{"id":"https://openalex.org/W2887766567","doi":"https://doi.org/10.1186/s12864-018-4922-4","title":"Single cell RNA-seq data clustering using TF-IDF based methods","display_name":"Single cell RNA-seq data clustering using TF-IDF based methods","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2887766567","doi":"https://doi.org/10.1186/s12864-018-4922-4","mag":"2887766567","pmid":"https://pubmed.ncbi.nlm.nih.gov/30367575","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6101073"},"language":"en","primary_location":{"id":"doi:10.1186/s12864-018-4922-4","doi":"https://doi.org/10.1186/s12864-018-4922-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-018-4922-4","pdf_url":"https://bmcgenomics.biomedcentral.com/track/pdf/10.1186/s12864-018-4922-4","source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Genomics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcgenomics.biomedcentral.com/track/pdf/10.1186/s12864-018-4922-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018308989","display_name":"Marmar R. Moussa","orcid":"https://orcid.org/0000-0003-0574-6656","observed_orcids":["https://orcid.org/0000-0003-0574-6656"]},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marmar Moussa","raw_affiliation_strings":["University of Connecticut, Storrs, 06269, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, 06269, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014788373","display_name":"Ion M\u0103ndoiu","orcid":"https://orcid.org/0000-0002-4818-0237","observed_orcids":["https://orcid.org/0000-0002-4818-0237"]},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ion I. M\u0103ndoiu","raw_affiliation_strings":["University of Connecticut, Storrs, 06269, CT, USA. ion.mandoiu@uconn.edu","University of Connecticut, Storrs, 06269, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, 06269, CT, USA. ion.mandoiu@uconn.edu","institution_ids":["https://openalex.org/I140172145"]},{"raw_affiliation_string":"University of Connecticut, Storrs, 06269, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014788373"],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":1.8337,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.8627695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"19","issue":"S6","first_page":"569","last_page":"569"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/single-cell-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.8389999866485596},{"id":"https://openalex.org/keywords/cell-clustering","display_name":"cell clustering","score":0.703000009059906},{"id":"https://openalex.org/keywords/tf-idf","display_name":"TF-IDF","score":0.9139999747276306},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.859000027179718},{"id":"https://openalex.org/keywords/cell-heterogeneity","display_name":"cellular heterogeneity","score":0.7279999852180481},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.722000002861023}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7952006459236145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5902857184410095},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.543491780757904},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49032261967658997},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45170724391937256},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.4512471556663513},{"id":"https://openalex.org/C144817290","wikidata":"https://www.wikidata.org/wiki/Q2976575","display_name":"Biclustering","level":5,"score":0.4309009313583374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.339447557926178},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3261201083660126},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25592002272605896},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.1995682418346405},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.13036441802978516},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12864-018-4922-4","doi":"https://doi.org/10.1186/s12864-018-4922-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-018-4922-4","pdf_url":"https://bmcgenomics.biomedcentral.com/track/pdf/10.1186/s12864-018-4922-4","source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Genomics","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:5052127","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6101073","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6101073","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6101073","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Genomics","raw_type":"Text"},{"id":"pmid:30367575","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30367575","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,"listed_in":[],"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":"BMC genomics","raw_type":"Evaluation Study"},{"id":"pmh:oai:doaj.org/article:b2d2322f7e164efc88bd7ef458c1fa23","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/b2d2322f7e164efc88bd7ef458c1fa23","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Genomics, Vol 19, Iss S6, Pp 31-45 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12864-018-4922-4","doi":"https://doi.org/10.1186/s12864-018-4922-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-018-4922-4","pdf_url":"https://bmcgenomics.biomedcentral.com/track/pdf/10.1186/s12864-018-4922-4","source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Genomics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3241938273","display_name":"ABI Innovation: Collaborative Research: Computational framework for inference of metabolic pathway activity from RNA-seq data","funder_award_id":"1564936","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4981134647","display_name":"Homeostatic regulation of NG2 cell dynamics","funder_award_id":"R01NS073425","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"},{"id":"https://openalex.org/G9000919492","display_name":"Inhibitory Cell Types and Circuits in the Lateral Hypothalamus","funder_award_id":"R01MH112739","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"},{"id":"https://openalex.org/F4320337359","display_name":"National Institute of Neurological Disorders and Stroke","ror":"https://ror.org/01s5ya894"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2887766567.pdf","grobid_xml":"https://content.openalex.org/works/W2887766567.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W74439177","https://openalex.org/W101836494","https://openalex.org/W229097380","https://openalex.org/W1736726159","https://openalex.org/W1977556410","https://openalex.org/W1980425490","https://openalex.org/W1981276685","https://openalex.org/W2010653277","https://openalex.org/W2012833704","https://openalex.org/W2016381774","https://openalex.org/W2019336343","https://openalex.org/W2047940964","https://openalex.org/W2069089843","https://openalex.org/W2126907894","https://openalex.org/W2131681506","https://openalex.org/W2141012957","https://openalex.org/W2150376021","https://openalex.org/W2187089797","https://openalex.org/W2286142055","https://openalex.org/W2342293862","https://openalex.org/W2426604946","https://openalex.org/W2511262512","https://openalex.org/W2523369352","https://openalex.org/W2551194178","https://openalex.org/W2559655401","https://openalex.org/W2949359662","https://openalex.org/W2949388608","https://openalex.org/W2950150251","https://openalex.org/W2951506174","https://openalex.org/W3127933230","https://openalex.org/W4241278170","https://openalex.org/W4245370006","https://openalex.org/W4300601563","https://openalex.org/W6600137863"],"related_works":["https://openalex.org/W2945586525","https://openalex.org/W3008563687","https://openalex.org/W3148355078","https://openalex.org/W4387300154","https://openalex.org/W4388525430","https://openalex.org/W4311113696","https://openalex.org/W4311671653","https://openalex.org/W3095414514","https://openalex.org/W2955621471","https://openalex.org/W4225149814"],"abstract_inverted_index":{"BACKGROUND:":[0],"Single":[1],"cell":[2,14,22],"transcriptomics":[3],"is":[4],"critical":[5],"for":[6,57],"understanding":[7],"cellular":[8],"heterogeneity":[9],"and":[10,40,43],"identification":[11],"of":[12,38,47,49,80],"novel":[13,28,54],"types.":[15],"Leveraging":[16],"the":[17,63,78],"recent":[18],"advances":[19],"in":[20,77],"single":[21],"RNA":[23],"sequencing":[24],"(scRNA-Seq)":[25],"technology":[26],"requires":[27],"unsupervised":[29],"clustering":[30,58,96],"algorithms":[31],"that":[32,72,88],"are":[33],"robust":[34],"to":[35,45],"high":[36],"levels":[37],"technical":[39],"biological":[41],"noise":[42],"scale":[44],"datasets":[46],"millions":[48],"cells.":[50],"RESULTS:":[51],"We":[52],"present":[53],"computational":[55],"approaches":[56],"scRNA-seq":[59],"data":[60],"based":[61],"on":[62],"Term":[64],"Frequency":[65,69],"-":[66],"Inverse":[67],"Document":[68],"(TF-IDF)":[70],"transformation":[71],"has":[73],"been":[74],"successfully":[75],"used":[76,94],"field":[79],"text":[81],"analysis.":[82],"CONCLUSIONS:":[83],"Empirical":[84],"experimental":[85],"results":[86],"show":[87],"TF-IDF":[89],"methods":[90],"consistently":[91],"outperform":[92],"commonly":[93],"scRNA-Seq":[95],"approaches.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-08-22T00:00:00"}
