Virtual Screening of Selective Multitarget Kinase Inhibitors by Combinatorial Support Vector Machines

• Published in: Molecular pharmaceutics 2010-10, Vol.7 (5), p.1545-1560
• Main Authors: Ma, X. H, Wang, R, Tan, C. Y, Jiang, Y. Y, Lu, T, Rao, H. B, Li, X. Y, Go, M. L, Low, B. C, Chen, Y. Z
• Format: Article
• Language: English
• Subjects: Antineoplastic Agents - chemistry; Antineoplastic Agents - pharmacology; CDC2 Protein Kinase - antagonists & inhibitors; Cyclin-Dependent Kinase 2 - antagonists & inhibitors; Drug Design; Drug Evaluation, Preclinical - methods; Glycogen Synthase Kinase 3 - antagonists & inhibitors; Humans; Lymphocyte Specific Protein Tyrosine Kinase p56(lck) - antagonists & inhibitors; Protein Kinase Inhibitors - chemistry; Protein Kinase Inhibitors - pharmacology; Receptor, Epidermal Growth Factor - antagonists & inhibitors; Receptors, Fibroblast Growth Factor - antagonists & inhibitors; Receptors, Platelet-Derived Growth Factor - antagonists & inhibitors; Receptors, Vascular Endothelial Growth Factor - antagonists & inhibitors; src-Family Kinases - antagonists & inhibitors; Support Vector Machine; User-Computer Interface
• ISSN: 1543-8384; 1543-8392
• DOI: 10.1021/mp100179t

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