{"id":"https://openalex.org/W2185628700","doi":"https://doi.org/10.1093/bib/bbv082","title":"Correct machine learning on protein sequences: a peer-reviewing perspective","display_name":"Correct machine learning on protein sequences: a peer-reviewing perspective","publication_year":2015,"publication_date":"2015-09-26","ids":{"openalex":"https://openalex.org/W2185628700","doi":"https://doi.org/10.1093/bib/bbv082","mag":"2185628700","pmid":"https://pubmed.ncbi.nlm.nih.gov/26411473"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbv082","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbv082","pdf_url":"https://academic.oup.com/bib/article-pdf/17/5/831/17485706/bbv082.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bib/article-pdf/17/5/831/17485706/bbv082.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060625212","display_name":"Ian Walsh","orcid":"https://orcid.org/0000-0003-3994-5522"},"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"]},{"id":"https://openalex.org/I24715933","display_name":"University of Reunion Island","ror":"https://ror.org/005ypkf75","country_code":"RE","type":"education","lineage":["https://openalex.org/I24715933"]}],"countries":["IT","RE"],"is_corresponding":false,"raw_author_name":"Ian Walsh","raw_affiliation_strings":["Ian Walsh is a PostDoc at the BioComputing UP laboratory, University of Padua. His main research interest is to develop novel prediction methods for structural bioinformatics using machine learning","Dept. of Biomedical Sciences, University of Padua, viale G. Colombo 3, 35131 Padova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ian Walsh is a PostDoc at the BioComputing UP laboratory, University of Padua. His main research interest is to develop novel prediction methods for structural bioinformatics using machine learning","institution_ids":["https://openalex.org/I24715933"]},{"raw_affiliation_string":"Dept. of Biomedical Sciences, University of Padua, viale G. Colombo 3, 35131 Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016630267","display_name":"Gianluca Pollastri","orcid":"https://orcid.org/0000-0002-5825-4949"},"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"]},{"id":"https://openalex.org/I66083562","display_name":"Systems Research Institute","ror":"https://ror.org/0111cp837","country_code":"PL","type":"facility","lineage":["https://openalex.org/I66083562","https://openalex.org/I99542240"]}],"countries":["IT","PL"],"is_corresponding":false,"raw_author_name":"Gianluca Pollastri","raw_affiliation_strings":["Gianluca Pollastri is a principal investigator in the Complex and Adaptive Systems Laboratory at University College Dublin. His research focuses on machine learning for structured data, mainly applied to bioinformatics and chemoinformatics","Dept. of Biomedical Sciences, University of Padua, viale G. Colombo 3, 35131 Padova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gianluca Pollastri is a principal investigator in the Complex and Adaptive Systems Laboratory at University College Dublin. His research focuses on machine learning for structured data, mainly applied to bioinformatics and chemoinformatics","institution_ids":["https://openalex.org/I66083562"]},{"raw_affiliation_string":"Dept. of Biomedical Sciences, University of Padua, viale G. Colombo 3, 35131 Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066560665","display_name":"Silvio C. E. Tosatto","orcid":"https://orcid.org/0000-0003-4525-7793"},"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"]},{"id":"https://openalex.org/I19908199","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03g9ch715","country_code":"BG","type":"facility","lineage":["https://openalex.org/I19908199"]}],"countries":["BG","IT"],"is_corresponding":true,"raw_author_name":"Silvio C. E. Tosatto","raw_affiliation_strings":["Silvio Tosatto is principal investigator of the BioComputing UP laboratory at the Department of Biomedical Sciences, University of Padua. He is also an editor for the journals Amino Acids, Biochimie, PeerJ and PLoS One. His research focuses on structural bioinformatics and its application to biomedical problems","Dept. of Biomedical Sciences, University of Padua, viale G. Colombo 3, 35131 Padova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Silvio Tosatto is principal investigator of the BioComputing UP laboratory at the Department of Biomedical Sciences, University of Padua. He is also an editor for the journals Amino Acids, Biochimie, PeerJ and PLoS One. His research focuses on structural bioinformatics and its application to biomedical problems","institution_ids":["https://openalex.org/I19908199"]},{"raw_affiliation_string":"Dept. of Biomedical Sciences, University of Padua, viale G. Colombo 3, 35131 Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066560665"],"corresponding_institution_ids":["https://openalex.org/I138689650","https://openalex.org/I19908199"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":2.0669,"has_fulltext":true,"cited_by_count":82,"citation_normalized_percentile":{"value":0.87269338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"17","issue":"5","first_page":"831","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9988999962806702,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9988999962806702,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.7969459295272827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.764039158821106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6723459362983704},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6348932981491089},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5423650741577148},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5388990640640259},