Quantum Chemistry Driven Molecular Inverse Design with Data-free Reinforcement Learning
arXiv:2503.12653 · doi:10.1021/acs.jctc.5c02055
Abstract
The inverse design of molecules has challenged chemists for decades. In the past years, machine learning and artificial intelligence have emerged as new tools to generate molecules tailoring desired properties, but with the limit of relying on models that are pretrained on large datasets. Here, we present a data-free generative model based on reinforcement learning and quantum mechanics calculations. To improve the generation, our software is based on a five-model reinforcement learning algorithm designed to mimic the syntactic rules of an original ASCII encoding based on the SMILES one, and here reported. The reinforcement learning generator is rewarded by on-the-fly quantum mechanics calculations within a computational routine addressing conformational sampling. We demonstrate that our software successfully generates new molecules with desired properties finding optimal solutions for problems with known solutions and (sub)optimal molecules for unexplored chemical (sub)spaces, jointly showing significant speed-up to a reference baseline.
47 pages including references and supporting material
References in corpus (9)
- Escaping free-energy minima
- Automatic chemical design using a data-driven continuous representation of molecules
- Optimization of Molecules via Deep Reinforcement Learning
- Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
- Generative Models for Automatic Chemical Design
- Inverse Quantum Chemistry: Concepts and Strategies for Rational Compound Design
- Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
- Gradient-Driven Molecule Construction: An Inverse Approach Applied to the Design of Small-Molecule Fixating Catalysts
- Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning