{"id":"https://openalex.org/W4404470858","doi":"https://doi.org/10.1145/3674658.3674674","title":"ESM-MHC: An Improved Predictor of MHC Using ESM Protein Language Model","display_name":"ESM-MHC: An Improved Predictor of MHC Using ESM Protein Language Model","publication_year":2024,"publication_date":"2024-05-24","ids":{"openalex":"https://openalex.org/W4404470858","doi":"https://doi.org/10.1145/3674658.3674674"},"language":"en","primary_location":{"id":"doi:10.1145/3674658.3674674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674658.3674674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Bioinformatics and Biomedical Technology","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Junjie Cai","orcid":"https://orcid.org/0009-0007-4693-6137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Cai","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0007-4693-6137","affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014460623","display_name":"Y. B. Li","orcid":"https://orcid.org/0000-0002-7175-5238"},"institutions":[{"id":"https://openalex.org/I4210123686","display_name":"Quzhou University","ror":"https://ror.org/024nfx323","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210123686"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjuan Li","raw_affiliation_strings":["College of Electrical and Information Engineering, Qu Zhou University, Quzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-7175-5238","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Qu Zhou University, Quzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123686"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100319437","display_name":"Dong Chen","orcid":"https://orcid.org/0000-0001-5922-8374"},"institutions":[{"id":"https://openalex.org/I4210123686","display_name":"Quzhou University","ror":"https://ror.org/024nfx323","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210123686"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Chen","raw_affiliation_strings":["College of Electrical and Information Engineering, Qu Zhou University, Quzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-5922-8374","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Qu Zhou University, Quzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123686"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":0.668,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70413657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"88","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9980999827384949,"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":0.9961000084877014,"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/major-histocompatibility-complex","display_name":"Major histocompatibility complex","score":0.5979997515678406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.596153736114502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35517358779907227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32852062582969666},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.11734423041343689},{"id":"https://openalex.org/keywords/antigen","display_name":"Antigen","score":0.08138203620910645},{"id":"https://openalex.org/keywords/immunology","display_name":"Immunology","score":0.07983717322349548}],"concepts":[{"id":"https://openalex.org/C207936829","wikidata":"https://www.wikidata.org/wiki/Q423163","display_name":"Major histocompatibility complex","level":3,"score":0.5979997515678406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.596153736114502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35517358779907227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32852062582969666},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11734423041343689},{"id":"https://openalex.org/C147483822","wikidata":"https://www.wikidata.org/wiki/Q103537","display_name":"Antigen","level":2,"score":0.08138203620910645},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.07983717322349548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674658.3674674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674658.3674674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Bioinformatics and Biomedical Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2157752701","https://openalex.org/W2170747616","https://openalex.org/W2274610632","https://openalex.org/W2900499839","https://openalex.org/W2923082472","https://openalex.org/W3192823273","https://openalex.org/W4205309242","https://openalex.org/W4211246989","https://openalex.org/W4212965593","https://openalex.org/W4224314929","https://openalex.org/W4225758372","https://openalex.org/W4283516025","https://openalex.org/W4295765292","https://openalex.org/W4313331036","https://openalex.org/W4317931114","https://openalex.org/W4366606495","https://openalex.org/W4385737488","https://openalex.org/W4385741267","https://openalex.org/W4388621595","https://openalex.org/W6682489755"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,129],"major":[1],"histocompatibility":[2],"complex":[3],"(MHC)":[4],"comprises":[5],"a":[6,55],"set":[7,123],"of":[8,29,80,134,151],"genes":[9],"located":[10],"on":[11,119],"chromosome":[12,17],"6":[13],"in":[14,19,24,35,48,77,138,149],"humans":[15],"and":[16,32,94,105,136,142],"17":[18],"mice.":[20],"It":[21],"is":[22,42],"instrumental":[23],"autoimmune":[25],"diseases,":[26],"the":[27,65,78,96,109,120,126,139],"success":[28],"organ":[30],"transplants,":[31],"antigen":[33],"presentation":[34],"tumor":[36],"immunotherapy.":[37],"Therefore,":[38],"accurately":[39],"identifying":[40],"MHC":[41],"essential":[43],"for":[44,59],"understanding":[45],"its":[46],"role":[47],"immunology.":[49],"In":[50],"this":[51],"study,":[52],"we":[53],"proposed":[54],"machine":[56],"learning-based":[57],"model":[58,69,130],"predicting":[60],"MHC,":[61],"called":[62],"ESM-MHC.":[63],"Firstly,":[64],"ESM":[66],"protein":[67,74],"language":[68],"was":[70,88,117],"employed":[71,89],"to":[72,90,124],"characterize":[73],"sequences,":[75],"resulting":[76],"generation":[79],"1280-dimensional":[81],"features.":[82],"Secondly,":[83],"principal":[84],"component":[85],"analysis":[86],"(PCA)":[87],"analyze":[91],"these":[92],"features":[93,97],"select":[95],"that":[98],"showed":[99],"notably":[100],"different":[101],"distributions":[102],"between":[103],"positive":[104],"negative":[106],"samples":[107],"as":[108],"final":[110,121],"feature":[111,122],"set.":[112],"Finally,":[113],"Multi-Layer":[114],"Perceptron":[115],"(MLP)":[116],"trained":[118],"obtain":[125],"identification":[127],"model.":[128],"achieved":[131],"an":[132],"accuracy":[133],"95.97%":[135],"96%":[137],"10-fold":[140],"cross-validation":[141],"test":[143],"set,":[144],"respectively,":[145],"outperforming":[146],"existing":[147],"methods":[148],"terms":[150],"performance.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}