{"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","doi":"https://doi.org/10.1093/bioinformatics/btg040","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg040","pdf_url":null,"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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","is_traditional":true,"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/A5048365807","display_name":"Javier Herrero","orcid":"https://orcid.org/0000-0001-7313-717X","observed_orcids":["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":false,"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"],"raw_orcid":null,"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","observed_orcids":["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"],"raw_orcid":null,"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\u00edn Dopazo","orcid":"https://orcid.org/0000-0003-3318-120X","observed_orcids":["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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089594"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":2.8285,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.91904085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"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":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":0.0,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gene-expression-microarrays","display_name":"gene expression microarrays","score":0.8330000042915344},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.9599999785423279},{"id":"https://openalex.org/keywords/web-based-tool","display_name":"web-based tool","score":0.6990000009536743},{"id":"https://openalex.org/keywords/scale-transformation","display_name":"scale transformation","score":0.6940000057220459},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.878000020980835},{"id":"https://openalex.org/keywords/interactive-data-analysis","display_name":"interactive data analysis","score":0.5789999961853027}],"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":"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":"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":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"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":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btg040","doi":"https://doi.org/10.1093/bioinformatics/btg040","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg040","pdf_url":null,"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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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","doi":null,"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,"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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1425236","doi":null,"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,"listed_in":[],"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":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"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/W2101641305","https://openalex.org/W2021139496","https://openalex.org/W7100672795","https://openalex.org/W2036811184","https://openalex.org/W1986823558","https://openalex.org/W2290287150","https://openalex.org/W2141694205","https://openalex.org/W2142650165","https://openalex.org/W2496410274","https://openalex.org/W3180480119"],"abstract_inverted_index":{"Abstract":[0],"Summary:":[1],"We":[2],"present":[3],"an":[4],"interactive":[5],"web":[6,72],"tool":[7],"for":[8],"preprocessing":[9,32],"microarray":[10],"gene":[11],"expression":[12],"data.":[13],"It":[14],"analyses":[15],"the":[16,19],"data,":[17],"suggests":[18],"most":[20],"appropriate":[21],"transformations":[22],"and":[23,46,49],"proceeds":[24],"with":[25],"them":[26],"after":[27],"user":[28],"agreement.":[29],"The":[30,58,71],"normal":[31],"steps":[33],"include":[34],"scale":[35],"transformations,":[36],"management":[37],"of":[38],"missing":[39],"values,":[40],"replicate":[41],"handling,":[42],"flat":[43],"pattern":[44,47,56,67],"filtering":[45],"standardization":[48],"they":[50],"are":[51],"required":[52],"before":[53],"performing":[54],"any":[55],"analysis.":[57],"processed":[59],"data":[60],"set":[61],"can":[62],"be":[63,85],"sent":[64],"to":[65],"other":[66],"analysis":[68],"tools.":[69],"Availability:":[70],"interface":[73],"is":[74],"accessible":[75],"through":[76],"http://bioinfo.cnio.es/cgi-bin/tools/dnarray/preprocess":[77],"Contact:":[78],"jdopazo@cnio.es":[79],"*":[80],"To":[81],"whom":[82],"correspondence":[83],"should":[84],"addressed.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}
