Abstract
We present SPOTLIGHT - a proof-of-concept for a method capable of designing a diverse set of novel drug molecules through a rule-based approach. The model constructs molecules atom-by-atom directly at the active site of a given target protein. SPOTLIGHT has the potential to be faster and more efficient than many existing methods that rely on generation cycles and docking/scoring to optimize their molecules. It requires no apriori information about known ligands as the molecule construction is purely based on classical interactions. We patch the model with deep reinforcement learning (RL) by using a Graph Convolution Policy Network (GCPN) to tune molecule-level properties directly during the generation phase. Our method has shown promising results when applied to the ATP binding pocket of the well-studied HSP90 protein. We show that our model upholds diversity while successfully producing strong binders to the protein. Given the stochasticity at each step, we do not expect it to reproduce known ligands exactly. However, we show how it uses significant fragments of known ligands as substructures while also providing an alternate way for tuning between similarity and novelty.
Supplementary materials
Title
Supporting information
Description
Supporting information for the manuscript "SPOTLIGHT: Structure-based Prediction and Optimization Tool for LIgand Generation on Hard-to-drug Targets - Combining Deep Reinforcement Learning with Physics-based de novo drug design"
Actions