Optimization of Molecules via Deep Reinforcement Learning
This work addresses molecule optimization for medicinal chemistry, offering a novel method but with incremental extensions to multi-objective tasks.
The authors tackled molecule optimization by developing MolDQN, a deep reinforcement learning framework that ensures 100% chemical validity and operates without pre-training, achieving improvements in drug-likeness while maintaining similarity to original molecules.
We present a framework, which we call Molecule Deep $Q$-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double $Q$-learning and randomized value functions). We directly define modifications on molecules, thereby ensuring 100\% chemical validity. Further, we operate without pre-training on any dataset to avoid possible bias from the choice of that set. Inspired by problems faced during medicinal chemistry lead optimization, we extend our model with multi-objective reinforcement learning, which maximizes drug-likeness while maintaining similarity to the original molecule. We further show the path through chemical space to achieve optimization for a molecule to understand how the model works.