{"id":"https://openalex.org/W2048495112","doi":"https://doi.org/10.1142/s0219720012500230","title":"TUNING THE PRECISION OF PREDICTORS TO REDUCE OVERESTIMATION OF PROTEIN DISORDER OVER LARGE DATASETS","display_name":"TUNING THE PRECISION OF PREDICTORS TO REDUCE OVERESTIMATION OF PROTEIN DISORDER OVER LARGE DATASETS","publication_year":2012,"publication_date":"2012-10-02","ids":{"openalex":"https://openalex.org/W2048495112","doi":"https://doi.org/10.1142/s0219720012500230","mag":"2048495112","pmid":"https://pubmed.ncbi.nlm.nih.gov/23600814"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720012500230","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720012500230","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048095929","display_name":"Antonio Deiana","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"ANTONIO DEIANA","raw_affiliation_strings":["Physics Department, Sapienza University of Rome, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Physics Department, Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090645044","display_name":"Andrea Giansanti","orcid":"https://orcid.org/0000-0002-8113-8188"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]},{"id":"https://openalex.org/I4210157426","display_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Roma I","ror":"https://ror.org/05eva6s33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I160013858","https://openalex.org/I4210157426"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"ANDREA GIANSANTI","raw_affiliation_strings":["INFN, Sezione di Roma1, Roma, 00185, Italy","Physics Department, Sapienza University of Rome, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"INFN, Sezione di Roma1, Roma, 00185, Italy","institution_ids":["https://openalex.org/I4210157426"]},{"raw_affiliation_string":"Physics Department, Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048095929"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.2627,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56986213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"11","issue":"02","first_page":"1250023","last_page":"1250023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9961000084877014,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9961000084877014,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9951000213623047,"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/discriminative-model","display_name":"Discriminative model","score":0.7458482384681702},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5263646245002747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.473476767539978},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.468201220035553},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.46313172578811646},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4608871638774872},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4384618401527405},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3816709518432617},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.34066444635391235},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.32939404249191284},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.31059330701828003},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26981836557388306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2632126808166504},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2535298764705658},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.14546909928321838}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7458482384681702},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5263646245002747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.473476767539978},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.468201220035553},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.46313172578811646},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4608871638774872},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4384618401527405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3816709518432617},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34066444635391235},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32939404249191284},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.31059330701828003},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26981836557388306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2632126808166504},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2535298764705658},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.14546909928321838},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"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":"D009363","descriptor_name":"Neoplasm Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009363","descriptor_name":"Neoplasm Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009363","descriptor_name":"Neoplasm Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009363","descriptor_name":"Neoplasm Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009363","descriptor_name":"Neoplasm Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009363","descriptor_name":"Neoplasm Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","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},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1142/s0219720012500230","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720012500230","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:23600814","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23600814","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of bioinformatics and computational biology","raw_type":null},{"id":"pmh:oai:iris.uniroma1.it:11573/497993","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/497993","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.uniroma1.it:11573/663013","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/663013","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W634123086","https://openalex.org/W1552660489","https://openalex.org/W1792685479","https://openalex.org/W1976526581","https://openalex.org/W1979079649","https://openalex.org/W1982250822","https://openalex.org/W1991906934","https://openalex.org/W1995945562","https://openalex.org/W2000330915","https://openalex.org/W2006654567","https://openalex.org/W2027302413","https://openalex.org/W2030776726","https://openalex.org/W2061271983","https://openalex.org/W2070496155","https://openalex.org/W2085126881","https://openalex.org/W2092153867","https://openalex.org/W2095283284","https://openalex.org/W2097564976","https://openalex.org/W2101840439","https://openalex.org/W2102267487","https://openalex.org/W2105869636","https://openalex.org/W2110110505","https://openalex.org/W2118608964","https://openalex.org/W2120881407","https://openalex.org/W2128413613","https://openalex.org/W2129261098","https://openalex.org/W2130479394","https://openalex.org/W2132720084","https://openalex.org/W2137995988","https://openalex.org/W2144252381","https://openalex.org/W2154335467","https://openalex.org/W2156465034","https://openalex.org/W2159938554","https://openalex.org/W2161199282","https://openalex.org/W2168211076","https://openalex.org/W3106889297","https://openalex.org/W4233334497"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W4328049145"],"abstract_inverted_index":{"This":[0,144],"is":[1,145],"a":[2,30,48,60,64,97,122,148,156,164],"study":[3,150],"on":[4,81,104,121],"the":[5,15,27,34,41,68,82,109,113,128,133,137,152,173,189],"precision":[6,102],"of":[7,29,33,36,43,51,70,84,112,139,158,175],"four":[8],"known":[9],"protein":[10],"disorder":[11,166,176],"predictors,":[12,45,53],"ranked":[13],"among":[14,130,177],"best-performing":[16],"ones:":[17],"DISOPRED2,":[18],"PONDR":[19],"VSL2B,":[20],"IUPred":[21],"and":[22,92,117,132,155,180],"ESpritz.":[23],"We":[24],"address":[25],"here":[26],"problem":[28,91],"systematic":[31],"overestimation":[32],"number":[35],"disordered":[37,71,140],"proteins":[38,72,141,179],"recognized":[39],"through":[40],"use":[42],"these":[44,52],"considered":[46],"as":[47],"standard.":[49],"Some":[50],"used":[54],"with":[55,89,162],"their":[56,119],"default":[57],"setting,":[58],"have":[59],"low":[61],"precision,":[62],"implying":[63],"tendency":[65,134],"to":[66,95,135],"overestimate":[67,136],"occurrence":[69,138,174],"in":[73,93,147,188],"genome-wide":[74],"surveys.":[75],"Moreover,":[76],"different":[77],"predictors":[78,114,131],"often":[79],"disagree":[80],"evaluation":[83],"individual":[85],"proteins.":[86],"To":[87],"cope":[88],"this":[90],"order":[94],"propose":[96],"simple":[98],"procedure":[99],"that":[100,172],"enhances":[101],"based":[103],"precision-recall":[105],"curves,":[106],"we":[107],"re-tuned":[108],"discriminative":[110],"thresholds":[111],"by":[115],"training":[116],"cross-validating":[118],"performance":[120],"cured":[123],"dataset.":[124],"After":[125],"re-tuning,":[126],"both":[127],"disagreement":[129],"are":[142],"reduced.":[143],"shown":[146],"dedicated":[149],"over":[151],"human":[153,160],"proteome":[154],"set":[157],"cancer-related":[159,178],"proteins,":[161],"no":[163],"priori":[165],"annotation.":[167],"Simple":[168],"quantitative":[169],"estimates":[170],"suggest":[171],"other":[181],"similar":[182],"large-scale":[183],"surveys":[184],"has":[185],"been":[186],"overestimated":[187],"past.":[190]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}