{"id":"https://openalex.org/W2099467260","doi":"https://doi.org/10.1093/bioinformatics/bth332","title":"Data mining techniques to study the disulfide-bonding state in proteins: signal peptide is a strong descriptor","display_name":"Data mining techniques to study the disulfide-bonding state in proteins: signal peptide is a strong descriptor","publication_year":2004,"publication_date":"2004-05-27","ids":{"openalex":"https://openalex.org/W2099467260","doi":"https://doi.org/10.1093/bioinformatics/bth332","mag":"2099467260","pmid":"https://pubmed.ncbi.nlm.nih.gov/15166026"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth332","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth332","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,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000575007","display_name":"Dominique Tessier","orcid":"https://orcid.org/0000-0003-1503-7693"},"institutions":[{"id":"https://openalex.org/I4210099947","display_name":"Biopolym\u00e8res Interactions Assemblages","ror":"https://ror.org/013vjwn12","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210099947","https://openalex.org/I4210108720"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Dominique Tessier","raw_affiliation_strings":["Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France. tessier@nantes.inra.fr","Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France"],"affiliations":[{"raw_affiliation_string":"Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France. tessier@nantes.inra.fr","institution_ids":["https://openalex.org/I4210099947"]},{"raw_affiliation_string":"Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France","institution_ids":["https://openalex.org/I4210099947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040815003","display_name":"Benjamin Bardiaux","orcid":"https://orcid.org/0000-0003-4014-9195"},"institutions":[{"id":"https://openalex.org/I4210099947","display_name":"Biopolym\u00e8res Interactions Assemblages","ror":"https://ror.org/013vjwn12","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210099947","https://openalex.org/I4210108720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benjamin Bardiaux","raw_affiliation_strings":["Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France"],"affiliations":[{"raw_affiliation_string":"Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France","institution_ids":["https://openalex.org/I4210099947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059593451","display_name":"Colette Larr\u00e9","orcid":"https://orcid.org/0000-0001-9585-9536"},"institutions":[{"id":"https://openalex.org/I4210099947","display_name":"Biopolym\u00e8res Interactions Assemblages","ror":"https://ror.org/013vjwn12","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210099947","https://openalex.org/I4210108720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Colette Larr\u00e9","raw_affiliation_strings":["Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France"],"affiliations":[{"raw_affiliation_string":"Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France","institution_ids":["https://openalex.org/I4210099947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112184401","display_name":"Yves Popineau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099947","display_name":"Biopolym\u00e8res Interactions Assemblages","ror":"https://ror.org/013vjwn12","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210099947","https://openalex.org/I4210108720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yves Popineau","raw_affiliation_strings":["Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France"],"affiliations":[{"raw_affiliation_string":"Unit\u00e9 de Recherche sur les Prot\u00e9ines V\u00e9g\u00e9tales et leurs Interactions, INRA Rue de la G\u00e9raudi\u00e8re, BP 71627, 44316 Nantes Cedex 3, France","institution_ids":["https://openalex.org/I4210099947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000575007"],"corresponding_institution_ids":["https://openalex.org/I4210099947"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.1206,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.49490388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":"16","first_page":"2509","last_page":"2512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.998199999332428,"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":0.9934999942779541,"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/disulfide-bond","display_name":"Disulfide bond","score":0.7182821035385132},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6143571734428406},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5515015125274658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5384073257446289},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.528501570224762},{"id":"https://openalex.org/keywords/signal-peptide","display_name":"Signal peptide","score":0.5099014043807983},{"id":"https://openalex.org/keywords/peptide","display_name":"Peptide","score":0.45588669180870056},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.4198577105998993},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.38154876232147217},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2775288224220276},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.2242211401462555},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.20102491974830627},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16207945346832275},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06763070821762085}],"concepts":[{"id":"https://openalex.org/C27256138","wikidata":"https://www.wikidata.org/wiki/Q1230226","display_name":"Disulfide bond","level":2,"score":0.7182821035385132},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6143571734428406},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5515015125274658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5384073257446289},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.528501570224762},{"id":"https://openalex.org/C10858879","wikidata":"https://www.wikidata.org/wiki/Q899790","display_name":"Signal peptide","level":4,"score":0.5099014043807983},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.45588669180870056},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.4198577105998993},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.38154876232147217},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2775288224220276},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.2242211401462555},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.20102491974830627},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16207945346832275},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06763070821762085},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004220","descriptor_name":"Disulfides","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004220","descriptor_name":"Disulfides","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004220","descriptor_name":"Disulfides","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004220","descriptor_name":"Disulfides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004220","descriptor_name":"Disulfides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004220","descriptor_name":"Disulfides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004721","descriptor_name":"Endoplasmic Reticulum","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004721","descriptor_name":"Endoplasmic Reticulum","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004721","descriptor_name":"Endoplasmic Reticulum","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D021382","descriptor_name":"Protein Sorting Signals","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D021382","descriptor_name":"Protein Sorting Signals","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D021382","descriptor_name":"Protein Sorting Signals","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bth332","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth332","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,"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:15166026","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15166026","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.861.1059","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.861.1059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2004/05/27/bioinformatics.bth332.full.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1975304761","https://openalex.org/W1984615569","https://openalex.org/W2003144438","https://openalex.org/W2008581287","https://openalex.org/W2008708467","https://openalex.org/W2009664421","https://openalex.org/W2039890138","https://openalex.org/W2068802139","https://openalex.org/W2101595316","https://openalex.org/W2103017472","https://openalex.org/W2108746608","https://openalex.org/W2123475246","https://openalex.org/W2128667006","https://openalex.org/W2130479394","https://openalex.org/W2143299777","https://openalex.org/W2166559705","https://openalex.org/W2168211076","https://openalex.org/W4236463097","https://openalex.org/W4239620712","https://openalex.org/W4243457879"],"related_works":["https://openalex.org/W4256688441","https://openalex.org/W1996059209","https://openalex.org/W2169730659","https://openalex.org/W2379641374","https://openalex.org/W2038339029","https://openalex.org/W2361419701","https://openalex.org/W2487270267","https://openalex.org/W2379758706","https://openalex.org/W2047298552","https://openalex.org/W2184206019"],"abstract_inverted_index":{"In":[0],"the":[1,4,14,58,61],"eucaryotic":[2],"cell,":[3],"formation":[5],"of":[6,60,64],"disulfide":[7],"bonds":[8],"takes":[9],"place":[10],"in":[11,40],"general":[12],"inside":[13],"endoplasmic":[15],"reticulum":[16],"which":[17],"provides":[18],"a":[19],"unique":[20],"folding":[21],"environment.":[22],"The":[23],"DisulfideDB":[24],"database":[25],"gathers":[26],"information":[27,37,44],"about":[28],"this":[29,43],"biological":[30],"process":[31],"with":[32,45],"structural,":[33],"evolutionary":[34],"and":[35],"neighborhood":[36],"on":[38],"cysteines":[39],"proteins.":[41],"Mining":[42],"an":[46],"association":[47],"rule":[48],"discovery":[49],"program":[50],"permits":[51],"to":[52],"extract":[53],"some":[54],"strong":[55],"rules":[56],"for":[57],"prediction":[59],"disulfide-bonding":[62],"state":[63],"cysteines.":[65]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
