{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T11:22:22Z","timestamp":1793445742204,"version":"4.5.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Traditional sequence-comparison methods face challenges when classifying and identifying low-homology proteins formed by convergent evolution. In this exploratory study, we built a PCA-based unsupervised clustering workflow combining high-dimensional embeddings from the frozen pre-trained protein-language model ESM-2 and weighted-fused physicochemical features. The workflow was explored for family-level grouping, identification of putative functional conservation, and cross-species evolutionary analysis of immune-active proteins. An independent external test dataset was further used to preliminarily probe its potential generalization behaviour.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Nineteen arthropod-derived immunocompetent proteins (tick lipocalin antihistamine proteins, mosquito D7 salivary proteins, dust mite allergens, and two additional arthropod immune-active proteins) formed our reference dataset. Eleven test sequences, comprising nine independent vertebrate Cathelicidin peptides and two tick lipocalin positive controls, including nine vertebrate cathelicidin antimicrobial peptides and two tick lipocalin homologs, served as the external test dataset. Using Python3.9, we implemented an analytical pipeline. The ESM-2 t33_650M_UR50D model in frozen pre-trained mode generated 1280-dimensional sequence embeddings. Six core physicochemical and secondary-structure descriptors were computed. An empirically-determined weight ratio (0.7:0.3) was applied to build a weighted fused dissimilarity matrix. After full feature concatenation, PCA-based clustering and visualization were performed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the reference data set, the fusion features showed a significant visual separation trend among different functional protein families. The fusion dissimilarity value within the family is usually lower than the dissimilarity value between the families, and there is a statistically significant difference at the group level (P &amp;lt; 0.05). The 9 vertebrate cathelicidin sequences in the test dataset form a unique cluster separated from the arthropod reference protein. The observed clustering patterns are generally consistent with the evolutionary relationship of species and the calculated physical and chemical properties.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This exploratory ESM-2-embedding and physicochemical-feature-fusion PCA clustering workflow shows promising descriptive performance for immune-active proteins. It can generate family-level grouping without relying on high-quality multiple-sequence alignments and may help analyse low-homology protein datasets. Nevertheless, given dataset-size limitations and the absence of quantitative clustering-validation metrics, its broad-scale classification accuracy, stability and generalizability remain to be further validated on larger datasets. This pipeline provides a reproducible bioinformatic framework for exploratory family screening, evolutionary interpretation and functional hypothesis generation for animal-derived immune-active proteins.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2026.1918918","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:56:28Z","timestamp":1790744188000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Characterization and clustering of immunocompetent proteins based on ESM-2 sequence embedding and physicochemical feature fusion"],"prefix":"10.3389","volume":"17","author":[{"given":"Xingxing","family":"Liu","sequence":"first","affiliation":[{"name":"School of Xinjiang Second Medical College, Xinjiang","place":["Karamay, China"]},{"name":"Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Xinjiang Second Medical College, Xinjiang","place":["Karamay, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Xinjiang Second Medical College, Xinjiang","place":["Karamay, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Xinjiang Second Medical College, Xinjiang","place":["Karamay, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panpan","family":"Tong","sequence":"additional","affiliation":[{"name":"Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxin","family":"Xie","sequence":"additional","affiliation":[{"name":"Laboratory of Animal Etiology and Epidemiology, College of Veterinary Medicine, Xinjiang Agricultural University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1016\/j.cell.2024.01.022","article-title":"An atlas of protein homo-oligomerization across domains of life","volume":"187","author":"Schweke","year":"2024","journal-title":"Cell"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrev.5b00562","article-title":"Protein ensembles: How does nature harness thermodynamic fluctuations for life? The diverse functional roles of conformational ensembles in the cell","volume":"116","author":"Wei","year":"2016","journal-title":"Chem Rev"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1508584112","article-title":"From residue coevolution to protein conformational ensembles and