Optimization of Molecules via Deep Reinforcement Learning

2018-10-19 · Zhenpeng Zhou, Steven Kearnes, Li Li, Richard N. Zare, Patrick Riley

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.

📄 PDF Abstract BibTeX arXiv:1810.08678

Code (7)

google-research/google-research/tree/master/mol_dqn 공식 구현 tf

2023-MindSpore-4/Code12/tree/main/d2l/chapter_11_optimization mindspore

aksub99/MolDQN-pytorch pytorch

caiyingchun/MolDQN tf

danilonumeroso/MEG pytorch

junyoung0131/Mol-DQN tf

tangxiangru/RL-for-RNA-design tf

Tasks

Deep Reinforcement LearningMolecular Graph GenerationMulti-Objective Reinforcement LearningQ-Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Diversity-Aware Reinforcement Learning for de novo Drug Design

2024-10-14 · Hampus Gummesson Svensson, Christian Tyrchan, Ola Engkvist, Morteza Haghir Chehreghani

Fine-tuning a pre-trained generative model has demonstrated good performance in generating promising drug molecules. The fine-tuning task is often formulated as a reinforcement learning problem, where previous methods ef…

Diversity Drug Design reinforcement-learning Reinforcement Learning

Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES

2022-10-22 · Esben Jannik Bjerrum, Christian Margreitter, Thomas Blaschke, Raquel López-Ríos de Castro

Using generative deep learning models and reinforcement learning together can effectively generate new molecules with desired properties. By employing a multi-objective scoring function, thousands of high-scoring molecul…

Diversity Drug Discovery reinforcement-learning Reinforcement Learning+1

Fragment-based Sequential Translation for Molecular Optimization

2021-10-26 · NeurIPS Workshop AI4Scien 2021 12 · Benson Chen, Xiang Fu, Regina Barzilay, Tommi Jaakkola

Searching for novel molecular compounds with desired properties is an important problem in drug discovery. Many existing frameworks generate molecules one atom at a time. We instead propose a flexible editing paradigm th…

Drug Discovery Reinforcement Learning (RL)Translation

Grammars and reinforcement learning for molecule optimization

2018-11-27 · Egor Kraev

We seek to automate the design of molecules based on specific chemical properties. Our primary contributions are a simpler method for generating SMILES strings guaranteed to be chemically valid, using a combination of a …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)valid

MOLUCINATE: A Generative Model for Molecules in 3D Space

2021-09-30 · Michael Arcidiacono, David Ryan Koes

Recent advances in machine learning have enabled generative models for both optimization and de novo generation of drug candidates with desired properties. Previous generative models have focused on producing SMILES stri…

Position reinforcement-learning Reinforcement Learning (RL)