{"id":"https://openalex.org/W4283798763","doi":"https://doi.org/10.1038/s43588-022-00263-8","title":"Minimal gene set discovery in single-cell mRNA-seq datasets with ActiveSVM","display_name":"Minimal gene set discovery in single-cell mRNA-seq datasets with ActiveSVM","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4283798763","doi":"https://doi.org/10.1038/s43588-022-00263-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/38177588"},"language":"en","primary_location":{"id":"doi:10.1038/s43588-022-00263-8","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s43588-022-00263-8","pdf_url":"https://www.nature.com/articles/s43588-022-00263-8.pdf","source":{"id":"https://openalex.org/S4210228084","display_name":"Nature Computational Science","issn_l":"2662-8457","issn":["2662-8457"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Computational Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s43588-022-00263-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102743593","display_name":"Xiaoqiao Chen","orcid":"https://orcid.org/0000-0003-4685-3466"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoqiao Chen","raw_affiliation_strings":["Department of Computing and Mathematical Sciences, California Institute of Technology, Pasadena, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Mathematical Sciences, California Institute of Technology, Pasadena, California, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341522","display_name":"Sisi Chen","orcid":"https://orcid.org/0000-0001-9448-9713"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sisi Chen","raw_affiliation_strings":["Beckman Institute Single-cell Profiling and Engineering Center, Pasadena, California, USA","Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute Single-cell Profiling and Engineering Center, Pasadena, California, USA","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, California, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014506392","display_name":"Matt Thomson","orcid":"https://orcid.org/0000-0003-1021-1234"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matt Thomson","raw_affiliation_strings":["Beckman Institute Single-cell Profiling and Engineering Center, Pasadena, California, USA. mthomson@caltech.edu","Department of Computing and Mathematical Sciences, California Institute of Technology, Pasadena, California, USA. mthomson@caltech.edu","Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, California, USA. mthomson@caltech.edu","Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-1021-1234","affiliations":[{"raw_affiliation_string":"Beckman Institute Single-cell Profiling and Engineering Center, Pasadena, California, USA. mthomson@caltech.edu","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Department of Computing and Mathematical Sciences, California Institute of Technology, Pasadena, California, USA. mthomson@caltech.edu","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, California, USA. mthomson@caltech.edu","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, California, USA","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014506392"],"corresponding_institution_ids":["https://openalex.org/I122411786"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":{"value":9750,"currency":"EUR","value_usd":11690},"fwci":1.9306,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.86555091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"2","issue":"6","first_page":"387","last_page":"398"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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":0.9833999872207642,"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/computational-biology","display_name":"Computational biology","score":0.6129447221755981},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5901643633842468},{"id":"https://openalex.org/keywords/gene-expression-profiling","display_name":"Gene expression profiling","score":0.48990243673324585},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.476775199174881},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4446825087070465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3665304183959961},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3498261570930481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3040604591369629},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.2955884337425232}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6129447221755981},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5901643633842468},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.48990243673324585},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.476775199174881},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4446825087070465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3665304183959961},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3498261570930481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3040604591369629},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.2955884337425232}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1038/s43588-022-00263-8","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s43588-022-00263-8","pdf_url":"https://www.nature.com/articles/s43588-022-00263-8.pdf","source":{"id":"https://openalex.org/S4210228084","display_name":"Nature Computational Science","issn_l":"2662-8457","issn":["2662-8457"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Computational Science","raw_type":"journal-article"},{"id":"pmid:38177588","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38177588","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature computational science","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10766518","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10766518","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10766518/pdf/43588_2022_Article_263.