{"id":"https://openalex.org/W3157660871","doi":"https://doi.org/10.1093/bib/bbab163","title":"Prediction of tumor purity from gene expression data using machine learning","display_name":"Prediction of tumor purity from gene expression data using machine learning","publication_year":2021,"publication_date":"2021-04-08","ids":{"openalex":"https://openalex.org/W3157660871","doi":"https://doi.org/10.1093/bib/bbab163","mag":"3157660871","pmid":"https://pubmed.ncbi.nlm.nih.gov/33954576"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbab163","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab163","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053984487","display_name":"Bonil Koo","orcid":"https://orcid.org/0000-0003-4357-1850"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bonil Koo","raw_affiliation_strings":["Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, Korea","School of Systems Biomedical Science, Soongsil University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Systems Biomedical Science, Soongsil University, Seoul, Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012207088","display_name":"Je\u2010Keun Rhee","orcid":"https://orcid.org/0000-0003-4811-8895"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Je-Keun Rhee","raw_affiliation_strings":["School of Systems Biomedical Science, Soongsil University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Systems Biomedical Science, Soongsil University, Seoul, Korea","institution_ids":["https://openalex.org/I141371507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012207088"],"corresponding_institution_ids":["https://openalex.org/I141371507"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":0.4071,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.58530539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.30550000071525574,"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/T10885","display_name":"Gene expression and cancer classification","score":0.30550000071525574,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.23899999260902405,"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/T11297","display_name":"Ferroptosis and cancer prognosis","score":0.10360000282526016,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6059051752090454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5831474661827087},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5551995038986206},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5198526978492737},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.509695291519165},{"id":"https://openalex.org/keywords/tumor-cells","display_name":"Tumor cells","score":0.45729199051856995},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3374135494232178},{"id":"https://openalex.org/keywords/cancer-research","display_name":"Cancer research","score":0.2287726104259491},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21115365624427795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6059051752090454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831474661827087},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5551995038986206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5198526978492737},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.509695291519165},{"id":"https://openalex.org/C3020616263","wikidata":"https://www.wikidata.org/wiki/Q1216998","display_name":"Tumor cells","level":2,"score":0.45729199051856995},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3374135494232178},{"id":"https://openalex.org/C502942594","wikidata":"https://www.wikidata.org/wiki/Q3421914","display_name":"Cancer research","level":1,"score":0.2287726104259491},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21115365624427795},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004273","descriptor_name":"DNA, Neoplasm","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004273","descriptor_name":"DNA, Neoplasm","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004273","descriptor_name":"DNA, Neoplasm","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":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014408","descriptor_name":"Biomarkers, Tumor","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014408","descriptor_name":"Biomarkers, Tumor","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014408","descriptor_name":"Biomarkers, Tumor","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbab163","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab163","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:33954576","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33954576","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5345504198","display_name":null,"funder_award_id":"NRF-2021R1C1C1008307","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G647744068","display_name":null,"funder_award_id":"NRF-2018R1C1B6005304","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1976199086","https://openalex.org/W1988391018","https://openalex.org/W2006288875","https://openalex.org/W2069295116","https://openalex.org/W2092743770","https://openalex.org/W2110065044","https://openalex.org/W2130430382","https://openalex.org/W2147486937","https://openalex.org/W2170490448","https://openalex.org/W2185207072","https://openalex.org/W2345356016","https://openalex.org/W2502949459","https://openalex.org/W2606274694","https://openalex.org/W2770698352","https://openalex.org/W2782755171","https://openalex.org/W2793005024","https://openalex.org/W2802901592","https://openalex.org/W2808837841","https://openalex.org/W2865352686","https://openalex.org/W2886347923","https://openalex.org/W2889275748","https://openalex.org/W2926010705","https://openalex.org/W2959772520","https://openalex.org/W2967361057","https://openalex.org/W2982402173","https://openalex.org/W2997038659","https://openalex.org/W2998649814","https://openalex.org/W3006517346","https://openalex.org/W3013961713","https://openalex.org/W3028304854","https://openalex.org/W3045343442","https://openalex.org/W3083461000","https://openalex.org/W3119858057","https://openalex.org/W6682207086"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W2161444195","https://openalex.org/W148178222","https://openalex.org/W2985540061","https://openalex.org/W2589019771","https://openalex.org/W2104657898","https://openalex.org/W2185012154","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W4252521128"],"abstract_inverted_index":{"MOTIVATION:":[0],"Bulk":[1],"tumor":[2,45,57,77,88,95,123],"samples":[3],"used":[4],"for":[5,73,145],"high-throughput":[6,60],"molecular":[7,61],"profiling":[8],"are":[9,148],"often":[10],"an":[11],"admixture":[12],"of":[13,37,44,76,115],"cancer":[14],"cells":[15],"and":[16,22,32,40,98,117],"non-cancerous":[17],"cells,":[18],"which":[19],"include":[20],"immune":[21,137],"stromal":[23],"cells.":[24],"The":[25,140],"mixed":[26],"composition":[27],"can":[28],"confound":[29],"the":[30,34,38,74,91,94,136],"analysis":[31],"affect":[33],"biological":[35],"interpretation":[36],"results,":[39],"thus,":[41],"accurate":[42],"prediction":[43],"purity":[46,58,96,124],"is":[47],"critical.":[48],"Although":[49],"several":[50],"methods":[51,72],"have":[52],"been":[53,65],"proposed":[54],"to":[55,86],"predict":[56,122],"using":[59],"data,":[62],"there":[63],"has":[64],"no":[66],"comprehensive":[67],"study":[68,147],"on":[69],"machine":[70,83,141],"learning-based":[71],"estimation":[75],"purity.":[78,89],"RESULTS:":[79],"We":[80],"applied":[81],"various":[82],"learning":[84,142],"models":[85,92,143],"estimate":[87],"Overall,":[90],"predicted":[93],"accurately":[97],"showed":[99],"a":[100,112],"high":[101],"correlation":[102],"with":[103],"well-established":[104],"gold":[105],"standard":[106],"methods.":[107],"In":[108],"addition,":[109],"we":[110,127],"identified":[111],"small":[113],"group":[114],"genes":[116,131],"demonstrated":[118],"that":[119,129],"they":[120],"could":[121],"well.":[125],"Finally,":[126],"confirmed":[128],"these":[130],"were":[132],"mainly":[133],"involved":[134],"in":[135],"system.":[138],"AVAILABILITY:":[139],"constructed":[144],"this":[146],"available":[149],"at":[150],"https://github.com/BonilKoo/ML_purity.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