functional dynamics","volume":"112","author":"Sutto","year":"2015","journal-title":"Proc Natl Acad Sci USA"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-022-01203-y","article-title":"Statistical and functional convergence of common and rare genetic influences on autism at chromosome 16p","volume":"54","author":"Weiner","year":"2022","journal-title":"Nat Genet"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09572-0","article-title":"Convergent evolution of diverse jaw joints in mammaliamorphs","volume":"647","author":"Mao","year":"2025","journal-title":"Nature"},{"key":"B6","doi-asserted-by":"publisher","first-page":"8278","DOI":"10.1038\/s41467-025-63898-x","article-title":"Repeatability of protein structural evolution following convergent gene fusions","volume":"16","author":"Konno","year":"2025","journal-title":"Nat Commun"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijbiomac.2025.148773","article-title":"Convergent evolution of a non-canonical bacterial antifreeze protein from Arctic Sea ice offers a blueprint for eco-friendly cryopreservation","volume":"333","author":"Liao","year":"2025","journal-title":"Int J Biol Macromol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2418254122","article-title":"Language models reveal a complex sequence basis for adaptive convergent evolution of protein functions","volume":"122","author":"Cao","year":"2025","journal-title":"Proc Natl Acad Sci USA"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.dci.2025.105434","article-title":"A histamine-binding protein derived from the hard tick Haemaphysalis qinghaiensis, alleviates xylene-induced mice skin edema","volume":"170","author":"Bai","year":"2025","journal-title":"Dev Comp Immunol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.vetpar.2026.110808","article-title":"A salivary histamine-binding protein from Rhipicephalus microplus and its evaluation as an anti-tick vaccine antigen","volume":"346","author":"Paes","year":"2026","journal-title":"Vet Parasitol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbag014","article-title":"Scalable embedding fusion with protein language models: insights from benchmarking text-integrated representations","volume":"27","author":"Ko","year":"2026","journal-title":"Brief Bioinform"},{"key":"B12","doi-asserted-by":"publisher","first-page":"4348","DOI":"10.1038\/s41467-022-32007-7","article-title":"ProtGPT2 is a deep unsupervised language model for protein design","volume":"13","author":"Ferruz","year":"2022","journal-title":"Nat Commun"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf026","article-title":"TargetCLP: clathrin proteins prediction combining transformed and evolutionary scale modeling-based multi-view features via weighted feature integration approach","volume":"26","author":"Ullah","year":"2024","journal-title":"Brief Bioinform"},{"key":"B14","doi-asserted-by":"publisher","first-page":"7049","DOI":"10.3390\/ijms25137049","article-title":"iNP_ESM: Neuropeptide identification based on evolutionary scale modeling and unified representation embedding features","volume":"25","author":"Li","year":"2024","journal-title":"Int J Mol Sci"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09722-4","article-title":"Convergent genome evolution shaped the emergence of terrestrial animals","volume":"649","author":"Wei","year":"2026","journal-title":"Nature"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.tig.2023.02.005","article-title":"Convergent evolution for antibiotic biosynthesis in bacteria and animals","volume":"39","author":"Papon","year":"2023","journal-title":"Trends Genet"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac619","article-title":"Tree visualizations of protein sequence embedding space enable improved functional clustering of diverse protein superfamilies","volume":"24","author":"Yeung","year":"2023","journal-title":"Brief Bioinform"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msg126","article-title":"The major tick salivary gland proteins and toxins from the soft tick, Ornithodoros savignyi, are part of the tick Lipocalin family: implications for the origins of tick toxicoses","volume":"20","author":"Mans","year":"2003","journal-title":"Mol Biol Evol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1128\/mbio.02289-23","article-title":"Aedes aEgypti D7 long salivary proteins modulate blood feeding and parasite infection","volume":"14","author":"Martin-Martin","year":"2023","journal-title":"mBio"},{"key":"B20","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1046\/j.1365-2583.2003.00416.x","article-title":"RNA interference in ticks: a study using histamine binding protein dsRNA in the female tick Amblyomma americanum","volume":"12","author":"Aljamali","year":"2003","journal-title":"Insect Mol Biol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1128\/spectrum.00534-22","article-title":"Efficacy of cathelicidin-mimetic antimicrobial peptoids against Staphylococcus aureus","volume":"10","author":"Benjamin","year":"2022","journal-title":"Microbiol Spectr"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2025.1524092","article-title":"Marsupial cathelicidins: characterization, antimicrobial