Diseases-Specific Chemogenomics Knowledgebases and Cloud Computing TargetHunter© for System Pharmacology and Drug Discovery Research
Abstract: Chemogenomics is an interdisciplinary research that utilizes chemicals/drugs and associated genomics data to systematically identify and analyze chemicals-protein/protein interactions for the purpose of enhancing new drug discovery. Computational chemogenomics draws from the cheminformatics/ bioinformatics and computational biology disciplines to produce useful information systems for researchers in pursuit of chemogenomics data-mining, predictive modeling, as well as techniques in ligand- and structure-based drug design. We have established an integrated platform of cloud computing algorithms and cloud sourcing chemogenomics knowledgebases for systems pharmacology drug discovery. Such diseases-specific chemogenomics knowledgebases (CGKB) are available online, including: cannabinoid molecular information database (CBID), drug abuse, Alzheimer’s disease, Parkinson's disease, multiple myeloma, liver fibrosis and stem cell chemogenomics databases, etc.). Our recently published Alzheimer’s disease (AD) CGKB platform has assembled various AD-related chemogenomics data records, including 928 genes and 320 proteins related to AD, 194 AD drugs approved or in clinical trials, and 405,188 chemicals associated with 1,023,137 records of reported bioactivities from 38,284 corresponding bioassays and 10,050 references. The CGKB system is implemented with our advanced GPU-accelerated machine learning and cheminformatics algorithms and tools, including online programs (TargetHunter, HTDocking, LiCABEDS classifier, ANN-QSAR and BBB predictors, etc). It transforms the one-target-one-drug development process to a new multi-targets-multi-drugs paradigm; as such it is perfect for the system study of polydrug and polypharmacology networks of drugs or chemicals for drug repurposing, drug synergy prediction and new drug discovery. Overall, such a cloud computing server will augment our capacity to benefit the broad research community and will help break the knowledge barrier, reduce costs, and accelerate advances in computer-aided drug design by consolidating existing data and computational technology. Ultimately, it will facilitate scientists to conduct “virtual to real” translational systems pharmacology research for target identification and drug discovery.