相关实验视频

Updated: Sep 17, 2025

qKAT: Quantitative Semi-automated Typing of Killer-cell Immunoglobulin-like Receptor Genes

qKAT: Quantitative Semi-automated Typing of Killer-cell Immunoglobulin-like Receptor Genes

Published on: March 6, 2019

预测KIR3DL1和人类白细胞抗原的结合

Martin Maiers¹, Yoram Louzoun², Philip Pymm³

¹CIBMTR® (Center for International Blood and Marrow Transplant Research), NMDP, Minneapolis, Minnesota, USA.

The Journal of biological chemistry

|July 3, 2025

概括

一个新的机器学习模型准确地预测了杀手细胞免疫球蛋白类受体 (KIR3DL1) 和人类白细胞抗原 (HLA) I 类分子之间的相互作用. 这推动了免疫遗传学研究,揭示了Bw4动机之外的复杂结合.

科学领域:

免疫遗传学免疫遗传学
计算生物学计算生物学
分子相互作用分子相互作用

背景情况:

杀手细胞免疫球蛋白样受体 (KIR) 3DL1是自然杀手细胞 (NK) 的抑制受体.
KIR3DL1识别了人类白细胞抗原 (HLA) I 类全型,Bw4 基因对结合至关重要.
现有知识表明,Bw4动机之外的多态性也会影响KIR3DL1-HLA结合亲和力.

研究的目的:

开发KIR3DL1-HLA类I相互作用的预测模型.
为了解决由KIR3DL1和HLA分子的广泛多样性产生的复杂性.
调查各种HLA序列特征对结合亲和力的贡献.

主要方法:

通过使用九个KIR3DL1四度体和一组HLAI类全型的结合数据,开发了一种机器学习模型.
评估了各种HLA序列特征,包括α1/α2域,Bw4动机和α螺旋残留物.
采用多标签矢量优化 (MLVO),最好的模型在α-螺旋位置上训练.

主要成果:

MLVO模型取得了高AUC得分 (0.740.974),有效地区分了KIR3DL1全型中的高和低结合剂.
该模型表明,除了Bw4基因之外的残留物以非添加方式显著促进结合强度.
使用简单的二进制分类器或单一动机规则无法准确预测绑定亲和力.

结论:

机器学习方法为建模KIR3DL1-HLA相互作用提供了更细致的框架.
预测KIR3DL1-HLA结合需要考虑已确定的Bw4基因之外的多重多态残留物.
该模型在免疫遗传学研究和临床决策方面具有广泛的适用性.

关键词:

生物信息学是一种生物信息学.细胞表面受体细胞表面受体主要组织相容性复合体 (MHC)自然杀手细胞是自然杀手细胞.接收器的结构-功能.移植移植移植移植

更多相关视频

Immunopeptidomics: Isolation of Mouse and Human MHC Class I- and II-Associated Peptides for Mass Spectrometry Analysis

Immunopeptidomics: Isolation of Mouse and Human MHC Class I- and II-Associated Peptides for Mass Spectrometry Analysis

Published on: October 15, 2021

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Published on: March 24, 2015

相关概念视频

Conserved Binding Sites

Conserved Binding Sites

Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...