{"id":"https://openalex.org/W4205272967","doi":"https://doi.org/10.1109/bibm52615.2021.9669606","title":"Improving human essential protein prediction using only protein sequences via ensemble learning","display_name":"Improving human essential protein prediction using only protein sequences via ensemble learning","publication_year":2021,"publication_date":"2021-12-09","ids":{"openalex":"https://openalex.org/W4205272967","doi":"https://doi.org/10.1109/bibm52615.2021.9669606"},"language":"en","primary_location":{"id":"doi:10.1109/bibm52615.2021.9669606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669606","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5033885404","display_name":"Min Zeng","orcid":"https://orcid.org/0000-0002-1726-0955"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zeng","raw_affiliation_strings":["Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744019","display_name":"Nian Wang","orcid":"https://orcid.org/0000-0002-8303-0365"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nian Wang","raw_affiliation_strings":["Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114948870","display_name":"Yifan Wu","orcid":"https://orcid.org/0009-0005-3029-2408"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wu","raw_affiliation_strings":["Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346366","display_name":"Yiming Li","orcid":"https://orcid.org/0000-0003-4602-3905"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Li","raw_affiliation_strings":["Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091157395","display_name":"Fang\u2010Xiang Wu","orcid":"https://orcid.org/0000-0002-4593-9332"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fang-Xiang Wu","raw_affiliation_strings":["Department of Computer Science, Department of Mechanical Engineering, Division of Biomedical Engineering, University of Saskatchewan, Saskatoon, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Department of Mechanical Engineering, Division of Biomedical Engineering, University of Saskatchewan, Saskatoon, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100719013","display_name":"Min Li","orcid":"https://orcid.org/0000-0002-0188-1394"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":["Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"103"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9991000294685364,"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":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.7976119518280029},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.6047384142875671},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5763272643089294},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5680147409439087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5670319199562073},{"id":"https://openalex.org/keywords/centrality","display_name":"Centrality","score":0.517839252948761},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4106401801109314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07527965307235718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976119518280029},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6047384142875671},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5763272643089294},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5680147409439087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5670319199562073},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.517839252948761},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4106401801109314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07527965307235718},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm52615.2021.9669606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669606","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":30,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1709660540","https://openalex.org/W1714524773","https://openalex.org/W1934704664","https://openalex.org/W2005740247","https://openalex.org/W2038681300","https://openalex.org/W2048386825","https://openalex.org/W2060816398","https://openalex.org/W2091185605","https://openalex.org/W2094934530","https://openalex.org/W2097606916","https://openalex.org/W2113140044","https://openalex.org/W2118978333","https://openalex.org/W2130790725","https://openalex.org/W2146447390","https://openalex.org/W2174686320","https://openalex.org/W2180291937","https://openalex.org/W2563010899","https://openalex.org/W2790765877","https://openalex.org/W2911960890","https://openalex.org/W2912802963","https://openalex.org/W2915554882","https://openalex.org/W2935275081","https://openalex.org/W2949280944","https://openalex.org/W2971405760","https://openalex.org/W2991321419","https://openalex.org/W3008847215","https://openalex.org/W3060351484","https://openalex.org/W3087747512","https://openalex.org/W3177371828"],"related_works":["https://openalex.org/W3082059448","https://openalex.org/W2905156999","https://openalex.org/W4229460275","https://openalex.org/W4313640622","https://openalex.org/W4296079469","https://openalex.org/W1987518466","https://openalex.org/W3135046080","https://openalex.org/W3023033471","https://openalex.org/W4376643315","https://openalex.org/W4324137541"],"abstract_inverted_index":{"Accurate":[0],"prediction":[1,63,87],"of":[2,14,31,64,84,114],"essential":[3,65,85],"proteins":[4,66],"by":[5,67,88],"using":[6,68,89],"computational":[7,18],"methods":[8,19,58,130],"can":[9,140],"effectively":[10],"reduce":[11,111],"the":[12,82,112],"cost":[13],"wet-lab":[15],"experiments.":[16],"Existing":[17],"usually":[20],"rely":[21],"on":[22],"constructed":[23],"protein-protein":[24],"interaction":[25],"(PPI)":[26],"networks":[27,37],"with":[28],"different":[29],"kinds":[30],"biological":[32,40],"data.":[33],"However,":[34],"high-quality":[35],"PPI":[36],"and":[38,53,61,131,138],"other":[39],"data":[41],"are":[42],"not":[43],"available":[44],"for":[45,59],"all":[46],"proteins.":[47],"Thus,":[48],"it":[49],"is":[50],"very":[51],"necessary":[52],"valuable":[54],"to":[55,80,110],"develop":[56],"accurate":[57],"fast":[60],"effective":[62],"only":[69,90],"protein":[70,86,91],"sequences.":[71,92],"We":[72],"propose":[73],"EPGBDT,":[74],"a":[75,119],"machine":[76],"learning":[77],"ensemble":[78,96],"model,":[79],"improve":[81],"performance":[83],"EP-GBDT":[93,117,126],"has":[94],"an":[95],"structure":[97],"that":[98,125],"combines":[99],"multiple":[100],"Gradient":[101],"Boosting":[102],"Decision":[103],"Tree":[104],"(GBDT)":[105],"base":[106],"classifiers.":[107],"In":[108],"addition,":[109],"effects":[113],"imbalanced":[115],"dataset,":[116],"uses":[118],"sampling":[120],"technique.":[121],"The":[122,135],"results":[123],"show":[124],"outperforms":[127],"state-of-the-art":[128],"sequence-based":[129],"network-based":[132],"centrality":[133],"measures.":[134],"source":[136],"code":[137],"datasets":[139],"be":[141],"downloaded":[142],"from":[143],"https://github.com/CSUBioGroup/EP-GBDT.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}