{"id":"https://openalex.org/W4311557029","doi":"https://doi.org/10.1371/journal.pcbi.1010718","title":"Eleven quick tips for data cleaning and feature engineering","display_name":"Eleven quick tips for data cleaning and feature engineering","publication_year":2022,"publication_date":"2022-12-15","ids":{"openalex":"https://openalex.org/W4311557029","doi":"https://doi.org/10.1371/journal.pcbi.1010718","pmid":"https://pubmed.ncbi.nlm.nih.gov/36520712"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1010718","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010718","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010718&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010718&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011556172","display_name":"Davide Chicco","orcid":"https://orcid.org/0000-0001-9655-7142"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Davide Chicco","raw_affiliation_strings":["Institute of Health Policy Management and Evaluation, University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9655-7142","affiliations":[{"raw_affiliation_string":"Institute of Health Policy Management and Evaluation, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045802198","display_name":"Luca Oneto","orcid":"https://orcid.org/0000-0002-8445-395X"},"institutions":[{"id":"https://openalex.org/I4210139705","display_name":"Ingegneria dei Sistemi (Italy)","ror":"https://ror.org/03spsm219","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210139705"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Oneto","raw_affiliation_strings":["Dipartimento di Informatica Bioingegneria Robotica e Ingegneria dei Sistemi, Universit\u00e0 di Genova, Genoa, Italy","ZenaByte S.r.l., Genoa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-8445-395X","affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica Bioingegneria Robotica e Ingegneria dei Sistemi, Universit\u00e0 di Genova, Genoa, Italy","institution_ids":["https://openalex.org/I4210139705"]},{"raw_affiliation_string":"ZenaByte S.r.l., Genoa, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039343044","display_name":"Erica Tavazzi","orcid":"https://orcid.org/0000-0001-6188-6413"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Erica Tavazzi","raw_affiliation_strings":["Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 di Padova, Padua, Italy","Dipartimento di Ingegneria dell\u2019Informazione, Universit\u00e0 di Padova, Padua, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 di Padova, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Dipartimento di Ingegneria dell\u2019Informazione, Universit\u00e0 di Padova, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011556172"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":7.214,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97512045,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":"12","first_page":"e1010718","last_page":"e1010718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9907000064849854,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9896000027656555,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.7735344171524048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271448373794556},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6549813747406006},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6294065117835999},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5709089636802673},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5461056232452393},{"id":"https://openalex.org/keywords/informatics","display_name":"Informatics","score":0.5243342518806458},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5003385543823242},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4949914813041687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48069244623184204},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.447859525680542},{"id":"https://openalex.org/keywords/health-informatics","display_name":"Health