{"id":"https://openalex.org/W4416366597","doi":"https://doi.org/10.1109/tcbbio.2025.3634612","title":"Sequence to Location: Protein Subcellular Localization Driven by Deep Pretrained Language Model","display_name":"Sequence to Location: Protein Subcellular Localization Driven by Deep Pretrained Language Model","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W4416366597","doi":"https://doi.org/10.1109/tcbbio.2025.3634612","pmid":"https://pubmed.ncbi.nlm.nih.gov/41259184"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2025.3634612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3634612","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","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/A5100759703","display_name":"Chen Song","orcid":"https://orcid.org/0000-0003-2671-6229"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Song","raw_affiliation_strings":["Tianjin University of Science and Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-2671-6229","affiliations":[{"raw_affiliation_string":"Tianjin University of Science and Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063102094","display_name":"Shidong Wu","orcid":"https://orcid.org/0009-0004-5023-8815"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shidong Wu","raw_affiliation_strings":["Tianjin University of Science and Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0004-5023-8815","affiliations":[{"raw_affiliation_string":"Tianjin University of Science and Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiankun Zhang","orcid":"https://orcid.org/0000-0003-0431-8895"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiankun Zhang","raw_affiliation_strings":["Tianjin University of Science and Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0431-8895","affiliations":[{"raw_affiliation_string":"Tianjin University of Science and Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722830","display_name":"Mengyu Li","orcid":"https://orcid.org/0000-0001-9327-434X"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyu Li","raw_affiliation_strings":["Tianjin University of Science and Technology, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University of Science and Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455376","display_name":"Tao Li","orcid":"https://orcid.org/0000-0003-1697-8022"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Haihe Laboratory of Information Technology Application Innovation and Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1697-8022","affiliations":[{"raw_affiliation_string":"Haihe Laboratory of Information Technology Application Innovation and Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26805289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"1","first_page":"89","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9937000274658203,"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":0.9937000274658203,"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":0.0020000000949949026,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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":0.78329998254776},{"id":"https://openalex.org/keywords/protein-subcellular-localization-prediction","display_name":"Protein subcellular localization prediction","score":0.7432000041007996},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4864000082015991},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.47679999470710754},{"id":"https://openalex.org/keywords/cytoplasm","display_name":"Cytoplasm","score":0.4124999940395355},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.39329999685287476},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3610999882221222}],"concepts":[{"id":"https://openalex.org/C2776879804","wikidata":"https://www.wikidata.org/wiki/Q7630919","display_name":"Subcellular localization","level":3,"score":0.78329998254776},{"id":"https://openalex.org/C140051345","wikidata":"https://www.wikidata.org/wiki/Q7251501","display_name":"Protein subcellular localization prediction","level":3,"score":0.7432000041007996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6276999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.47679999470710754},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C190062978","wikidata":"https://www.wikidata.org/wiki/Q79899","display_name":"Cytoplasm","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C559089031","wikidata":"https://www.wikidata.org/wiki/Q658882","display_name":"Protein targeting","level":4,"score":0.32409998774528503},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C49805395","wikidata":"https://www.wikidata.org/wiki/Q910966","display_name":"Nuclear localization sequence","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27469998598098755},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.25429999828338623}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep 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":"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":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"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":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D013347","descriptor_name":"Subcellular Fractions","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"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}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbbio.2025.3634612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3634612","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41259184","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41259184","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":"IEEE transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1851926402","display_name":null,"funder_award_id":"62377036","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1982228765","https://openalex.org/W2103934447","https://openalex.org/W2108206279","https://openalex.org/W2120671490","https://openalex.org/W2158173168","https://openalex.org/W2730472814","https://openalex.org/W2735158968","https://openalex.org/W2800722856","https://openalex.org/W2900490197","https://openalex.org/W2946990319","https://openalex.org/W2949819099","https://openalex.org/W3027130957","https://openalex.org/W3129049721","https://openalex.org/W3177500196","https://openalex.org/W4205192056","https://openalex.org/W4225264859","https://openalex.org/W4236358448","https://openalex.org/W4242765109","https://openalex.org/W4296039106","https://openalex.org/W4327680967","https://openalex.org/W4378804467","https://openalex.org/W4390511508","https://openalex.org/W4392599850","https://openalex.org/W4393235963","https://openalex.org/W4400074196","https://openalex.org/W4401243288","https://openalex.org/W4401728757","https://openalex.org/W4401816084","https://openalex.org/W4401845440","https://openalex.org/W4404447386","https://openalex.org/W4406002713"],"related_works":[],"abstract_inverted_index":{"Proteins":[0],"serve":[1],"as":[2],"the":[3,58,95],"essential":[4],"executors":[5],"of":[6,77,159],"cellular":[7],"activities,":[8],"and":[9,30,74,119,130,162,175],"their":[10,27],"mislocalization":[11],"often":[12],"resulting":[13],"in":[14,146,157,172],"diverse":[15],"diseases.":[16],"Traditional":[17],"methods":[18,156],"for":[19,26,45,133],"determining":[20],"protein":[21,47,61,67,78,84],"subcellular":[22,48,135,151],"localization":[23,136],"are":[24],"noted":[25],"time-consuming,":[28],"labor-intensive,":[29],"complex":[31],"nature.":[32],"To":[33],"address":[34],"these":[35],"challenges,":[36],"this":[37],"study":[38],"introduces":[39],"SubLoc,":[40],"a":[41,82,102,114],"deep":[42,59],"learning-based":[43],"algorithm":[44],"predicting":[46],"localization.":[49],"The":[50],"methodology":[51],"comprises":[52],"three":[53],"key":[54],"steps:":[55],"Firstly,":[56],"leveraging":[57],"pretrained":[60],"language":[62],"model":[63,87],"ProtT5":[64],"to":[65,106,123],"derive":[66],"embedding":[68],"vectors,":[69],"thereby":[70],"capturing":[71],"intricate":[72],"patterns":[73],"biological":[75],"functionalities":[76],"sequences.":[79],"Secondly,":[80],"constructing":[81],"3D":[83],"structure":[85],"graph":[86,103],"using":[88],"amino":[89],"acid":[90],"residue":[91],"contact":[92],"relationships":[93],"within":[94],"sequence,":[96],"which":[97],"is":[98],"subsequently":[99],"processed":[100],"by":[101],"convolutional":[104],"network":[105],"effectively":[107],"manage":[108],"spatial":[109],"structural":[110,129],"information.":[111],"Lastly,":[112],"employing":[113],"bidirectional":[115],"gated":[116],"recurrent":[117],"unit":[118],"multi-head":[120],"attention":[121],"mechanism":[122],"analyze":[124],"sequence":[125,131],"features,":[126],"integrating":[127],"both":[128],"data":[132],"enhanced":[134],"prediction.":[137],"Experimental":[138],"results":[139,171],"demonstrate":[140],"that":[141],"SubLoc":[142,167],"exhibits":[143],"exceptional":[144],"performance":[145],"localizing":[147],"proteins":[148],"across":[149],"10":[150],"compartments,":[152],"outperforming":[153],"all":[154],"comparative":[155],"terms":[158],"precision,":[160],"recall,":[161],"MCC":[163],"average":[164],"values.":[165],"Notably,":[166],"achieves":[168],"particularly":[169],"notable":[170],"identifying":[173],"Cytoplasm":[174],"Mitochondrion":[176],"locations.":[177]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-19T00:00:00"}