{"id":"https://openalex.org/W7214918752","doi":"https://doi.org/10.3389/fimmu.2026.1918918","title":"Characterization and clustering of immunocompetent proteins based on ESM-2 sequence embedding and physicochemical feature fusion","display_name":"Characterization and clustering of immunocompetent proteins based on ESM-2 sequence embedding and physicochemical feature fusion","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7214918752","doi":"https://doi.org/10.3389/fimmu.2026.1918918","pmid":"https://pubmed.ncbi.nlm.nih.gov/42876657","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13661372"},"language":"en","primary_location":{"id":"doi:10.3389/fimmu.2026.1918918","doi":"https://doi.org/10.3389/fimmu.2026.1918918","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fimmu.2026.1918918","pdf_url":"https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2026.1918918/pdf","source":{"id":"https://openalex.org/S2595292759","display_name":"Frontiers in Immunology","issn_l":"1664-3224","issn":["1664-3224"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Immunology","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2026.1918918/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5149732873","display_name":"Xingxing Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I166427055","display_name":"Xinjiang Agricultural University","ror":"https://ror.org/04qjh2h11","country_code":"CN","type":"education","lineage":["https://openalex.org/I166427055"]},{"id":"https://openalex.org/I4405270164","display_name":"Xinjiang Second Medical College","ror":"https://ror.org/005vn6s32","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405270164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxing Liu","raw_affiliation_strings":["Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University","School of Xinjiang Second Medical College, Xinjiang"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University","institution_ids":["https://openalex.org/I166427055"]},{"raw_affiliation_string":"School of Xinjiang Second Medical College, Xinjiang","institution_ids":["https://openalex.org/I4405270164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153627898","display_name":"Rui Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270164","display_name":"Xinjiang Second Medical College","ror":"https://ror.org/005vn6s32","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405270164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["School of Xinjiang Second Medical College, Xinjiang"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Xinjiang Second Medical College, Xinjiang","institution_ids":["https://openalex.org/I4405270164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153642880","display_name":"Jie Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270164","display_name":"Xinjiang Second Medical College","ror":"https://ror.org/005vn6s32","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405270164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["School of Xinjiang Second Medical College, Xinjiang"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Xinjiang Second Medical College, Xinjiang","institution_ids":["https://openalex.org/I4405270164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012101473","display_name":"ZHANG Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270164","display_name":"Xinjiang Second Medical College","ror":"https://ror.org/005vn6s32","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405270164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["School of Xinjiang Second Medical College, Xinjiang"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Xinjiang Second Medical College, Xinjiang","institution_ids":["https://openalex.org/I4405270164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145505447","display_name":"\u4edd\u76fc\u76fc","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I166427055","display_name":"Xinjiang Agricultural University","ror":"https://ror.org/04qjh2h11","country_code":"CN","type":"education","lineage":["https://openalex.org/I166427055"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Panpan Tong","raw_affiliation_strings":["Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University","institution_ids":["https://openalex.org/I166427055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153556315","display_name":"Jinxin Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I166427055","display_name":"Xinjiang Agricultural University","ror":"https://ror.org/04qjh2h11","country_code":"CN","type":"education","lineage":["https://openalex.org/I166427055"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxin Xie","raw_affiliation_strings":["Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University","institution_ids":["https://openalex.org/I166427055"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5145505447"],"corresponding_institution_ids":["https://openalex.org/I166427055"],"apc_list":{"value":3150,"currency":"CHF","value_usd":3801},"apc_paid":{"value":3150,"currency":"CHF","value_usd":3801},"fwci":1.5377,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87337601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":95},"biblio":{"volume":"17","issue":null,"first_page":"1918918","last_page":"1918918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.7153000235557556,"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":0.7153000235557556,"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":0.10040000081062317,"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/T11103","display_name":"Antimicrobial