{"id":"https://openalex.org/W7128529265","doi":"https://doi.org/10.64898/2026.02.06.704110","title":"cspray: Distributed Single Cell Transcriptome Analysis","display_name":"cspray: Distributed Single Cell Transcriptome Analysis","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128529265","doi":"https://doi.org/10.64898/2026.02.06.704110"},"language":"en","primary_location":{"id":"doi:10.64898/2026.02.06.704110","doi":"https://doi.org/10.64898/2026.02.06.704110","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.06.704110","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/09/2026.02.06.704110.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/2026/02/09/2026.02.06.704110.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101441629","display_name":"Peter G. Hawkins","orcid":"https://orcid.org/0000-0003-2109-9938","observed_orcids":["https://orcid.org/0000-0003-2109-9938"]},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter G. Hawkins","raw_affiliation_strings":["Databricks, 160 Spear St 15th Floor, San Francisco, CA 94105, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks, 160 Spear St 15th Floor, San Francisco, CA 94105, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049430075","display_name":"Eli M. Swanson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eli M. Swanson","raw_affiliation_strings":["Databricks, 160 Spear St 15th Floor, San Francisco, CA 94105, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks, 160 Spear St 15th Floor, San Francisco, CA 94105, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125537245","display_name":"Megan Feichtel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Megan Feichtel","raw_affiliation_strings":["Databricks, 160 Spear St 15th Floor, San Francisco, CA 94105, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks, 160 Spear St 15th Floor, San Francisco, CA 94105, USA","institution_ids":["https://openalex.org/I4401726825"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101441629"],"corresponding_institution_ids":["https://openalex.org/I4401726825"],"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/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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.75},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"distributed computing","score":0.9359999895095825},{"id":"https://openalex.org/keywords/big-data-processing","display_name":"big data processing","score":0.7080000042915344},{"id":"https://openalex.org/keywords/single-cell-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.6019999980926514},{"id":"https://openalex.org/keywords/highly-variable-genes","display_name":"highly variable genes","score":0.7450000047683716},{"id":"https://openalex.org/keywords/pca","display_name":"PCA","score":0.4339999854564667},{"id":"https://openalex.org/keywords/cell-clustering","display_name":"cell clustering","score":0.734000027179718},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9100000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66839998960495},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.4207000136375427},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3849000036716461},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C2776950831","wikidata":"https://www.wikidata.org/wiki/Q15635432","display_name":"Single-cell analysis","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C107397762","wikidata":"https://www.wikidata.org/wiki/Q2542347","display_name":"RNA-Seq","level":5,"score":0.2793999910354614},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C2992444157","wikidata":"https://www.wikidata.org/wiki/Q775079","display_name":"Single point","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.02.06.704110","doi":"https://doi.org/10.64898/2026.02.06.704110","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.06.704110","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/09/2026.02.06.704110.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:10.64898/2026.02.06.704110","doi":"https://doi.org/10.64898/2026.02.06.704110","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.06.704110","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/09/2026.02.06.704110.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/W7128529265.pdf","grobid_xml":"https://content.openalex.org/works/W7128529265.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2069089843","https://openalex.org/W2102212449","https://openalex.org/W2527672088","https://openalex.org/W2542459869","https://openalex.org/W2564176045","https://openalex.org/W2800392236","https://openalex.org/W2907514116","https://openalex.org/W3003257820","https://openalex.org/W3085477028","https://openalex.org/W3164692211","https://openalex.org/W3170771812","https://openalex.org/W4221065117","https://openalex.org/W4281761771","https://openalex.org/W4323320159","https://openalex.org/W4362737480","https://openalex.org/W4379521442","https://openalex.org/W4386563833","https://openalex.org/W4392168151","https://openalex.org/W4392904401","https://openalex.org/W4393153069","https://openalex.org/W4402902773","https://openalex.org/W4404793799","https://openalex.org/W4412723694","https://openalex.org/W4414525096","https://openalex.org/W4415692570","https://openalex.org/W4416194301","https://openalex.org/W7118299690"],"related_works":["https://openalex.org/W3105283194","https://openalex.org/W2950548777","https://openalex.org/W7135198140","https://openalex.org/W2899212028","https://openalex.org/W3003444384","https://openalex.org/W3044388039","https://openalex.org/W4412723694","https://openalex.org/W4409055145","https://openalex.org/W3089978715","https://openalex.org/W4284962632"],"abstract_inverted_index":{"The":[0],"size":[1,44],"of":[2,17,38,45,66,73],"individual":[3,21],"single":[4,56,122],"cell":[5,57,123],"samples":[6,18],"continues":[7],"to":[8,120],"grow":[9],"with":[10],"advancing":[11],"technologies,":[12],"as":[13],"do":[14],"the":[15,42,46],"number":[16],"included":[19],"in":[20,36],"experiments":[22],"and":[23,41,71,93],"across":[24],"organizations.":[25],"This":[26],"presents":[27],"challenges":[28],"for":[29],"processing":[30,59,67,100],"this":[31,51,99],"data":[32,85,124],"at":[33,101,127],"scale,":[34],"both":[35],"terms":[37],"computational":[39],"throughput":[40],"required":[43],"machines":[47],"that":[48,61,98],"must":[49],"process":[50],"data.":[52],"We":[53,95],"present":[54],"a":[55],"RNA":[58],"method":[60],"is":[62],"fully":[63],"distributed,":[64],"capable":[65],"arbitrarily":[68],"large":[69],"files,":[70,74],"numbers":[72],"without":[75],"requiring":[76],"per-file":[77],"based":[78,105],"compute":[79],"sizing.":[80],"Our":[81],"method,":[82],"cspray,":[83],"includes":[84],"ingestion,":[86],"preprocessing,":[87],"highly":[88],"variable":[89],"gene":[90],"annotation,":[91],"PCA,":[92],"clustering.":[94],"also":[96],"show":[97],"scale":[102],"permits":[103],"LLM":[104],"reference-free":[106],"cluster":[107],"annotation":[108],"on":[109],"low":[110],"resolution":[111],"clusters,":[112],"which":[113],"demonstrates":[114],"these":[115],"techniques":[116],"can":[117],"be":[118],"used":[119],"build":[121],"discovery":[125],"platforms":[126],"scale.":[128]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-02-11T00:00:00"}