informatics","score":0.4109848141670227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35688018798828125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3201430141925812},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15419480204582214},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.1360747516155243},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.12529519200325012}],"concepts":[{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.7735344171524048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271448373794556},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6549813747406006},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6294065117835999},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5709089636802673},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5461056232452393},{"id":"https://openalex.org/C191630685","wikidata":"https://www.wikidata.org/wiki/Q4027615","display_name":"Informatics","level":2,"score":0.5243342518806458},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5003385543823242},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4949914813041687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48069244623184204},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.447859525680542},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.4109848141670227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35688018798828125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3201430141925812},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15419480204582214},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.1360747516155243},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.12529519200325012},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004738","descriptor_name":"Engineering","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004738","descriptor_name":"Engineering","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004738","descriptor_name":"Engineering","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004738","descriptor_name":"Engineering","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":9,"locations":[{"id":"doi:10.1371/journal.pcbi.1010718","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010718","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010718&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:36520712","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36520712","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:RePEc:plo:pcbi00:1010718","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010718","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:boa.unimib.it:10281/430240","is_oa":true,"landing_page_url":"https://hdl.handle.net/10281/430240","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:32379077850a48e2bb6e3e43f6df4159","is_oa":true,"landing_page_url":"https://doaj.org/article/32379077850a48e2bb6e3e43f6df4159","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 18, Iss 12 (2022)","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:b717d08bc69a4c2d8e74c759723767b2","is_oa":true,"landing_page_url":"https://doaj.org/article/b717d08bc69a4c2d8e74c759723767b2","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 18, Iss 12, p e1010718 (2022)","raw_type":"article"},{"id":"pmh:oai:iris.unige.it:11567/1143895","is_oa":true,"landing_page_url":"https://hdl.handle.net/11567/1143895","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9754225","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9754225","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"},{"id":"pmh:oai:www.research.unipd.it:11577/3470334","is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3470334","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1010718","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010718","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010718&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311557029.pdf","grobid_xml":"https://content.openalex.org/works/W4311557029.grobid-xml"},"referenced_works_count":224,"referenced_works":["https://openalex.org/W133884053","https://openalex.org/W327170683","https://openalex.org/W1187335281","https://openalex.org/W1486089178","https://openalex.org/W1486401986","https://openalex.org/W1492653423","https://openalex.org/W1510073064","https://openalex.org/W1570640594","https://openalex.org/W1574901103","https://openalex.org/W1576808520","https://openalex.org/W1594220124","https://openalex.org/W1594924988","https://openalex.org/W1598796236","https://openalex.org/W1680622244","https://openalex.org/W1742512077","https://openalex.org/W1761022139","https://openalex.org/W1768179097","https://openalex.org/W1971935224","https://openalex.org/W1986849266","https://openalex.org/W2002645541","https://openalex.org/W2008255964","https://openalex.org/W2011301426","https://openalex.org/W2024812658","https://openalex.org/W2027595342","https://openalex.org/W2036318837","https://openalex.org/W2040032582","https://openalex.org/W2049446938","https://openalex.org/W2056575763","https://openalex.org/W2072062223","https://openalex.org/W2077641783","https://openalex.org/W2081028405","https://openalex.org/W2083927153","https://openalex.org/W2096192437","https://openalex.org/W2096506014","https://openalex.org/W2103018059","https://openalex.org/W2106