Peptides and Activities","score":0.07289999723434448,"subfield":{"id":"https://openalex.org/subfields/2404","display_name":"Microbiology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-family-clustering","display_name":"protein family clustering","score":0.5820000171661377},{"id":"https://openalex.org/keywords/convergent-evolution","display_name":"convergent evolution","score":0.7929999828338623},{"id":"https://openalex.org/keywords/mosquito-salivary-proteins","display_name":"mosquito salivary proteins","score":0.8330000042915344},{"id":"https://openalex.org/keywords/house-dust-mite-allergens","display_name":"house dust mite allergens","score":0.9850000143051147},{"id":"https://openalex.org/keywords/cathelicidin","display_name":"cathelicidin","score":0.9100000262260437},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.5249999761581421},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.6060000061988831}],"concepts":[{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6330000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004999876022339},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5734000205993652},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.559499979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4609000086784363},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3903000056743622},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.353300005197525},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2777379352","wikidata":"https://www.wikidata.org/wiki/Q24739493","display_name":"Cathelicidin","level":4,"score":0.33869999647140503},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3228999972343445},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.30390000343322754},{"id":"https://openalex.org/C20299238","wikidata":"https://www.wikidata.org/wiki/Q363928","display_name":"Lipocalin","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2776134702","wikidata":"https://www.wikidata.org/wiki/Q1360","display_name":"Arthropod","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2526000142097473},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.25220000743865967},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.25060001015663147},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2502000033855438}],"mesh":[{"descriptor_ui":"D000098430","descriptor_name":"Clustering Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D054834","descriptor_name":"Lipocalins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060829","descriptor_name":"Arthropod Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D060829","descriptor_name":"Arthropod Proteins","qualifier_ui":"Q000276","qualifier_name":"immunology","is_major_topic":true},{"descriptor_ui":"D060829","descriptor_name":"Arthropod Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.3389/fimmu.2026.1918918","doi":"https://doi.org/10.3389/fimmu.2026.1918918","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fimmu.2026.1918918","pdf_url":"https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2026.1918918/pdf","source":{"id":"https://openalex.org/S2595292759","display_name":"Frontiers in Immunology","issn_l":"1664-3224","issn":["1664-3224"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Immunology","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13661372","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13661372/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13661372/pdf/fimmu-17-1918918.pdf","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Front Immunol","raw_type":"Text"},{"id":"pmid:42876657","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42876657","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,"listed_in":[],"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":"Frontiers in immunology","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:d0534792c65b4b129cceb4e43cac670b","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/d0534792c65b4b129cceb4e43cac670b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Immunology, Vol 17 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fimmu.2026.1918918","doi":"https://doi.org/10.3389/fimmu.2026.1918918","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fimmu.2026.1918918","pdf_url":"https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2026.1918918/pdf","source":{"id":"https://openalex.org/S2595292759","display_name":"Frontiers in Immunology","issn_l":"1664-3224","issn":["1664-3224"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Immunology","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328898","display_name":"Natural Science Foundation of Xinjiang","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214918752.pdf","grobid_xml":"https://content.openalex.org/works/W7214918752.