{"id":"https://openalex.org/W2916041164","doi":"https://doi.org/10.1089/cmb.2018.0238","title":"CuMiDa: An Extensively Curated Microarray Database for Benchmarking and Testing of Machine Learning Approaches in Cancer Research","display_name":"CuMiDa: An Extensively Curated Microarray Database for Benchmarking and Testing of Machine Learning Approaches in Cancer Research","publication_year":2019,"publication_date":"2019-02-21","ids":{"openalex":"https://openalex.org/W2916041164","doi":"https://doi.org/10.1089/cmb.2018.0238","mag":"2916041164","pmid":"https://pubmed.ncbi.nlm.nih.gov/30789283"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2018.0238","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2018.0238","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5081162394","display_name":"Bruno C\u00e9sar Feltes","orcid":"https://orcid.org/0000-0002-2825-8295"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno C\u00e9sar Feltes","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066035131","display_name":"Eduardo Bassani Chandelier","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Eduardo Bassani Chandelier","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012548285","display_name":"Bruno Iochins Grisci","orcid":"https://orcid.org/0000-0003-4083-5881"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Iochins Grisci","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026741733","display_name":"M\u00e1rcio Dorn","orcid":"https://orcid.org/0000-0001-8534-3480"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"M\u00e1rcio Dorn","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5026741733"],"corresponding_institution_ids":["https://openalex.org/I130442723"],"apc_list":null,"apc_paid":null,"fwci":2.8499,"has_fulltext":false,"cited_by_count":128,"citation_normalized_percentile":{"value":0.91879717,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"26","issue":"4","first_page":"376","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","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/T10885","display_name":"Gene expression and cancer classification","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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9965999722480774,"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":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/microarray-databases","display_name":"Microarray databases","score":0.7956101894378662},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7952723503112793},{"id":"https://openalex.org/keywords/microarray-analysis-techniques","display_name":"Microarray analysis techniques","score":0.6406937837600708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6402289271354675},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6035836935043335},{"id":"https://openalex.org/keywords/database-normalization","display_name":"Database normalization","score":0.5590013861656189},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5280070304870605},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37472769618034363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2390928566455841},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.164383202791214},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12922996282577515},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.10000702738761902},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09184890985488892}],"concepts":[{"id":"https://openalex.org/C548314002","wikidata":"https://www.wikidata.org/wiki/Q6839218","display_name":"Microarray databases","level":5,"score":0.7956101894378662},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7952723503112793},{"id":"https://openalex.org/C8415881","wikidata":"https://www.wikidata.org/wiki/Q6839217","display_name":"Microarray analysis techniques","level":4,"score":0.6406937837600708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402289271354675},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6035836935043335},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.5590013861656189},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5280070304870605},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37472769618034363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2390928566455841},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.164383202791214},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12922996282577515},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.10000702738761902},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09184890985488892},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","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":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1089/cmb.2018.0238","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2018.0238","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:30789283","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30789283","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W597424329","https://openalex.org/W1520812622","https://openalex.org/W1570448133","https://openalex.org/W1629202041","https://openalex.org/W1964042173","https://openalex.org/W1967180093","https://openalex.org/W1970156673","https://openalex.org/W1973094248","https://openalex.org/W1977859620","https://openalex.org/W1987389010","https://openalex.org/W2007176121","https://openalex.org/W2040407051","https://openalex.org/W2046904226","https://openalex.org/W2063907483","https://openalex.org/W2070999857","https://openalex.org/W2087684630","https://openalex.org/W2088337738","https://openalex.org/W2100239923","https://openalex.org/W2101234009","https://openalex.org/W2103964110","https://openalex.org/W2105642898","https://openalex.org/W2106608030","https://openalex.org/W2109363337","https://openalex.org/W2116634113","https://openalex.org/W2117195823","https://openalex.org/W2131822674","https://openalex.org/W2140736261","https://openalex.org/W2144692687","https://openalex.org/W2146512944","https://openalex.org/W2147246240","https://openalex.org/W2159096710","https://openalex.org/W2159400887","https://openalex.org/W2344681634","https://openalex.org/W2559479590","https://openalex.org/W2767913312","https://openalex.org/W2795102902","https://openalex.org/W2799587242","https://openalex.org/W2801425369","https://openalex.org/W2902415855"],"related_works":["https://openalex.org/W2943416042","https://openalex.org/W4241705247","https://openalex.org/W2145362441","https://openalex.org/W2101622345","https://openalex.org/W1544923801","https://openalex.org/W3152114242","https://openalex.org/W2582603276","https://openalex.org/W2147353173","https://openalex.org/W3140461004","https://openalex.org/W2110940238"],"abstract_inverted_index":{"The":[0],"employment":[1],"of":[2,54,74,177],"machine":[3],"learning":[4],"(ML)":[5],"approaches":[6,152,179],"to":[7,109,120,141,153,181],"extract":[8],"gene":[9],"expression":[10],"information":[11],"from":[12,87,93],"microarray":[13,77,91,164],"studies":[14],"has":[15],"increased":[16],"in":[17,30,33,61],"the":[18,66,94,159],"past":[19],"years,":[20],"specially":[21],"on":[22,44],"cancer-related":[23],"works.":[24],"However,":[25],"despite":[26],"this":[27,62],"continuous":[28],"interest":[29],"applying":[31],"ML":[32,151,178],"cancer":[34,58,182],"biomedical":[35],"research,":[36],"there":[37],"are":[38],"no":[39],"curated":[40],"repositories":[41],"focused":[42],"only":[43],"providing":[45],"quality":[46,114],"data":[47,78,104,125,165],"sets":[48,79,105,126],"exclusively":[49],"for":[50,57,80,158,163,173],"benchmarking":[51,174],"and":[52,116,134,145,175],"testing":[53,176],"such":[55],"techniques":[56,161],"research.":[59,183],"Thus,":[60],"work,":[63],"we":[64],"present":[65],"Curated":[67],"Microarray":[68],"Database":[69],"(CuMiDa),":[70],"a":[71,99,155,169],"database":[72,170],"composed":[73],"78":[75],"handpicked":[76],"Homo":[81],"sapiens":[82],"that":[83],"were":[84,106,117,127,146],"carefully":[85],"examined":[86],"more":[88],"than":[89],"30,000":[90],"experiments":[92],"Gene":[95],"Expression":[96],"Omnibus":[97],"using":[98,129,149],"rigorous":[100],"filtering":[101],"criteria.":[102],"All":[103,124],"individually":[107],"submitted":[108],"background":[110],"correction,":[111],"normalization,":[112],"sample":[113,143],"analysis":[115,132],"manually":[118],"edited":[119],"eliminate":[121],"erroneous":[122],"probes.":[123],"tested":[128,148],"principal":[130],"component":[131],"(PCA)":[133],"t-distributed":[135],"stochastic":[136],"neighbor":[137],"embedding":[138],"(t-SNE)":[139],"analyses":[140],"observe":[142],"division":[144],"additionally":[147],"various":[150],"provide":[154],"base":[156],"accuracy":[157],"major":[160],"employed":[162],"sets.":[166],"CuMiDa":[167],"is":[168],"created":[171],"solely":[172],"applied":[180]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-09-07T09:17:50.787605","created_date":"2025-10-10T00:00:00"}