Virtual Screening of Selective Multitarget Kinase Inhibitors by Combinatorial Support Vector Machines
Virtual Screening of Selective Multitarget Kinase Inhibitors by Combinatorial Support Vector Machines
复制标题
通过组合支持向量机虚拟筛选选择性多靶点激酶抑制剂
DOI：
10.1021/mp100179t
复制
发表时间：
2010-09-01
影响因子：
4.9
通讯作者：
Chen, Y. Z.
中科院分区：
文献类型：
--
作者：
Ma, X. H.;Wang, R.;Chen, Y. Z.
人们越来越多地探索多靶点药物以提高疗效并减少反靶点活性和毒性。人们需要有效的虚拟筛选（VS）工具来搜索选择性多靶点药物。组合支持向量机 (C-SVM) 作为 VS 工具进行了测试，用于搜索 9 种抗癌激酶靶标（EGFR、VEGFR、PDGFR、Src、FGFR、Lck、CDK1、CDK2、GSK3）的 11 种组合的双抑制剂。对 233-1,316 个非双抑制剂进行训练的 C-SVM 正确识别了 56-230 个激酶组内双抑制剂中的 26.8%-57.3%（大多数>36%）（相当于两个独立的单独目标 VS 工具的 50-70% 产率），以及 41 个激酶组间双抑制剂中的 12.2%双抑制剂。 C-SVM 在错误识别为双抑制剂方面具有相当的选择性 3.7%-48.1%（大多数
Multitarget agents have been increasingly explored for enhancing efficacy and reducing countertarget activities and toxicities. Efficient virtual screening (VS) tools for searching selective multitarget agents are desired. Combinatorial support vector machines (C-SVM) were tested as VS tools for searching dual-inhibitors of 11 combinations of 9 anticancer kinase targets (EGFR, VEGFR, PDGFR, Src, FGFR, Lck, CDK1, CDK2, GSK3). C-SVM trained on 233-1,316 non-dual-inhibitors correctly identified 26.8%-57.3% (majority >36%) of the 56-230 intra-kinase-group dual-inhibitors (equivalent to the 50-70% yields of two independent individual target VS tools), and 12.2% of the 41 inter-kinase-group dual-inhibitors. C-SVM were fairly selective in misidentifying as dual-inhibitors 3.7%-48.1% (majority