Combining Machine Learning Systems and Multiple Docking Simulation Packages to Improve Docking Prediction Reliability for Network Pharmacology

• DOI: 10.1371/journal.pone.0083922
• Publication Date: 2013-12-31T22:04:35Z
• Authors: Kun-Yi Hsin; Samik Ghosh; Hiroaki Kitano
• Keywords: Docking (animal); Interaction network

Increased availability of bioinformatics resources is creating opportunities for the application network pharmacology to predict drug effects and toxicity resulting from multi-target interactions. Here we present a high-precision computational prediction approach that combines two elaborately built machine learning systems multiple molecular docking tools assess binding potentials test compound against proteins involved in complex network. One re-scoring function evaluate modes generated by tools. The second mode selection identify most predictive mode. Results series benchmark validations case study show this surpasses reliability other techniques it also identifies either primary or off-targets kinase inhibitors. Integrating with maps makes possible address safety issues comprehensively investigating network-dependent candidate.