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1951660422","https://openalex.org/W2131075173","https://openalex.org/W2147962977","https://openalex.org/W2265800909","https://openalex.org/W2514745723","https://openalex.org/W2518955480","https://openalex.org/W2770117063","https://openalex.org/W2896138651","https://openalex.org/W2922882614","https://openalex.org/W2977440864","https://openalex.org/W3016468256","https://openalex.org/W3087977202","https://openalex.org/W4220864432","https://openalex.org/W4224627781","https://openalex.org/W4288066876","https://openalex.org/W4307657653","https://openalex.org/W4316363330","https://openalex.org/W4321503094","https://openalex.org/W4388128323","https://openalex.org/W4390793633","https://openalex.org/W4391045808","https://openalex.org/W4391563878","https://openalex.org/W4396513997","https://openalex.org/W4400083372","https://openalex.org/W4405837413","https://openalex.org/W4406692153","https://openalex.org/W4409197174","https://openalex.org/W4410343785","https://openalex.org/W4412658145","https://openalex.org/W4414427187","https://openalex.org/W4414428129","https://openalex.org/W4414468172","https://openalex.org/W4415845451","https://openalex.org/W4416047368","https://openalex.org/W4416202126","https://openalex.org/W7119483463","https://openalex.org/W7126175224","https://openalex.org/W7127198527","https://openalex.org/W7162207661"],"related_works":["https://openalex.org/W7221654065","https://openalex.org/W184018770","https://openalex.org/W4211008914","https://openalex.org/W2094089396","https://openalex.org/W613568531","https://openalex.org/W2611907773","https://openalex.org/W2090557416","https://openalex.org/W4362677363","https://openalex.org/W7100789859","https://openalex.org/W4316363330"],"abstract_inverted_index":{"Objective:":[0],"Traditional":[1],"sequence-comparison":[2],"methods":[3],"face":[4],"challenges":[5],"when":[6],"classifying":[7],"and":[8,37,53,91,110,122,155,180,221,267,271,278,301,312,324,347],"identifying":[9],"low-homology":[10,305],"proteins":[11,79],"formed":[12,97],"by":[13],"convergent":[14],"evolution.":[15],"In":[16],"this":[17],"exploratory":[18,276,342],"study,":[19],"we":[20,135],"built":[21],"a":[22,169,194,224,245,337],"PCA-based":[23,178],"unsupervised":[24],"clustering":[25,179,256,281],"workflow":[26,42,282],"combining":[27],"high-dimensional":[28],"embeddings":[29],"from":[30,249],"the":[31,129,186,190,209,215,219,229,241,250,262,268,313],"frozen":[32,145],"pre-trained":[33,146],"protein-language":[34],"model":[35,143],"ESM-2":[36,141],"weighted-fused":[38],"physicochemical":[39,154],"features.":[40],"The":[41,140,204,235,254],"was":[43,65,165],"explored":[44],"for":[45,287,341,351],"family-level":[46,293],"grouping,":[47],"identification":[48],"of":[49,57,265,315],"putative":[50],"functional":[51,201,348],"conservation,":[52],"cross-species":[54],"evolutionary":[55,263,345],"analysis":[56],"immune-active":[58,95,288,353],"proteins.":[59,289,354],"An":[60,160],"independent":[61,106],"external":[62,130],"test":[63,102,131,242],"dataset":[64,243],"further":[66,329],"used":[67],"to":[68,167,327],"preliminarily":[69],"probe":[70],"its":[71,319],"potential":[72],"generalization":[73],"behaviour.":[74],"Methods:":[75],"Nineteen":[76],"arthropod-derived":[77],"immunocompetent":[78],"(tick":[80],"lipocalin":[81,113,125],"antihistamine":[82],"proteins,":[83,87],"mosquito":[84],"D7":[85],"salivary":[86],"dust":[88],"mite":[89],"allergens,":[90],"two":[92,111,123],"additional":[93],"arthropod":[94,251],"proteins)":[96],"our":[98],"reference":[99,187,252],"dataset.":[100,132],"Eleven":[101],"sequences,":[103],"comprising":[104],"nine":[105,117],"vertebrate":[107,118,237],"Cathelicidin":[108],"peptides":[109,121],"tick":[112,124],"positive":[114],"controls,":[115],"including":[116],"cathelicidin":[119,238],"antimicrobial":[120],"homologs,":[126],"served":[127],"as":[128],"Using":[133],"Python3.9,":[134],"implemented":[136],"an":[137],"analytical":[138],"pipeline.":[139],"t33_650M_UR50D":[142],"in":[144,240],"mode":[147],"generated":[148],"1280-dimensional":[149],"sequence":[150],"embeddings.":[151],"Six":[152],"core":[153],"secondary-structure":[156],"descriptors":[157],"were":[158,182],"computed.":[159],"empirically-determined":[161],"weight":[162],"ratio":[163],"(0.7:0.3)":[164],"applied":[166],"build":[168],"weighted":[170],"fused":[171],"dissimilarity":[172,206,216],"matrix.":[173],"After":[174],"full":[175],"feature":[176],"concatenation,":[177],"visualization":[181],"performed.":[183],"Results:":[184],"On":[185],"data":[188],"set,":[189],"fusion":[191,205],"features":[192],"showed":[193],"significant":[195,226],"visual":[196],"separation":[197],"trend":[198],"among":[199],"different":[200],"protein":[202,306],"families.":[203],"value":[207,217],"within":[208],"family":[210,343],"is":[211,223],"usually":[212],"lower":[213],"than":[214],"between":[218],"families,":[220],"there":[222],"statistically":[225],"difference":[227],"at":[228],"group":[230],"level":[231],"(P":[232],"<":[233],"0.05).":[234],"9":[236],"sequences":[239],"form":[244],"unique":[246],"cluster":[247],"separated":[248],"protein.":[253],"observed":[255],"patterns":[257],"are":[258],"generally":[259],"consistent":[260],"with":[261],"relationship":[264],"species":[266],"calculated":[269],"physical":[270],"chemical":[272],"properties.":[273],"Conclusion:":[274],"This":[275,334],"ESM-2-embedding":[277],"physicochemical-feature-fusion":[279],"PCA":[280],"shows":[283],"promising":[284],"descriptive":[285],"performance":[286],"It":[290],"can":[291],"generate":[292],"grouping":[294],"without":[295],"relying":[296],"on":[297,331],"high-quality":[298],"multiple-sequence":[299],"alignments":[300],"may":[302],"help":[303],"analyse":[304],"datasets.":[307,333],"Nevertheless,":[308],"given":[309],"dataset-size":[310],"limitations":[311],"absence":[314],"quantitative":[316],"clustering-validation":[317],"metrics,":[318],"broad-scale":[320],"classification":[321],"accuracy,":[322],"stability":[323],"generalizability":[325],"remain":[326],"be":[328],"validated":[330],"larger":[332],"pipeline":[335],"provides":[336],"reproducible":[338],"bioinformatic":[339],"framework":[340],"screening,":[344],"interpretation":[346],"hypothesis":[349],"generation":[350],"animal-derived":[352]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-01T00:00:00"}
