{"id":"https://openalex.org/W3037558964","doi":"https://doi.org/10.1093/bib/bbaa097","title":"SMNN: batch effect correction for single-cell RNA-seq data via supervised mutual nearest neighbor detection","display_name":"SMNN: batch effect correction for single-cell RNA-seq data via supervised mutual nearest neighbor detection","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3037558964","doi":"https://doi.org/10.1093/bib/bbaa097","mag":"3037558964","pmid":"https://pubmed.ncbi.nlm.nih.gov/32591778"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbaa097","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbaa097","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8324985","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008604223","display_name":"Yuchen Yang","orcid":"https://orcid.org/0000-0001-5977-1617"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchen Yang","raw_affiliation_strings":["Department of Genetics at the University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics at the University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438758","display_name":"Gang Li","orcid":"https://orcid.org/0000-0003-0759-9063"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023204979","display_name":"Huijun Qian","orcid":"https://orcid.org/0000-0002-8171-1378"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huijun Qian","raw_affiliation_strings":["Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill"],"raw_orcid":"https://orcid.org/0000-0002-8171-1378","affiliations":[{"raw_affiliation_string":"Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004390437","display_name":"Kirk C. Wilhelmsen","orcid":"https://orcid.org/0000-0002-4432-8302"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kirk C Wilhelmsen","raw_affiliation_strings":["Department of Genetics at the University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics at the University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103220709","display_name":"Yin Shen","orcid":"https://orcid.org/0000-0001-9901-5613"},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]},{"id":"https://openalex.org/I4210105714","display_name":"Center for Human Genetics","ror":"https://ror.org/01gcrbc43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210105714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin Shen","raw_affiliation_strings":["Institute for Human Genetics and Department of Neurology at the University of California San Francisco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human Genetics and Department of Neurology at the University of California San Francisco","institution_ids":["https://openalex.org/I4210105714","https://openalex.org/I180670191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369226","display_name":"Yun Li","orcid":"https://orcid.org/0000-0002-9275-4189"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun Li","raw_affiliation_strings":["Departments of Genetics, Biostatistics and Computer Science at the University of North Carolina at Chapel Hill"],"raw_orcid":"https://orcid.org/0000-0002-9275-4189","affiliations":[{"raw_affiliation_string":"Departments of Genetics, Biostatistics and Computer Science at the University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100369226"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":1.5006,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.82306897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"3","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/T10773","display_name":"Extracellular vesicles in disease","score":0.9771000146865845,"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":0.9266999959945679,"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/computer-science","display_name":"Computer science","score":0.7039903998374939},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5816205739974976},{"id":"https://openalex.org/keywords/rna-seq","display_name":"RNA-Seq","score":0.5317384600639343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4861421287059784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4781695008277893},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4768748879432678},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39502570033073425},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.232812762260437},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.16664746403694153},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1134042739868164},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.08917427062988281},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06999483704566956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039903998374939},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5816205739974976},{"id":"https://openalex.org/C107397762","wikidata":"https://www.wikidata.org/wiki/Q2542347","display_name":"RNA-Seq","level":5,"score":0.5317384600639343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4861421287059784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4781695008277893},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4768748879432678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39502570033073425},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.232812762260437},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.16664746403694153},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1134042739868164},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.08917427062988281},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06999483704566956}],"mesh":[{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbaa097","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbaa097","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:32591778","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32591778","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8324985","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8324985","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8324985","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8324985","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6020865454","display_name":null,"funder_award_id":"R01 GM105785","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7763635395","display_name":null,"funder_award_id":"R01 HL129132","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1495503443","https://openalex.org/W1546952499","https://openalex.org/W1875842236","https://openalex.org/W1988391018","https://openalex.org/W2035618305","https://openalex.org/W2107665951","https://openalex.org/W2122982115","https://openalex.org/W2170398220","https://openalex.org/W2177432730","https://openalex.org/W2465917013","https://openalex.org/W2472063172","https://openalex.org/W2526262591","https://openalex.org/W2766959028","https://openalex.org/W2794480084","https://openalex.org/W2794521141","https://openalex.org/W2798909945","https://openalex.org/W2884197618","https://openalex.org/W2885376126","https://openalex.org/W2902652978","https://openalex.org/W2907783748","https://openalex.org/W2912390237","https://openalex.org/W2948469692","https://openalex.org/W2949177718","https://openalex.org/W2949236943","https://openalex.org/W2949329924","https://openalex.org/W2950014930","https://openalex.org/W2951506174","https://openalex.org/W2997470228","https://openalex.org/W4233637541","https://openalex.org/W4235169531"],"related_works":["https://openalex.org/W2466816617","https://openalex.org/W1970834875","https://openalex.org/W842936808","https://openalex.org/W3174028392","https://openalex.org/W2000517284","https://openalex.org/W2365318811","https://openalex.org/W2136503713","https://openalex.org/W2062957446","https://openalex.org/W2147397890","https://openalex.org/W2166213322"],"abstract_inverted_index":{"Batch":[0],"effect":[1,35,59],"correction":[2,60,121],"has":[3],"been":[4],"recognized":[5],"to":[6,47,92,131],"be":[7],"indispensable":[8],"when":[9],"integrating":[10],"single-cell":[11,22],"RNA":[12],"sequencing":[13],"(scRNA-seq)":[14],"data":[15,63],"from":[16],"multiple":[17],"batches.":[18],"State-of-the-art":[19],"methods":[20],"ignore":[21],"cluster":[23],"label":[24],"information,":[25],"but":[26],"such":[27],"information":[28],"can":[29],"improve":[30],"the":[31,85],"effectiveness":[32],"of":[33,61],"batch":[34,48,58],"correction,":[36],"particularly":[37],"under":[38],"realistic":[39],"scenarios":[40],"where":[41],"biological":[42],"differences":[43],"are":[44],"not":[45],"orthogonal":[46],"effects.":[49],"To":[50],"address":[51],"this":[52],"issue,":[53],"we":[54],"propose":[55],"SMNN":[56,80,104,120],"for":[57],"scRNA-seq":[62],"via":[64],"supervised":[65],"mutual":[66],"nearest":[67],"neighbor":[68],"detection.":[69],"Our":[70],"extensive":[71],"evaluations":[72],"in":[73],"simulated":[74],"and":[75,101],"real":[76],"datasets":[77],"show":[78],"that":[79],"provides":[81],"improved":[82],"merging":[83],"within":[84],"corresponding":[86],"cell":[87,117],"types":[88,118],"across":[89,95],"batches,":[90],"leading":[91],"reduced":[93],"differentiation":[94],"batches":[96],"over":[97],"MNN,":[98],"Seurat":[99],"v3":[100],"LIGER.":[102],"Furthermore,":[103],"retains":[105],"more":[106,124],"cell-type-specific":[107],"features,":[108],"partially":[109],"manifested":[110],"by":[111,129],"differentially":[112],"expressed":[113],"genes":[114],"identified":[115],"between":[116],"after":[119],"being":[122],"biologically":[123],"relevant,":[125],"with":[126],"precision":[127],"improving":[128],"up":[130],"841.0%.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
