{"id":"https://openalex.org/W2166902257","doi":"https://doi.org/10.1093/bioinformatics/btg040","title":"Gene expression data preprocessing","display_name":"Gene expression data preprocessing","publication_year":2003,"publication_date":"2003-03-21","ids":{"openalex":"https://openalex.org/W2166902257","doi":"https://doi.org/10.1093/bioinformatics/btg040","mag":"2166902257","pmid":"https://pubmed.ncbi.nlm.nih.gov/12651726"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg040","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg040","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/5/655/48904171/bioinformatics_19_5_655.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/19/5/655/48904171/bioinformatics_19_5_655.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048365807","display_name":"Javier Herrero","orcid":"https://orcid.org/0000-0001-7313-717X"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"J. Herrero","raw_affiliation_strings":["Unidad de Bioinform\u00e1tica, Centro Nacional de Investigaciones Oncol\u00f3gicas (CNIO), Melchor Fern\u00e1ndez Almagro, 3 28029 Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Unidad de Bioinform\u00e1tica, Centro Nacional de Investigaciones Oncol\u00f3gicas (CNIO), Melchor Fern\u00e1ndez Almagro, 3 28029 Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080620893","display_name":"Ram\u00f3n D\u00edaz\u2010Uriarte","orcid":"https://orcid.org/0000-0002-6637-9039"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"R. D\u00edaz-Uriarte","raw_affiliation_strings":["Unidad de Bioinform\u00e1tica, Centro Nacional de Investigaciones Oncol\u00f3gicas (CNIO), Melchor Fern\u00e1ndez Almagro, 3 28029 Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Unidad de Bioinform\u00e1tica, Centro Nacional de Investigaciones Oncol\u00f3gicas (CNIO), Melchor Fern\u00e1ndez Almagro, 3 28029 Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074140420","display_name":"Joaqu\u0131\u0301n Dopazo","orcid":"https://orcid.org/0000-0003-3318-120X"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"J. Dopazo","raw_affiliation_strings":["Unidad de Bioinform\u00e1tica, Centro Nacional de Investigaciones Oncol\u00f3gicas (CNIO), Melchor Fern\u00e1ndez Almagro, 3 28029 Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Unidad de Bioinform\u00e1tica, Centro Nacional de Investigaciones Oncol\u00f3gicas (CNIO), Melchor Fern\u00e1ndez Almagro, 3 28029 Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048365807"],"corresponding_institution_ids":["https://openalex.org/I4210089594"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.5459,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.93582064,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"5","first_page":"655","last_page":"656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9994999766349792,"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/T10885","display_name":"Gene expression and cancer classification","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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9879999756813049,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/preprocessor","display_name":"Preprocessor","score":0.8705205917358398},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.7391785383224487},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.6992567777633667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6935173273086548},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6261632442474365},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.6194602251052856},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5944544672966003},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.532317578792572},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5203575491905212},{"id":"https://openalex.org/keywords/microarray-analysis-techniques","display_name":"Microarray analysis techniques","score":0.5124102234840393},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.48839229345321655},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.4235437214374542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32354143261909485},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.23654809594154358},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13499373197555542},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12972018122673035},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10876020789146423},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09751242399215698},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08112862706184387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07367917895317078}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8705205917358398},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.7391785383224487},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.6992567777633667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6935173273086548},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6261632442474365},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6194602251052856},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5944544672966003},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.532317578792572},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5203575491905212},{"id":"https://openalex.org/C8415881","wikidata":"https://www.wikidata.org/wiki/Q6839217","display_name":"Microarray analysis techniques","level":4,"score":0.5124102234840393},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.48839229345321655},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.4235437214374542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32354143261909485},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.23654809594154358},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13499373197555542},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12972018122673035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10876020789146423},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09751242399215698},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08112862706184387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07367917895317078},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","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":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btg040","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg040","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/5/655/48904171/bioinformatics_19_5_655.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:12651726","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12651726","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1425236","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1425236/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   BIOINFORMATICS , 19  (5)   pp. 655-656.   (2003)      ","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btg040","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg040","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/5/655/48904171/bioinformatics_19_5_655.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2166902257.pdf","grobid_xml":"https://content.openalex.org/works/W2166902257.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1970156673","https://openalex.org/W2000393684","https://openalex.org/W2040613244","https://openalex.org/W2060406328","https://openalex.org/W2096863518","https://openalex.org/W2103017472","https://openalex.org/W2137540340"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W22115721","https://openalex.org/W2211931904","https://openalex.org/W2321234655","https://openalex.org/W2952773340","https://openalex.org/W2470062578","https://openalex.org/W2981861370","https://openalex.org/W3149103228","https://openalex.org/W2379323287"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"interactive":[3],"web":[4],"tool":[5],"for":[6],"preprocessing":[7,30],"microarray":[8],"gene":[9],"expression":[10],"data.":[11],"It":[12],"analyses":[13],"the":[14,17],"data,":[15],"suggests":[16],"most":[18],"appropriate":[19],"transformations":[20],"and":[21,44,47],"proceeds":[22],"with":[23],"them":[24],"after":[25],"user":[26],"agreement.":[27],"The":[28,56],"normal":[29],"steps":[31],"include":[32],"scale":[33],"transformations,":[34],"management":[35],"of":[36],"missing":[37],"values,":[38],"replicate":[39],"handling,":[40],"flat":[41],"pattern":[42,45,54,65],"filtering":[43],"standardization":[46],"they":[48],"are":[49],"required":[50],"before":[51],"performing":[52],"any":[53],"analysis.":[55],"processed":[57],"data":[58],"set":[59],"can":[60],"be":[61],"sent":[62],"to":[63],"other":[64],"analysis":[66],"tools.":[67]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