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nat Comput Sci","raw_type":"Text"},{"id":"pmh:oai:authors.library.caltech.edu:115426","is_oa":true,"landing_page_url":"https://authors.library.caltech.edu/115426/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1038/s43588-022-00263-8","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s43588-022-00263-8","pdf_url":"https://www.nature.com/articles/s43588-022-00263-8.pdf","source":{"id":"https://openalex.org/S4210228084","display_name":"Nature Computational Science","issn_l":"2662-8457","issn":["2662-8457"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Computational Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2216906004","display_name":null,"funder_award_id":"R01HD100039","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2696502328","display_name":null,"funder_award_id":"R21 CA284221","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G5183578178","display_name":null,"funder_award_id":"R01 HD100039","funder_id":"https://openalex.org/F4320337611","funder_display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development"},{"id":"https://openalex.org/G6574198690","display_name":null,"funder_award_id":"R01 GM150125","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G771627689","display_name":null,"funder_award_id":"R01HD100039","funder_id":"https://openalex.org/F4320306085","funder_display_name":"U.S. Department of Health and Human Services"}],"funders":[{"id":"https://openalex.org/F4320306085","display_name":"U.S. Department of Health and Human Services","ror":"https://ror.org/033jnv181"},{"id":"https://openalex.org/F4320314885","display_name":"Heritage Medical Research Institute","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337611","display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","ror":"https://ror.org/04byxyr05"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283798763.pdf","grobid_xml":"https://content.openalex.org/works/W4283798763.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1527620915","https://openalex.org/W1964940342","https://openalex.org/W1973267259","https://openalex.org/W1981552604","https://openalex.org/W2026498605","https://openalex.org/W2034365297","https://openalex.org/W2076003134","https://openalex.org/W2095162291","https://openalex.org/W2098454110","https://openalex.org/W2102212449","https://openalex.org/W2106578604","https://openalex.org/W2118561568","https://openalex.org/W2125283600","https://openalex.org/W2131681506","https://openalex.org/W2135248331","https://openalex.org/W2146180544","https://openalex.org/W2147423551","https://openalex.org/W2151570219","https://openalex.org/W2151987348","https://openalex.org/W2160470066","https://openalex.org/W2166643977","https://openalex.org/W2335295795","https://openalex.org/W2336509969","https://openalex.org/W2339229309","https://openalex.org/W2342807339","https://openalex.org/W2462053388","https://openalex.org/W2514159238","https://openalex.org/W2546945975","https://openalex.org/W2561754210","https://openalex.org/W2607806728","https://openalex.org/W2768455369","https://openalex.org/W2781615683","https://openalex.org/W2800392236","https://openalex.org/W2891114977","https://openalex.org/W2892143295","https://openalex.org/W2894687190","https://openalex.org/W2896353945","https://openalex.org/W2900487160","https://openalex.org/W2923300855","https://openalex.org/W2947422809","https://openalex.org/W2951506174","https://openalex.org/W2951799803","https://openalex.org/W2952887658","https://openalex.org/W2973989845","https://openalex.org/W2982231537","https://openalex.org/W2982357115","https://openalex.org/W2998891415","https://openalex.org/W3013900499","https://openalex.org/W3032573523","https://openalex.org/W3082077009","https://openalex.org/W3092316288","https://openalex.org/W3096333621","https://openalex.org/W3099768174","https://openalex.org/W3104887532","https://openalex.org/W3105524694","https://openalex.org/W3110592098","https://openalex.org/W3113630028","https://openalex.org/W3194298692","https://openalex.org/W6969004615"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2131250617","https://openalex.org/W4233034052","https://openalex.org/W2371030422","https://openalex.org/W2982642565","https://openalex.org/W2065530813","https://openalex.org/W1509071637","https://openalex.org/W4366601060","https://openalex.org/W2113421559","https://openalex.org/W2043521617"],"abstract_inverted_index":{"Sequencing":[0],"costs":[1,20],"currently":[2],"prohibit":[3],"the":[4,53,129],"application":[5,135],"of":[6,34,55,70,118,131,136],"single-cell":[7,16,64,82,137],"mRNA-seq":[8,138],"to":[9,139],"many":[10],"biological":[11,28],"and":[12,60,113,144],"clinical":[13,140],"analyses.":[14],"Targeted":[15],"mRNA-sequencing":[17],"reduces":[18],"sequencing":[19],"by":[21,84],"profiling":[22],"reduced":[23],"gene":[24,49,79,100,123],"sets":[25,50,80,101,124],"that":[26,43,51,95,102],"capture":[27],"information":[29],"with":[30],"a":[31,67],"minimal":[32,45,78],"number":[33,69,130],"genes.":[35,71],"Here":[36],"we":[37],"introduce":[38],"an":[39,86],"active":[40,73,87],"learning":[41],"method":[42],"identifies":[44,99],"but":[46,120],"highly":[47,121],"informative":[48,122],"enable":[52,103,126],"identification":[54],"cell":[56,111],"types,":[57],"physiological":[58],"states":[59],"genetic":[61,145],"perturbations":[62],"in":[63,128],"data":[65,83],"using":[66],"small":[68,119],"Our":[72],"feature":[74,97],"selection":[75,98],"procedure":[76],"generates":[77],"from":[81],"employing":[85],"support":[88],"vector":[89],"machine":[90],"(ActiveSVM)":[91],"classifier.":[92],"We":[93],"demonstrate":[94],"ActiveSVM":[96],"~90%":[104],"cell-type":[105],"classification":[106],"accuracy":[107],"across,":[108],"for":[109,134],"example,":[110],"atlas":[112],"disease-characterization":[114],"datasets.":[115],"The":[116],"discovery":[117,143],"should":[125],"reductions":[127],"measurements":[132],"necessary":[133],"tests,":[141],"therapeutic":[142],"screens.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}