810132","https://openalex.org/W2116814040","https://openalex.org/W2125569215","https://openalex.org/W2131479089","https://openalex.org/W2133111499","https://openalex.org/W2135606128","https://openalex.org/W2140503409","https://openalex.org/W2144981148","https://openalex.org/W2147013674","https://openalex.org/W2158131535","https://openalex.org/W2161336914","https://openalex.org/W2162772535","https://openalex.org/W2163922914","https://openalex.org/W2187059374","https://openalex.org/W2191679689","https://openalex.org/W2252523470","https://openalex.org/W2275841169","https://openalex.org/W2302501749","https://openalex.org/W2315493944","https://openalex.org/W2344424577","https://openalex.org/W2490023472","https://openalex.org/W2496114304","https://openalex.org/W2533800772","https://openalex.org/W2534699084","https://openalex.org/W2551432253","https://openalex.org/W2551974706","https://openalex.org/W2556970231","https://openalex.org/W2562568662","https://openalex.org/W2568949447","https://openalex.org/W2592929672","https://openalex.org/W2594475271","https://openalex.org/W2606089314","https://openalex.org/W2618025634","https://openalex.org/W2670253439","https://openalex.org/W2691976780","https://openalex.org/W2725273399","https://openalex.org/W2733722625","https://openalex.org/W2739655593","https://openalex.org/W2739783898","https://openalex.org/W2765811365","https://openalex.org/W2766447205","https://openalex.org/W2769353087","https://openalex.org/W2771169143","https://openalex.org/W2771817472","https://openalex.org/W2772803673","https://openalex.org/W2773446523","https://openalex.org/W2784283104","https://openalex.org/W2790370540","https://openalex.org/W2791315675","https://openalex.org/W2793630790","https://openalex.org/W2794386528","https://openalex.org/W2799040448","https://openalex.org/W2799900537","https://openalex.org/W2802802541","https://openalex.org/W2803805253","https://openalex.org/W2805627121","https://openalex.org/W2807124908","https://openalex.org/W2885311373","https://openalex.org/W2889470180","https://openalex.org/W2889585390","https://openalex.org/W2897666594","https://openalex.org/W2897765576","https://openalex.org/W2906319771","https://openalex.org/W2912526495","https://openalex.org/W2913694513","https://openalex.org/W2941955549","https://openalex.org/W2942967593","https://openalex.org/W2945020349","https://openalex.org/W2951384661","https://openalex.org/W2955863859","https://openalex.org/W2962772482","https://openalex.org/W2962843773","https://openalex.org/W2963095307","https://openalex.org/W2963258365","https://openalex.org/W2963360736","https://openalex.org/W2963518130","https://openalex.org/W2963611658","https://openalex.org/W2966284335","https://openalex.org/W2967098998","https://openalex.org/W2970030610","https://openalex.org/W2971384042","https://openalex.org/W2980282514","https://openalex.org/W2981731882","https://openalex.org/W2986579771","https://openalex.org/W2991046651","https://openalex.org/W2991157178","https://openalex.org/W2994742268","https://openalex.org/W2997785591","https://openalex.org/W2998216295","https://openalex.org/W2998768810","https://openalex.org/W3000409346","https://openalex.org/W3002944878","https://openalex.org/W3005153041","https://openalex.org/W3005552578","https://openalex.org/W3006241798","https://openalex.org/W3007960301","https://openalex.org/W3009943557","https://openalex.org/W3010062253","https://openalex.org/W3014590323","https://openalex.org/W3015567273","https://openalex.org/W3021654819","https://openalex.org/W3032467329","https://openalex.org/W3033040110","https://openalex.org/W3033733989","https://openalex.org/W3035242236","https://openalex.org/W3037582100","https://openalex.org/W3077205433","https://openalex.org/W3080427797","https://openalex.org/W3092005729","https://openalex.org/W3096481255","https://openalex.org/W3097993951","https://openalex.org/W3105571542","https://openalex.org/W3105580455","https://openalex.org/W3107001518","https://openalex.org/W3118310392","https://openalex.org/W3119124294","https://openalex.org/W3119160562","https://openalex.org/W3123155958","https://openalex.org/W3134665742","https://openalex.org/W3134989920","https://openalex.org/W3135347465","https://openalex.org/W3156950777","https://openalex.org/W3163842339","https://openalex.org/W3164396614","https://openalex.org/W3165904677","https://openalex.org/W3170719901","https://openalex.org/W3176690277","https://openalex.org/W3177828909","https://openalex.org/W3181414820","https://openalex.org/W3181518724","https://openalex.org/W3182546273","https://openalex.org/W3184353232","https://openalex.org/W3195438473","https://openalex.org