Unknown

Dataset Information

0

Optimization of Molecules via Deep Reinforcement Learning.

ABSTRACT: 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. MolDQN achieves comparable or better performance against several other recently published algorithms for benchmark molecular optimization tasks. However, we also argue that many of these tasks are not representative of real optimization problems in drug discovery. 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.

SUBMITTER: Zhou Z 

PROVIDER: S-EPMC6656766 | biostudies-literature | 2019 Jul

REPOSITORIES: biostudies-literature

Json Xml
altmetric image

Publications

Optimization of Molecules via Deep Reinforcement Learning.

Zhou Zhenpeng Z   Kearnes Steven S   Li Li L   Zare Richard N RN   Riley Patrick P  

Scientific reports 20190724 1

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. MolDQN achieves comparable or better performance agains  ...[more]

Similar Datasets

Unknown Patient-Specific Sedation Management via Deep Reinforcement Learning
| S-EPMC8521809 | biostudies-literature
Unknown Strain design optimization using reinforcement learning.
| S-EPMC9200333 | biostudies-literature
Unknown Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning.
| S-EPMC7774092 | biostudies-literature
Unknown Multimodal bipedal locomotion generation with passive dynamics via deep reinforcement learning
| S-EPMC9899902 | biostudies-literature
Unknown Optimization of binding affinities in chemical space with generative pre-trained transformer and deep reinforcement learning.
| S-EPMC10905145 | biostudies-literature
Unknown The AI Economist: Taxation policy design via two-level deep multiagent reinforcement learning.
| S-EPMC9067926 | biostudies-literature
Unknown Perspective Taking in Deep Reinforcement Learning Agents.
| S-EPMC7390927 | biostudies-literature
Unknown Deep reinforcement learning for personalized treatment recommendation.
| S-EPMC9427729 | biostudies-literature
Unknown Temporal encoding in deep reinforcement learning agents.
| S-EPMC10724179 | biostudies-literature
Unknown Deep-reinforcement-learning-based water diversion strategy.
| S-EPMC10405199 | biostudies-literature