908","pdf_url":"https://arxiv.org/pdf/2609.38908","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.38908","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092120655","display_name":"Suyuan Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Suyuan","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University","Institute for AI Industry Research (AIR) , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR) , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153718158","display_name":"Minghao Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Minghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154026928","display_name":"Yizhen Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Yizhen","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University","Institute for AI Industry Research (AIR) , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR) , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343","observed_orcids":["https://orcid.org/0000-0002-1134-2343"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nie, Zaiqing","raw_affiliation_strings":["Institute for AI Industry Research (AIR) , Tsinghua University","PharMolix Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR) , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"PharMolix Inc","institution_ids":[]}]}],"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"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"}},{"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/T10621","display_name":"Gene Regulatory Network Analysis","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/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.9459999799728394},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.875},{"id":"https://openalex.org/keywords/single-cell-foundation-models","display_name":"single-cell foundation models","score":0.8019999861717224},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.6899999976158142},{"id":"https://openalex.org/keywords/context-modeling","display_name":"context modeling","score":0.8270000219345093},{"id":"https://openalex.org/keywords/batch-effects","display_name":"batch effects","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.738099992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106999754905701},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6028000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982000231742859},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5981000065803528},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3427000045776367},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38908","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38908","pdf_url":"https://arxiv.org/pdf/2609.38908","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.38908","doi":"https://doi.org/10.48550/arxiv.2609.38908","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38908","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:2609.38908","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38908","pdf_url":"https://arxiv.org/pdf/2609.38908","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215123979.pdf","grobid_xml":"https://content.openalex.org/works/W7215123979.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2049017883","https://openalex.org/W2786672974","https://openalex.org/W2964121744","https://openalex.org/W4225598893","https://openalex.org/W4297808394","https://openalex.org/W4308834893","https://openalex.org/W4396912918","https://openalex.org/W4414876904"],"related_works":["https://openalex.org/W7208735616","https://openalex.org/W7220945821","https://openalex.org/W6999617892","https://openalex.org/W7196966009","https://openalex.org/W7196966245","https://openalex.org/W7127326875","https://openalex.org/W4407100080","https://openalex.org/W4414130562","https://openalex.org/W4415227048","https://openalex.org/W7172429527"],"abstract_inverted_index":{"Single-cell":[0],"transcriptomics":[1],"enables":[2],"profiling":[3],"of":[4,100,176],"cellular":[5],"states":[6],"at":[7,202],"unprecedented":[8],"resolution,":[9],"but":[10],"its":[11],"high":[12],"dimensionality,":[13],"sparsity,":[14],"and":[15,52,75,137,144],"technical":[16],"batch":[17,41],"effects":[18],"pose":[19],"significant":[20],"challenges":[21],"for":[22,42,92,163],"representation":[23,114,154,165],"learning.":[24,166],"Existing":[25],"single-cell":[26,63,113,174],"foundation":[27],"models":[28,64,79],"typically":[29],"encode":[30],"each":[31,127],"cell":[32,53,87,140,180],"independently":[33],"or":[34],"only":[35],"model":[36,56],"cells":[37,133],"from":[38,67,134],"the":[39,46,98,203],"same":[40],"denoising,":[43],"thereby":[44],"underutilizing":[45],"rich":[47],"relational":[48],"information":[49],"across":[50,77,196],"batches":[51,136],"types":[54,141],"to":[55],"gene":[57],"expression":[58],"patterns.":[59],"We":[60,167],"argue":[61],"that":[62,117,189],"can":[65,80],"benefit":[66],"more":[68],"informative":[69],"cell-context":[70],"modeling.":[71,125],"By":[72],"comparing":[73],"consistency":[74],"variation":[76],"cells,":[78],"capture":[81],"fine-grained":[82,164],"gene-gene":[83],"dependencies":[84],"associated":[85],"with":[86],"states,":[88],"which":[89],"are":[90],"essential":[91],"learning":[93,115],"high-quality":[94],"representations.":[95],"Inspired":[96],"by":[97],"use":[99],"multiple":[101,197],"sequence":[102],"alignment":[103],"(MSA)":[104],"context":[105],"in":[106],"protein":[107],"modeling,":[108],"we":[109],"propose":[110],"CellMSA,":[111],"a":[112,149,159,171],"framework":[116,191],"introduces":[118],"an":[119],"MSA-inspired":[120],"inductive":[121],"bias":[122],"into":[123,148,158],"transcriptomic":[124],"For":[126],"target":[128],"cell,":[129],"CellMSA":[130,169],"retrieves":[131],"relevant":[132],"different":[135],"biologically":[138],"related":[139],"as":[142],"context,":[143],"summarizes":[145],"cross-cell":[146],"patterns":[147],"context-dependent":[150],"gene-pair":[151],"representation.":[152],"This":[153],"is":[155,200],"then":[156],"injected":[157],"pair-aware":[160],"target-cell":[161],"encoder":[162],"pretrain":[168],"on":[170],"large-scale":[172],"human":[173],"corpus":[175],"approximately":[177],"109":[178],"million":[179,184],"observations,":[181],"including":[182],"65.6":[183],"primary":[185],"observations.":[186],"Experiments":[187],"show":[188],"our":[190],"consistently":[192],"outperforms":[193],"existing":[194],"methods":[195],"benchmarks.":[198],"Code":[199],"available":[201],"following":[204],"repository:":[205],"https://github.com/PharMolix/CellMSA.":[206]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-02T00:00:00"}