/W3195439074","https://openalex.org/W3195971125","https://openalex.org/W3197494818","https://openalex.org/W3197744105","https://openalex.org/W3204504767","https://openalex.org/W3204683753","https://openalex.org/W3213384164","https://openalex.org/W3214243459","https://openalex.org/W3216759837","https://openalex.org/W4205436505","https://openalex.org/W4206212643","https://openalex.org/W4207035044","https://openalex.org/W4211072535","https://openalex.org/W4213424654","https://openalex.org/W4223413649","https://openalex.org/W4230765542","https://openalex.org/W4232619139","https://openalex.org/W4232994680","https://openalex.org/W4236362309","https://openalex.org/W4240301789","https://openalex.org/W4242186111","https://openalex.org/W4243072198","https://openalex.org/W4244529562","https://openalex.org/W4247200422","https://openalex.org/W4249224151","https://openalex.org/W4255289024","https://openalex.org/W4280553965","https://openalex.org/W4281683366","https://openalex.org/W4285405545","https://openalex.org/W4287393709","https://openalex.org/W4288091267","https://openalex.org/W4290973443","https://openalex.org/W4293089508","https://openalex.org/W4294839477","https://openalex.org/W4295750444","https://openalex.org/W4297730339","https://openalex.org/W4298826872","https://openalex.org/W4300982406","https://openalex.org/W4301396488","https://openalex.org/W4301518628","https://openalex.org/W4376453806","https://openalex.org/W6653178256","https://openalex.org/W6657138077","https://openalex.org/W6680836886","https://openalex.org/W6692628530","https://openalex.org/W6722680694","https://openalex.org/W6747227044","https://openalex.org/W6751069187","https://openalex.org/W6753278433","https://openalex.org/W6775487275","https://openalex.org/W6776331362","https://openalex.org/W6798026231","https://openalex.org/W6802417858","https://openalex.org/W6803813760","https://openalex.org/W6807912955","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3092506759","https://openalex.org/W3010890513","https://openalex.org/W2390914021","https://openalex.org/W2389417819","https://openalex.org/W3195278891"],"abstract_inverted_index":{"Applying":[0],"computational":[1,49,215],"statistics":[2],"or":[3,96,121,193,200],"machine":[4],"learning":[5],"methods":[6],"to":[7,26,43,47,146,181,190,196,222],"data":[8,46,54,67,111,139,198],"is":[9],"a":[10,87,90,94,102,105],"key":[11,60],"component":[12],"of":[13,62,81,93],"many":[14],"scientific":[15,64,183],"studies,":[16],"in":[17,104,170,177,220],"any":[18,36,63,182,191],"field,":[19],"but":[20],"alone":[21],"might":[22],"not":[23],"be":[24,72,179],"sufficient":[25],"generate":[27],"robust":[28],"and":[29,32,56,69,75,113,126,141,157,166,211,226],"reliable":[30,228],"outcomes":[31,225],"results.":[33],"Before":[34],"applying":[35],"discovery":[37],"method,":[38],"preprocessing":[39,151],"steps":[40,116,152],"are":[41,59,118],"necessary":[42],"prepare":[44],"the":[45,48,78,82],"analysis.":[50],"In":[51],"this":[52,130],"framework,":[53],"cleaning":[55,112,140,199],"feature":[57,114,142,201],"engineering":[58,115,143],"pillars":[61],"study":[65],"involving":[66],"analysis":[68],"that":[70,217],"should":[71],"adequately":[73],"designed":[74,161],"performed":[76],"since":[77],"first":[79],"phases":[80],"project.":[83],"We":[84,185,203],"call":[85],"\"feature\"":[86],"variable":[88],"describing":[89],"particular":[91],"trait":[92],"person":[95],"an":[97],"observation,":[98],"recorded":[99],"usually":[100],"as":[101],"column":[103],"dataset.":[106],"Even":[107],"if":[108],"pivotal,":[109],"these":[110,149,162,188],"sometimes":[117],"done":[119],"poorly":[120],"inefficiently,":[122],"especially":[123],"by":[124],"beginners":[125],"unexperienced":[127],"researchers.":[128],"For":[129],"reason,":[131],"we":[132,160,172],"propose":[133],"here":[134],"our":[135,205],"quick":[136],"tips":[137],"for":[138],"on":[144],"how":[145],"carry":[147],"out":[148],"important":[150],"correctly":[153],"avoiding":[154],"common":[155],"mistakes":[156],"pitfalls.":[158],"Although":[159],"guidelines":[163,189],"with":[164],"bioinformatics":[165],"health":[167],"informatics":[168],"scenarios":[169],"mind,":[171],"believe":[173,204],"they":[174],"can":[175,208,218],"more":[176,223,227],"general":[178],"applied":[180],"area.":[184],"therefore":[186],"target":[187],"researcher":[192],"practitioners":[194],"wanting":[195],"perform":[197,213],"engineering.":[202],"simple":[206],"recommendations":[207],"help":[209],"researchers":[210],"scholars":[212],"better":[214],"analyses":[216],"lead,":[219],"turn,":[221],"solid":[224],"discoveries.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}