{"id":"https://openalex.org/W2076578973","doi":"https://doi.org/10.1142/s0219720006002405","title":"PROTEIN SUBCELLULAR LOCALIZATION BASED ON PSI-BLAST AND MACHINE LEARNING","display_name":"PROTEIN SUBCELLULAR LOCALIZATION BASED ON PSI-BLAST AND MACHINE LEARNING","publication_year":2006,"publication_date":"2006-12-01","ids":{"openalex":"https://openalex.org/W2076578973","doi":"https://doi.org/10.1142/s0219720006002405","mag":"2076578973","pmid":"https://pubmed.ncbi.nlm.nih.gov/17245809"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720006002405","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720006002405","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/A5100607720","display_name":"Jian Guo","orcid":"https://orcid.org/0000-0002-9530-8440"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JIAN GUO","raw_affiliation_strings":["Laboratory of Statistical Computation, Department of Mathematical Sciences, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Statistical Computation, Department of Mathematical Sciences, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046044404","display_name":"Xian Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"XIAN PU","raw_affiliation_strings":["Department of Computer Science, The City University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100843509","display_name":"Yuanlie Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YUANLIE LIN","raw_affiliation_strings":["Laboratory of Statistical Computation, Department of Mathematical Sciences, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Statistical Computation, Department of Mathematical Sciences, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001617092","display_name":"Howard Leung","orcid":"https://orcid.org/0000-0002-2633-2965"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"HOWARD LEUNG","raw_affiliation_strings":["Department of Computer Science, The City University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4052,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.61542852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"04","issue":"06","first_page":"1181","last_page":"1195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987000226974487,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9962999820709229,"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/subcellular-localization","display_name":"Subcellular localization","score":0.8144571185112},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6319053173065186},{"id":"https://openalex.org/keywords/protein-subcellular-localization-prediction","display_name":"Protein subcellular localization prediction","score":0.6129630208015442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.562168538570404},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5402538180351257},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4895997643470764},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.48755496740341187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4619256854057312},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.45897239446640015},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45664259791374207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39653682708740234},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.38123148679733276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3728938102722168},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.3609400987625122},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.22703039646148682},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22232285141944885}],"concepts":[{"id":"https://openalex.org/C2776879804","wikidata":"https://www.wikidata.org/wiki/Q7630919","display_name":"Subcellular localization","level":3,"score":0.8144571185112},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6319053173065186},{"id":"https://openalex.org/C140051345","wikidata":"https://www.wikidata.org/wiki/Q7251501","display_name":"Protein subcellular localization prediction","level":3,"score":0.6129630208015442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562168538570404},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5402538180351257},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4895997643470764},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.48755496740341187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4619256854057312},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.45897239446640015},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45664259791374207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39653682708740234},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38123148679733276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3728938102722168},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3609400987625122},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.22703039646148682},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22232285141944885},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D013347","descriptor_name":"Subcellular Fractions","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D013347","descriptor_name":"Subcellular Fractions","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D013347","descriptor_name":"Subcellular Fractions","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":2,"locations":[{"id":"doi:10.1142/s0219720006002405","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720006002405","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:17245809","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17245809","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W149741886","https://openalex.org/W326552434","https://openalex.org/W1480577415","https://openalex.org/W1491250132","https://openalex.org/W1526754730","https://openalex.org/W1919783154","https://openalex.org/W1964168965","https://openalex.org/W1970068990","https://openalex.org/W1978136924","https://openalex.org/W1978736122","https://openalex.org/W1979228662","https://openalex.org/W1992577925","https://openalex.org/W1993711987","https://openalex.org/W1997996819","https://openalex.org/W2008895011","https://openalex.org/W2009703007","https://openalex.org/W2010877280","https://openalex.org/W2020194549","https://openalex.org/W2021357636","https://openalex.org/W2025131366","https://openalex.org/W2033588290","https://openalex.org/W2049023560","https://openalex.org/W2050913696","https://openalex.org/W2053427692","https://openalex.org/W2053963319","https://openalex.org/W2054068479","https://openalex.org/W2054342685","https://openalex.org/W2063088204","https://openalex.org/W2064450641","https://openalex.org/W2066363861","https://openalex.org/W2082605863","https://openalex.org/W2085022192","https://openalex.org/W2094931538","https://openalex.org/W2100851422","https://openalex.org/W2109553965","https://openalex.org/W2110659301","https://openalex.org/W2117919289","https://openalex.org/W2118020555","https://openalex.org/W2119452210","https://openalex.org/W2119677615","https://openalex.org/W2120026469","https://openalex.org/W2135322638","https://openalex.org/W2136930152","https://openalex.org/W2137920018","https://openalex.org/W2145036462","https://openalex.org/W2145957695","https://openalex.org/W2148622452","https://openalex.org/W2148853951","https://openalex.org/W2152458080","https://openalex.org/W2154202919","https://openalex.org/W2155755608","https://openalex.org/W2158714788","https://openalex.org/W2160072419","https://openalex.org/W2160979370","https://openalex.org/W2161257366","https://openalex.org/W2170700642"],"related_works":["https://openalex.org/W2351398203","https://openalex.org/W4205775722","https://openalex.org/W4366498163","https://openalex.org/W2402975874","https://openalex.org/W2384110740","https://openalex.org/W2389499846","https://openalex.org/W2374123826","https://openalex.org/W2128345772","https://openalex.org/W256932276","https://openalex.org/W2144244209"],"abstract_inverted_index":{"Subcellular":[0],"location":[1],"is":[2,20,60,68],"an":[3],"important":[4],"functional":[5],"annotation":[6],"of":[7,55,80,86,108,138],"proteins.":[8],"An":[9],"automatic,":[10],"reliable":[11],"and":[12,66,83,94,114],"efficient":[13],"prediction":[14,118,136],"system":[15],"for":[16,22],"protein":[17,30,38,47,51],"subcellular":[18,31],"localization":[19,32],"necessary":[21],"large-scale":[23],"genome":[24],"analysis.":[25],"This":[26],"paper":[27],"describes":[28],"a":[29,50],"method":[33,111,124,141],"which":[34],"extracts":[35],"features":[36],"from":[37,42],"profiles":[39],"rather":[40],"than":[41,71,127],"amino":[43,73,77,132],"acid":[44,74,78,133],"sequences.":[45,134],"The":[46,76,117,135],"profile":[48,82,88],"represents":[49],"family,":[52],"discards":[53],"part":[54],"the":[56,64,72,84,87,96,105,109,122,139],"sequence":[57],"information":[58],"that":[59,121],"not":[61],"conserved":[62],"throughout":[63],"family":[65],"therefore":[67],"more":[69],"sensitive":[70],"sequence.":[75],"compositions":[79],"whole":[81],"N-terminus":[85],"are":[89,142],"extracted,":[90],"respectively,":[91],"to":[92],"train":[93],"test":[95],"probabilistic":[97],"neural":[98],"network":[99],"classifiers.":[100],"On":[101],"two":[102,148],"benchmark":[103],"datasets,":[104],"overall":[106],"accuracies":[107],"proposed":[110,123,140],"reach":[112],"89.1%":[113],"68.9%,":[115],"respectively.":[116],"results":[119,137],"show":[120],"perform":[125],"better":[126],"those":[128],"methods":[129],"based":[130],"on":[131,147],"also":[143],"compared":[144],"with":[145],"Subloc":[146],"redundance-reduced":[149],"datasets.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}