基于高维特征非线性筛选的HLA-A*0201限制性CTL表位预测

高活性细胞毒T细胞(CTL)表位鉴定是设计肿瘤疫苗的关键内容.采用天然氨基酸的531个物理化学性质参数表征HLA-A^*0201限制性表位9肽, 从531×9个初始描述子出发, 经二元矩阵重排过滤器粗筛和多轮末尾淘汰精细筛选, 获得18个物理化学意义明确的保留描述子. 18个保留描述子主要涉及除1位、5位外各位置残基的疏水性和空间结构特征, 3位残基疏水性对活性影响最大, 且2位、4位、9位残基共占10个保留描述子,支持2位和9位残基为锚点、3位为关键位点以及4位残基为标志链的现有认知. 对18个保留描述子以支持向量回归构建定量序效模型,其拟合、留一法交叉验证决定系数R²、Q_cv²分别为0.957、0.708; 独立预测决定系数及均方根误差Q_ext² 、RMSE_ext分别为0.818、0.366, 明显优于文献报道. 通过对全组合虚拟9肽的预测, 得到了多条预测活性高于已知表位肽的9肽, 可供实验验证. 较全面阐明了特定位置残基对多肽亲和性的影响规律, 为高活性多肽疫苗分子设计提供了切实指导.     

Prediction of acute toxicity of organophosphorus pesticides using topological indices

Topological indices were used in the prediction of the acute toxicity (intraperitoneal and oral LD₅₀) of organophosphorus pesticides on rats. Models with six variables for the prediction of LD₅₀-i.p. (r?=?0.849, Q ²?=?0.613) and eight variables for LD₅₀-oral (r?=?0.906, Q ²?=?0.701) were selected. External group and cross-validation by use of leave-n-out tests were also performed in order to assess the stability and the prediction performance of the selected topological models.