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45927128195762634},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44817084074020386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969459295272827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.764039158821106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6723459362983704},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6348932981491089},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5423650741577148},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5388990640640259},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45927128195762634},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44817084074020386},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bib/bbv082","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbv082","pdf_url":"https://academic.oup.com/bib/article-pdf/17/5/831/17485706/bbv082.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26411473","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26411473","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:open-archive.highwire.org:bib:17/5/831","is_oa":false,"landing_page_url":"http://bib.oxfordjournals.org/cgi/content/short/17/5/831","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"},{"id":"pmh:oai:www.research.unipd.it:11577/3230654","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/3230654","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bib/bbv082","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbv082","pdf_url":"https://academic.oup.com/bib/article-pdf/17/5/831/17485706/bbv082.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2334119310","display_name":null,"funder_award_id":"GR-2011-02347754","funder_id":"https://openalex.org/F4320321781","funder_display_name":"Ministero della Salute"},{"id":"https://openalex.org/G3526188868","display_name":null,"funder_award_id":"GR-2011-02346845","funder_id":"https://openalex.org/F4320321781","funder_display_name":"Ministero della Salute"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320321781","display_name":"Ministero della Salute","ror":"https://ror.org/00789fa95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2185628700.pdf","grobid_xml":"https://content.openalex.org/works/W2185628700.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1499450468","https://openalex.org/W1505191356","https://openalex.org/W1508885706","https://openalex.org/W1510073064","https://openalex.org/W1967112996","https://openalex.org/W1969007008","https://openalex.org/W1981552604","https://openalex.org/W1982267716","https://openalex.org/W1996342555","https://openalex.org/W2005129098","https://openalex.org/W2030776726","https://openalex.org/W2047544230","https://openalex.org/W2047750588","https://openalex.org/W2048947602","https://openalex.org/W2072132202","https://openalex.org/W2076586303","https://openalex.org/W2091940856","https://openalex.org/W2092247420","https://openalex.org/W2096929799","https://openalex.org/W2098740506","https://openalex.org/W2109801072","https://openalex.org/W2110149903","https://openalex.org/W2112081648","https://openalex.org/W2117486996","https://openalex.org/W2119387367","https://openalex.org/W2119479037","https://openalex.org/W2119939131","https://openalex.org/W2130161623","https://openalex.org/W2137219016","https://openalex.org/W2137995988","https://openalex.org/W2141007997","https://openalex.org/W2143199763","https://openalex.org/W2147526198","https://openalex.org/W2148633389","https://openalex.org/W2148740464","https://openalex.org/W2153153865","https://openalex.org/W2153187042","https://openalex.org/W2156125289","https://openalex.org/W2157437977","https://openalex.org/W2158698691","https://openalex.org/W2158714788","https://openalex.org/W2164632416","https://openalex.org/W2167277498","https://openalex.org/W2214916291","https://openalex.org/W2605068739","https://openalex.org/W2751318774","https://openalex.org/W2997833137","https://openalex.org/W3104887532","https://openalex.org/W3198350258","https://openalex.org/W4285719527","https://openalex.org/W6688612899"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W92963860","https://openalex.org/W2041249487"],"abstract_inverted_index":{"Machine":[0,13],"learning":[1,14,56],"methods":[2],"are":[3],"becoming":[4],"increasingly":[5],"popular":[6],"to":[7,32,45,52,62,69,82,100,118],"predict":[8],"protein":[9],"features":[10],"from":[11],"sequences.":[12],"in":[15,123],"bioinformatics":[16],"can":[17],"be":[18,70,101],"powerful":[19],"but":[20],"carries":[21],"also":[22,89],"the":[23,36,75,112,120],"risk":[24],"of":[25,35,43],"introducing":[26],"unexpected":[27],"biases,":[28],"which":[29,67,87],"may":[30],"lead":[31],"an":[33],"overestimation":[34],"performance.":[37],"This":[38],"article":[39],"espouses":[40],"a":[41],"set":[42],"guidelines":[44,114],"allow":[46],"both":[47],"peer":[48],"reviewers":[49],"and":[50,72,77],"authors":[51],"avoid":[53,83],"common":[54],"machine":[55,124],"pitfalls.":[57],"Understanding":[58],"biology":[59],"is":[60,80,88],"necessary":[61],"produce":[63],"useful":[64],"data":[65],"sets,":[66],"have":[68],"large":[71],"diverse.":[73],"Separating":[74],"training":[76],"test":[78],"process":[79],"imperative":[81],"over-selling":[84],"method":[85],"performance,":[86],"dependent":[90],"on":[91],"several":[92,104],"hidden":[93],"parameters.":[94],"A":[95],"novel":[96],"predictor":[97],"has":[98],"always":[99],"compared":[102],"with":[103],"existing":[105],"methods,":[106],"including":[107],"simple":[108],"baseline":[109],"strategies.":[110],"Using":[111],"presented":[113],"will":[115],"help":[116],"nonspecialists":[117],"appreciate":[119],"critical":[121],"issues":[122],"learning.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}