Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

TL;DR

This paper introduces a reinforcement learning approach for molecular design in Cartesian coordinates, utilizing quantum-chemical properties as rewards, enabling the generation of diverse molecules with physical plausibility.

Contribution

It presents a novel RL formulation for molecular design in Cartesian space, incorporating quantum mechanics-based rewards and a new environment for benchmarking.

Findings

RL agent efficiently learns to solve molecular design tasks

Method generates molecules invariant to translation and rotation

Uses quantum-chemical properties for reward calculation

Abstract

Automating molecular design using deep reinforcement learning (RL) holds the promise of accelerating the discovery of new chemical compounds. Existing approaches work with molecular graphs and thus ignore the location of atoms in space, which restricts them to 1) generating single organic molecules and 2) heuristic reward functions. To address this, we present a novel RL formulation for molecular design in Cartesian coordinates, thereby extending the class of molecules that can be built. Our reward function is directly based on fundamental physical properties such as the energy, which we approximate via fast quantum-chemical methods. To enable progress towards de-novo molecular design, we introduce MolGym, an RL environment comprising several challenging molecular design tasks along with baselines. In our experiments, we show that our agent can efficiently learn to solve these tasks from scratch by working in a translation and rotation invariant state-action space.