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

• Published in: Molecular pharmaceutics Vol. 7; no. 5; pp. 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: Journal Article
• Language: English
• Published: United States American Chemical Society 04.10.2010
• 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; kinase inhibitor; support vector machines; virtual screening; computer aided drug design; high-throughput screening; Anticancer; multitarget
• 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 <20%) of the 233−1,316 non-dual-inhibitors of the same kinase pairs and 0.98%−4.77% of the 3,971−5,180 inhibitors of other kinases. C-SVM produced low false-hit rates in misidentifying as dual-inhibitors 1,746−4,817 (0.013%−0.036%) of the 13.56 M PubChem compounds, 12−175 (0.007%−0.104%) of the 168 K MDDR compounds, and 0−84 (0.0%−2.9%) of the 19,495−38,483 MDDR compounds similar to the known dual-inhibitors. C-SVM was compared to other VS methods Surflex-Dock, DOCK Blaster, kNN and PNN against the same sets of kinase inhibitors and the full set or subset of the 1.02 M Zinc clean-leads data set. C-SVM produced comparable dual-inhibitor yields, slightly better false-hit rates for kinase inhibitors, and significantly lower false-hit rates for the Zinc clean-leads data set. Combinatorial SVM showed promising potential for searching selective multitarget agents against intra-kinase-group kinases without explicit knowledge of multitarget agents.