{"id":"https://openalex.org/W2771582859","doi":"https://doi.org/10.1109/bibm.2017.8217622","title":"DeepText2Go: Improving large-scale protein function prediction with deep semantic text representation","display_name":"DeepText2Go: Improving large-scale protein function prediction with deep semantic text representation","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2771582859","doi":"https://doi.org/10.1109/bibm.2017.8217622","mag":"2771582859"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2017.8217622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2017.8217622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5015677036","display_name":"Ronghui You","orcid":"https://orcid.org/0000-0002-7608-4867"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghui You","raw_affiliation_strings":["School of Computer Science and Shanghai Key Lab of Intelligent Information Processing, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Shanghai Key Lab of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045866167","display_name":"Shanfeng Zhu","orcid":"https://orcid.org/0000-0002-6067-5312"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanfeng Zhu","raw_affiliation_strings":["Center for Computational System Biology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational System Biology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9973999857902527,"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":0.9966999888420105,"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/uniprot","display_name":"UniProt","score":0.9198616743087769},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.719199538230896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7163934111595154},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5924261808395386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5527281165122986},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5355111956596375},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5343766808509827},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.533139705657959},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4879459738731384},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.44702035188674927},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4303871989250183},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3862910568714142},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36954236030578613},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.24121680855751038},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15829989314079285},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09150093793869019},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06805410981178284}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.9198616743087769},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.719199538230896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163934111595154},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5924261808395386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5527281165122986},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5355111956596375},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5343766808509827},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.533139705657959},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4879459738731384},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.44702035188674927},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4303871989250183},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3862910568714142},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36954236030578613},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.24121680855751038},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15829989314079285},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09150093793869019},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06805410981178284},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2017.8217622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2017.8217622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":28,"referenced_works":["https://openalex.org/W1504124766","https://openalex.org/W1663797894","https://openalex.org/W1872414266","https://openalex.org/W1982088273","https://openalex.org/W2041187413","https://openalex.org/W2102814386","https://openalex.org/W2103017472","https://openalex.org/W2106093878","https://openalex.org/W2108984616","https://openalex.org/W2117486996","https://openalex.org/W2118585731","https://openalex.org/W2127119915","https://openalex.org/W2131744502","https://openalex.org/W2138842411","https://openalex.org/W2139294595","https://openalex.org/W2153579005","https://openalex.org/W2161955763","https://openalex.org/W2164620224","https://openalex.org/W2167289895","https://openalex.org/W2227395312","https://openalex.org/W2428528690","https://openalex.org/W2535702297","https://openalex.org/W2739999456","https://openalex.org/W4234797890","https://openalex.org/W4294170691","https://openalex.org/W6677656871","https://openalex.org/W6679775712","https://openalex.org/W6682691769"],"related_works":["https://openalex.org/W2102027645","https://openalex.org/W2107785922","https://openalex.org/W2035528219","https://openalex.org/W2402478170","https://openalex.org/W2952660917","https://openalex.org/W1818938668","https://openalex.org/W2730472814","https://openalex.org/W2159663778","https://openalex.org/W2065993463","https://openalex.org/W2181899571"],"abstract_inverted_index":{"UniProtKB":[0],"has":[1],"collected":[2],"more":[3],"than":[4,13,70],"88":[5],"million":[6],"protein":[7,30,44],"sequences":[8],"by":[9,98],"July":[10],"2017.":[11],"Less":[12],"0.2%":[14],"of":[15,43,80],"these":[16],"proteins,":[17],"however,":[18],"have":[19,127],"added":[20],"experimental":[21],"GO":[22],"annotations.":[23],"To":[24],"reduce":[25],"this":[26],"huge":[27],"gap,":[28],"automatic":[29],"function":[31],"prediction":[32],"(AFP)":[33],"becomes":[34],"increasingly":[35],"important.":[36],"Results":[37],"on":[38,120],"CAFA":[39],"(the":[40],"Critical":[41],"Assessment":[42],"Function":[45],"Annotation":[46],"algorithms)":[47],"benchmark":[48,122],"demonstrates":[49],"that":[50,129],"sequence":[51,71,111,136],"homology":[52],"based":[53],"methods":[54,113],"are":[55],"highly":[56],"competitive":[57],"in":[58,83],"AFP.":[59,73],"One":[60],"imperative":[61],"issues":[62],"will":[63],"be":[64],"incorporating":[65],"other":[66,69],"information":[67],"sources":[68],"for":[72],"In":[74],"contrast":[75],"to":[76,94],"using":[77,99],"BOW":[78],"(bag":[79],"words)":[81],"representation":[82,103],"traditional":[84],"text-based":[85,109,134],"AFP,":[86],"we":[87],"proposed":[88],"a":[89,115],"new":[90],"method":[91],"called":[92],"DeepText2GO":[93,106,130],"improve":[95],"large-scale":[96],"AFP":[97],"deep":[100],"semantic":[101],"text":[102],"instead.":[104],"Furthermore,":[105],"integrates":[107],"both":[108,133],"and":[110,135],"homology-based":[112,137],"through":[114],"consensus":[116],"approach.":[117],"Extensive":[118],"experiments":[119],"the":[121],"dataset":[123],"extracted":[124],"from":[125],"UniProt/SwissProt":[126],"demonstrated":[128],"significantly":[131],"outperformed":[132],"methods,":[138],"validating":[139],"its":[140],"superiority.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}