Martin Maiers, Yoram Louzoun, Philip Pymm, Julian P Vivian, Jamie Rossjohn, Andrew G Brooks, Philippa M Saunders
{"title":"KIR3DL1与人白细胞抗原结合的预测。","authors":"Martin Maiers, Yoram Louzoun, Philip Pymm, Julian P Vivian, Jamie Rossjohn, Andrew G Brooks, Philippa M Saunders","doi":"10.1016/j.jbc.2025.110437","DOIUrl":null,"url":null,"abstract":"<p><p>KIR3DL1 is a polymorphic inhibitory receptor on natural killer (NK) cells that recognizes HLA class I allotypes. While the Bw4 motif spanning residues 77-83 is central to this interaction, structural studies have shown that polymorphisms elsewhere in the HLA molecule also influence binding. To address the challenge of predicting interactions across the extensive diversity of both KIR3DL1 and HLA, we developed a machine learning model trained on binding data from nine KIR3DL1 tetramers tested against a panel of HLA class I allotypes. Multiple models were evaluated using different subsets of HLA sequence features, including the full α1/α2 domains, the Bw4 motif, and α-helical residues excluding loop regions. The best-performing model, using Multi-Label-Vector Optimization (MLVO) and trained on α-helix positions, achieved AUC scores ranging from 0.74 to 0.974 across all KIR3DL1 allotypes. The model effectively distinguished high and low binders, revealing that residues beyond the Bw4 motif contribute to binding strength in a nonadditive manner. These findings demonstrate that binding affinity cannot be accurately captured by binary classifiers or single-motif rules. Our approach offers a more nuanced framework for modeling KIR3DL1-HLA interactions, with broad applicability to immunogenetic research and clinical decision-making.</p>","PeriodicalId":15140,"journal":{"name":"Journal of Biological Chemistry","volume":" ","pages":"110437"},"PeriodicalIF":4.0000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Prediction of KIR3DL1 and Human Leukocyte Antigen binding.\",\"authors\":\"Martin Maiers, Yoram Louzoun, Philip Pymm, Julian P Vivian, Jamie Rossjohn, Andrew G Brooks, Philippa M Saunders\",\"doi\":\"10.1016/j.jbc.2025.110437\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>KIR3DL1 is a polymorphic inhibitory receptor on natural killer (NK) cells that recognizes HLA class I allotypes. While the Bw4 motif spanning residues 77-83 is central to this interaction, structural studies have shown that polymorphisms elsewhere in the HLA molecule also influence binding. To address the challenge of predicting interactions across the extensive diversity of both KIR3DL1 and HLA, we developed a machine learning model trained on binding data from nine KIR3DL1 tetramers tested against a panel of HLA class I allotypes. Multiple models were evaluated using different subsets of HLA sequence features, including the full α1/α2 domains, the Bw4 motif, and α-helical residues excluding loop regions. The best-performing model, using Multi-Label-Vector Optimization (MLVO) and trained on α-helix positions, achieved AUC scores ranging from 0.74 to 0.974 across all KIR3DL1 allotypes. The model effectively distinguished high and low binders, revealing that residues beyond the Bw4 motif contribute to binding strength in a nonadditive manner. These findings demonstrate that binding affinity cannot be accurately captured by binary classifiers or single-motif rules. Our approach offers a more nuanced framework for modeling KIR3DL1-HLA interactions, with broad applicability to immunogenetic research and clinical decision-making.</p>\",\"PeriodicalId\":15140,\"journal\":{\"name\":\"Journal of Biological Chemistry\",\"volume\":\" \",\"pages\":\"110437\"},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2025-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Biological Chemistry\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1016/j.jbc.2025.110437\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BIOCHEMISTRY & MOLECULAR BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Biological Chemistry","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1016/j.jbc.2025.110437","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
Prediction of KIR3DL1 and Human Leukocyte Antigen binding.
KIR3DL1 is a polymorphic inhibitory receptor on natural killer (NK) cells that recognizes HLA class I allotypes. While the Bw4 motif spanning residues 77-83 is central to this interaction, structural studies have shown that polymorphisms elsewhere in the HLA molecule also influence binding. To address the challenge of predicting interactions across the extensive diversity of both KIR3DL1 and HLA, we developed a machine learning model trained on binding data from nine KIR3DL1 tetramers tested against a panel of HLA class I allotypes. Multiple models were evaluated using different subsets of HLA sequence features, including the full α1/α2 domains, the Bw4 motif, and α-helical residues excluding loop regions. The best-performing model, using Multi-Label-Vector Optimization (MLVO) and trained on α-helix positions, achieved AUC scores ranging from 0.74 to 0.974 across all KIR3DL1 allotypes. The model effectively distinguished high and low binders, revealing that residues beyond the Bw4 motif contribute to binding strength in a nonadditive manner. These findings demonstrate that binding affinity cannot be accurately captured by binary classifiers or single-motif rules. Our approach offers a more nuanced framework for modeling KIR3DL1-HLA interactions, with broad applicability to immunogenetic research and clinical decision-making.
期刊介绍:
The Journal of Biological Chemistry welcomes high-quality science that seeks to elucidate the molecular and cellular basis of biological processes. Papers published in JBC can therefore fall under the umbrellas of not only biological chemistry, chemical biology, or biochemistry, but also allied disciplines such as biophysics, systems biology, RNA biology, immunology, microbiology, neurobiology, epigenetics, computational biology, ’omics, and many more. The outcome of our focus on papers that contribute novel and important mechanistic insights, rather than on a particular topic area, is that JBC is truly a melting pot for scientists across disciplines. In addition, JBC welcomes papers that describe methods that will help scientists push their biochemical inquiries forward and resources that will be of use to the research community.