A machine learning and network framework to discover new indications for small molecules

Drug repurposing, identifying novel indications for drugs, bypasses common drug development pitfalls to ultimately deliver therapies to patients faster. However, most repurposing discoveries have been led by anecdotal observations (e.g. Viagra) or experimental-based repurposing screens, which are costly, time-consuming, and imprecise. Recently, more systematic computational approaches have been proposed, however these rely on utilizing the information from the diseases a drug is already approved to treat. This inherently limits the algorithms, making them unusable for investigational molecules. Here, we present a computational approach to drug repurposing, CATNIP, that requires only biological and chemical information of a molecule. CATNIP is trained with 2,576 diverse small molecules and uses 16 different drug similarity features, such as structural, target, or pathway based similarity. This model obtains significant predictive power (AUC = 0.841). Using our model, we created a repurposing network to identify broad scale repurposing opportunities between drug types. By exploiting this network, we identified literature-supported repurposing candidates, such as the use of systemic hormonal preparations for the treatment of respiratory illnesses. Furthermore, we demonstrated that we can use our approach to identify novel uses for defined drug classes. We found that adrenergic uptake inhibitors, specifically amitriptyline and trimipramine, could be potential therapies for Parkinson's disease. Additionally, using CATNIP, we predicted the kinase inhibitor, vandetanib, as a possible treatment for Type 2 Diabetes. Overall, this systematic approach to drug repurposing lays the groundwork to streamline future drug development efforts. Author summary Currently, clinical approval of a drug is an arduous process that results in an overwhelming number of compounds failing due to safety or efficacy concerns, which leaves patients without novel, lifesaving treatments. The idea of drug repurposing is to take approved drugs, or compounds that were shelved due to reasons other than safety and identify new diseases for them to treat. This would allow drugs, if they are sufficiently effective, to quickly go through the FDA approval process and be available to patients quicker, which also cuts the ever growing cost of novel compound research and development. Here, we introduce CATNIP, a computational model, that can predict novel indications for specific drugs or entire drug classes. This approach analyzes drug similarity across a wide range of biological, chemical and clinical features, giving a complete picture of each drug's mechanism and possible indications. Interestingly, CATNIP can be used for drugs that not only are previously approved, but also shelved compounds, which are often overlooked in previous repurposing analyses. Most importantly, CATNIP successfully identified novel treatments for both Parkinson's disease and Type 2 Diabetes, which are currently undergoing pre-clinical validation.