Abstract
In this contribution, we propose a novel framework, 3D-MolGNNRL, coupling reinforcement learning (RL) to a deep generative model based on 3D-Scaffold to generate target candidates specific to a protein pocket building up atom by atom from the core scaffold. 3D-MolGNNRL provides an efficient way to optimize key features within a protein pocket using a parallel graph neural network model. The agent learns to build molecules in 3D space while optimizing the binding affinity, potency, and synthetic accessibility of the candidates generated for the SARS-CoV-2 Main protease.
Application Number
18/370,814
Inventors
Bontha,Mridula V S
Kumar,Neeraj
Pope,Jenna A
McNaughton,Andrew D
Knutson,Carter R
Market Sector
Biological Sciences and Omics