{"id":"https://openalex.org/W2562883458","doi":"https://doi.org/10.1186/s12918-016-0352-6","title":"Identifying the missing proteins in human proteome by biological language model","display_name":"Identifying the missing proteins in human proteome by biological language model","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2562883458","doi":"https://doi.org/10.1186/s12918-016-0352-6","mag":"2562883458","pmid":"https://pubmed.ncbi.nlm.nih.gov/28155671"},"language":"en","primary_location":{"id":"doi:10.1186/s12918-016-0352-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12918-016-0352-6","pdf_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/s12918-016-0352-6","source":{"id":"https://openalex.org/S92363890","display_name":"BMC Systems Biology","issn_l":"1752-0509","issn":["1752-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Systems Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/s12918-016-0352-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100608345","display_name":"Qiwen Dong","orcid":"https://orcid.org/0000-0002-3166-0541"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiwen Dong","raw_affiliation_strings":["Institute for Data Science and Engineering, East China Normal University, Shanghai, 200062, People's Republic of China. qwdong@sei.ecnu.edu.cn","Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, 518055, People's Republic of China. qwdong@sei.ecnu.edu.cn","Institute for Data Science and Engineering, East China Normal University, Shanghai, People\u2019s Republic of China","Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Data Science and Engineering, East China Normal University, Shanghai, 200062, People's Republic of China. qwdong@sei.ecnu.edu.cn","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, 518055, People's Republic of China. qwdong@sei.ecnu.edu.cn","institution_ids":["https://openalex.org/I3131625388"]},{"raw_affiliation_string":"Institute for Data Science and Engineering, East China Normal University, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, People\u2019s Republic of China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437036","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-6170-4744"},"institutions":[{"id":"https://openalex.org/I4210152006","display_name":"Jilin Agricultural University","ror":"https://ror.org/05dmhhd41","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152006"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["College of Animal Science and technology, Jilin Agricultural University, Changchun, 130118, People's Republic of China","College of Animal Science and technology, Jilin Agricultural University, Changchun, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Animal Science and technology, Jilin Agricultural University, Changchun, 130118, People's Republic of China","institution_ids":["https://openalex.org/I4210152006"]},{"raw_affiliation_string":"College of Animal Science and technology, Jilin Agricultural University, Changchun, People\u2019s Republic of China","institution_ids":["https://openalex.org/I4210152006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362379","display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0003-4598-4202"},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["College of Engineering, Shanghai Ocean University, Shanghai, 201303, People's Republic of China. xliu@shou.edu.cn","College of Engineering, Shanghai Ocean University, Shanghai, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Shanghai Ocean University, Shanghai, 201303, People's Republic of China. xliu@shou.edu.cn","institution_ids":["https://openalex.org/I44675526"]},{"raw_affiliation_string":"College of Engineering, Shanghai Ocean University, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I44675526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100362379","https://openalex.org/A5100608345"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I3131625388","https://openalex.org/I44675526","https://openalex.org/I66867065"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":0.3207,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67656749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":"S4","first_page":"113","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8440999984741211,"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":0.8440999984741211,"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":0.035999998450279236,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.023099999874830246,"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/systems-biology","display_name":"Systems biology","score":0.7123291492462158},{"id":"https://openalex.org/keywords/human-proteome-project","display_name":"Human proteome project","score":0.67766273021698},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6544861793518066},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.6525111198425293},{"id":"https://openalex.org/keywords/biological-network","display_name":"Biological network","score":0.4768332540988922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4727899730205536},{"id":"https://openalex.org/keywords/human-biology","display_name":"Human biology","score":0.4253772497177124},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3682721257209778},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36057963967323303},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.34658709168434143},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3033473491668701},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11393311619758606},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0827186107635498}],"concepts":[{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.7123291492462158},{"id":"https://openalex.org/C94795543","wikidata":"https://www.wikidata.org/wiki/Q3813754","display_name":"Human proteome project","level":4,"score":0.67766273021698},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6544861793518066},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.6525111198425293},{"id":"https://openalex.org/C28225019","wikidata":"https://www.wikidata.org/wiki/Q4915005","display_name":"Biological network","level":2,"score":0.4768332540988922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4727899730205536},{"id":"https://openalex.org/C84084929","wikidata":"https://www.wikidata.org/wiki/Q339557","display_name":"Human biology","level":2,"score":0.4253772497177124},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3682721257209778},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36057963967323303},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.34658709168434143},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3033473491668701},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11393311619758606},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0827186107635498}],"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":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","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":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D042541","descriptor_name":"Intracellular