activity and evolution in this unique mammalian lineage","volume":"16","author":"Peel","year":"2025","journal-title":"Front Immunol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1705","DOI":"10.1038\/s42003-024-07411-y","article-title":"Annotating protein functions via fusing multiple biological modalities","volume":"7","author":"Ma","year":"2024","journal-title":"Commun Biol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1038\/s41576-026-00933-7","article-title":"The genetic foundations of convergent traits","volume":"27","author":"Allard","year":"2026","journal-title":"Nat Rev Genet"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1093\/sysbio\/syaf034","article-title":"Unraveling the effects of ecology and evolutionary history in the phenotypic convergence of fishes","volume":"74","author":"Hodge","year":"2025","journal-title":"Syst Biol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1186\/s12864-018-5118-7","article-title":"Effects of evolutionary history on genome wide and phenotypic convergence in Drosophila populations","volume":"19","author":"Phillips","year":"2018","journal-title":"BMC Genomics"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2026.108572","article-title":"AttCo: Attention-based co-learning fusion of deep feature representation for medical image segmentation using multimodality","volume":"198","author":"Dao","year":"2026","journal-title":"Neural Netw"},{"key":"B28","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1186\/s13071-016-1790-0","article-title":"Specific histamine binding activity of a new lipocalin from Hyalomma asiaticum (Ixodidae) and therapeutic effects on allergic asthma in mice","volume":"9","author":"Wang","year":"2016","journal-title":"Parasit Vectors"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/biom10101372","article-title":"Aedes albopictus D7 salivary protein prevents host hemostasis and inflammation","volume":"10","author":"Martin-Martin","year":"2020","journal-title":"Biomolecules"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.6026\/97320630013366","article-title":"In silico validation of D7 salivary protein-derived B- and T-cell epitopes of Aedes aEgypti as potential vaccine to prevent transmission of flaviviruses and togaviruses to humans","volume":"13","author":"Sankar","year":"2017","journal-title":"Bioinformation"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaci.2024.04.017","article-title":"Structural analysis of human IgE monoclonal antibody epitopes on dust mite allergen Der p 2","volume":"154","author":"Ball","year":"2024","journal-title":"J Allergy Clin Immunol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giaf122","article-title":"Complete end-to-end learning from protein feature representation to protein interactome inference","volume":"14","author":"Chen","year":"2025","journal-title":"GigaScience"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.0c00189","article-title":"Cathelicidin-DM is an antimicrobial peptide from Duttaphrynus melanostictus and has wound-healing therapeutic potential","volume":"5","author":"Shi","year":"2020","journal-title":"ACS Omega"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1038\/srep32372","article-title":"Substrate prediction of Ixodes ricinus salivary lipocalins differentially expressed during Borrelia afzelii infection","volume":"6","author":"Vald\u00e9s","year":"2016","journal-title":"Sci Rep"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2022.846683","article-title":"Votucalis, a novel centrally sparing histamine-binding protein, attenuates histaminergic itch and neuropathic pain in mice","volume":"13","author":"Alrashdi","year":"2022","journal-title":"Front Pharmacol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/978-1-4939-9845-6_6","article-title":"Exploring toxin evolution: venom protein transcript sequencing and transcriptome-guided high-throughput proteomics","volume":"2068","author":"Modahl","year":"2020","journal-title":"Methods Mol Biol"},{"key":"B37","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1038\/s41467-024-45068-7","article-title":"Structure-guided discovery of anti-CRISPR and anti-phage defense proteins","volume":"15","author":"Duan","year":"2024","journal-title":"Nat Commun"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1007\/s00105-023-05277-5","article-title":"Insect venom allergies-What will change in times of global change","volume":"75","author":"Ru\u00ebff","year":"2024","journal-title":"Dermatologie (Heidelb)"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1906831117","article-title":"Expert-augmented machine learning","volume":"117","author":"Gennatas","year":"2020","journal-title":"Proc Natl Acad Sci USA"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1918918\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:56:28Z","timestamp":1790744188000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1918918\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":39,"alternative-id":["10.3389\/fimmu.2026.1918918"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2026.1918918","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]},"article-number":"1918918"}}