Energy-based generative models for target-specific drug discovery
-
Published:2023-06-01
Issue:
Volume:3
Page:
-
ISSN:2674-0095
-
Container-title:Frontiers in Molecular Medicine
-
language:
-
Short-container-title:Front. Mol. Med
Author:
Li Junde,Beaudoin Collin,Ghosh Swaroop
Abstract
Drug targets are the main focus of drug discovery due to their key role in disease pathogenesis. Computational approaches are widely applied to drug development because of the increasing availability of biological molecular datasets. Popular generative approaches can create new drug molecules by learning the given molecule distributions. However, these approaches are mostly not for target-specific drug discovery. We developed an energy-based probabilistic model for computational target-specific drug discovery. Results show that our proposed TagMol can generate molecules with similar binding affinity scores as real molecules. GAT-based models showed faster and better learning relative to Graph Convolutional Network baseline models.
Funder
Office of Integrative Activities
Division of Graduate Education
Division of Computer and Network Systems
Division of Computing and Communication Foundations
Publisher
Frontiers Media SA
Reference26 articles.
1. Wasserstein generative adversarial networks;Arjovsky,2017
2. Hp-gan: Probabilistic 3d human motion prediction via gan;Barsoum,2018
3. Molecular docking and ligand specificity in fragment-based inhibitor discovery;Chen;Nat. Chem. Biol.,2009
4. Cogmol: Target-specific and selective drug design for Covid-19 using deep generative models;Chenthamarakshan;Adv. Neural Inf. Process. Syst.,2020