Space","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D042541","descriptor_name":"Intracellular Space","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D042541","descriptor_name":"Intracellular Space","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1186/s12918-016-0352-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12918-016-0352-6","pdf_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/s12918-016-0352-6","source":{"id":"https://openalex.org/S92363890","display_name":"BMC Systems Biology","issn_l":"1752-0509","issn":["1752-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Systems Biology","raw_type":"journal-article"},{"id":"pmid:28155671","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28155671","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":"BMC systems biology","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:5259966","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5259966","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":"BMC Syst Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12918-016-0352-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12918-016-0352-6","pdf_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/s12918-016-0352-6","source":{"id":"https://openalex.org/S92363890","display_name":"BMC Systems Biology","issn_l":"1752-0509","issn":["1752-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Systems Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4044104431","display_name":null,"funder_award_id":"U1401256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4598902760","display_name":null,"funder_award_id":"2016 YFB1000905","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4932408243","display_name":null,"funder_award_id":"61402177","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6339712341","display_name":"\u57fa\u4e8e\u4eba\u7c7b\u86cb\u767d\u8d28\u7ec4\u7684\u7ed3\u6784\u548c\u529f\u80fd\u9884\u6d4b\u7814\u7a76","funder_award_id":"61672234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2562883458.pdf","grobid_xml":"https://content.openalex.org/works/W2562883458.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W652664929","https://openalex.org/W1494484168","https://openalex.org/W1518399713","https://openalex.org/W1972624882","https://openalex.org/W1977046142","https://openalex.org/W1987437192","https://openalex.org/W2009470087","https://openalex.org/W2017277794","https://openalex.org/W2031095666","https://openalex.org/W2037312364","https://openalex.org/W2049928819","https://openalex.org/W2056499061","https://openalex.org/W2058833671","https://openalex.org/W2060593022","https://openalex.org/W2060769471","https://openalex.org/W2069860553","https://openalex.org/W2070980386","https://openalex.org/W2074229758","https://openalex.org/W2074956188","https://openalex.org/W2080993908","https://openalex.org/W2085277871","https://openalex.org/W2086226889","https://openalex.org/W2092067718","https://openalex.org/W2098174226","https://openalex.org/W2102245393","https://openalex.org/W2104812418","https://openalex.org/W2117502874","https://openalex.org/W2121085676","https://openalex.org/W2123525093","https://openalex.org/W2127230663","https://openalex.org/W2133657429","https://openalex.org/W2136101247","https://openalex.org/W2146628513","https://openalex.org/W2148279834","https://openalex.org/W2153349010","https://openalex.org/W2161072217","https://openalex.org/W2161811833","https://openalex.org/W2165460636","https://openalex.org/W2170747616","https://openalex.org/W2398160319","https://openalex.org/W2739999456","https://openalex.org/W2792561556","https://openalex.org/W2915667579","https://openalex.org/W4210767115","https://openalex.org/W4302378679"],"related_works":["https://openalex.org/W3092794487","https://openalex.org/W2094752534","https://openalex.org/W2885268310","https://openalex.org/W2025055488","https://openalex.org/W2575115220","https://openalex.org/W2580329791","https://openalex.org/W2909412621","https://openalex.org/W3032536091","https://openalex.org/W2145037531","https://openalex.org/W1975345997"],"abstract_inverted_index":{"BACKGROUND:":[0],"With":[1],"the":[2,9,17,27,40,45,66,75,93,102,108,121,135,139,148,166,178,191,221],"rapid":[3],"development":[4],"of":[5,65,74,77,138,171,220],"high-throughput":[6],"sequencing":[7],"technology,":[8],"proteomics":[10],"research":[11],"becomes":[12,63],"a":[13,162],"trendy":[14],"field":[15,115],"in":[16,49,68,127,196],"post":[18],"genomics":[19],"era.":[20],"It":[21],"is":[22],"necessary":[23],"to":[24,56,91,119,155,233],"identify":[25],"all":[26],"native-encoding":[28],"protein":[29],"sequences":[30,104],"for":[31],"further":[32],"function":[33,170],"and":[34,105,169,175,218],"pathway":[35],"analysis.":[36],"Toward":[37],"that":[38,190,210],"end,":[39],"Human":[41,46,69],"Proteome":[42,70],"Organization":[43],"lunched":[44],"Protein":[47],"Project":[48],"2011.":[50],"However":[51],"many":[52],"proteins":[53,81,133,145,174,181,212,217,223,229],"are":[54,99,143,195,224,231],"hard":[55,232],"be":[57,156,214,234],"detected":[58,235],"by":[59,82,147,202,236],"experiment":[60,237],"methods,":[61],"which":[62,151,230],"one":[64],"bottleneck":[67],"Project.":[71],"In":[72],"consideration":[73],"complicatedness":[76],"detecting":[78],"these":[79,172],"missing":[80,94,122,132,173,222],"using":[83],"wet-experiment":[84],"approach,":[85],"here":[86,194],"we":[87],"use":[88],"bioinformatics":[89],"method":[90],"pre-filter":[92],"proteins.":[95,123,159],"RESULTS:":[96],"Since":[97],"there":[98],"analogy":[100],"between":[101],"biological":[103],"natural":[106],"language,":[107],"n-gram":[109,149],"models":[110],"from":[111,134],"Natural":[112],"Language":[113],"Processing":[114],"has":[116],"been":[117],"used":[118,126],"filter":[120],"The":[124,187,207],"dataset":[125],"this":[128],"study":[129],"contains":[130],"616":[131],"\"uncertain\"":[136],"category":[137],"neXtProt":[140],"database.":[141],"There":[142],"102":[144,211],"deduced":[146],"model,":[150],"have":[152],"high":[153,179],"probability":[154,180],"native":[157,215],"human":[158],"We":[160],"perform":[161],"detail":[163],"analysis":[164,208],"on":[165],"predicted":[167],"structure":[168],"also":[176],"compare":[177],"with":[182,199],"other":[183,203],"mass":[184],"spectrum":[185],"datasets.":[186],"evaluation":[188],"shows":[189,209],"results":[192],"reported":[193],"good":[197],"agreement":[198],"those":[200],"obtained":[201],"well-established":[204],"databases.":[205],"CONCLUSION:":[206],"may":[213],"gene-coding":[216],"some":[219],"membrane":[225],"or":[226],"natively":[227],"disordered":[228],"methods.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
