DeepAI AI Chat
Log In Sign Up

Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

by   Soojung Yang, et al.

Recently, utilizing reinforcement learning (RL) to generate molecules with desired properties has been highlighted as a promising strategy for drug design. A molecular docking program - a physical simulation that estimates protein-small molecule binding affinity - can be an ideal reward scoring function for RL, as it is a straightforward proxy of the therapeutic potential. Still, two imminent challenges exist for this task. First, the models often fail to generate chemically realistic and pharmacochemically acceptable molecules. Second, the docking score optimization is a difficult exploration problem that involves many local optima and less smooth surfaces with respect to molecular structure. To tackle these challenges, we propose a novel RL framework that generates pharmacochemically acceptable molecules with large docking scores. Our method - Fragment-based generative RL with Explorative Experience replay for Drug design (FREED) - constrains the generated molecules to a realistic and qualified chemical space and effectively explores the space to find drugs by coupling our fragment-based generation method and a novel error-prioritized experience replay (PER). We also show that our model performs well on both de novo and scaffold-based schemes. Our model produces molecules of higher quality compared to existing methods while achieving state-of-the-art performance on two of three targets in terms of the docking scores of the generated molecules. We further show with ablation studies that our method, predictive error-PER (FREED(PE)), significantly improves the model performance.


page 8

page 9

page 16


Structure-aware generation of drug-like molecules

Structure-based drug design involves finding ligand molecules that exhib...

De novo design of protein target specific scaffold-based Inhibitors via Reinforcement Learning

Efficient design and discovery of target-driven molecules is a critical ...

Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning

Machine learning has the potential to automate molecular design and dras...

Guiding Deep Molecular Optimization with Genetic Exploration

De novo molecular design attempts to search over the chemical space for ...

PaccMann^RL on SARS-CoV-2: Designing antiviral candidates with conditional generative models

With the fast development of COVID-19 into a global pandemic, scientists...

Symmetry-Aware Actor-Critic for 3D Molecular Design

Automating molecular design using deep reinforcement learning (RL) has t...