Generative Models for De Novo Drug Design

Abstract

Artificial intelligence (AI) is booming. Among various AI approaches, generative models have received much attention in recent years. Inspired by these successes, researchers are now applying generative model techniques to de novo drug design, which has been considered as the “holy grail” of drug discovery. In this Perspective, we first focus on describing models such as recurrent neural network, autoencoder, generative adversarial network, transformer, and hybrid models with reinforcement learning. Next, we summarize the applications of generative models to drug design, including generating various compounds to expand the compound library and designing compounds with specific properties, and we also list a few publicly available molecular design tools based on generative models which can be used directly to generate molecules. In addition, we also introduce current benchmarks and metrics frequently used for generative models. Finally, we discuss the challenges and prospects of using generative models to aid drug design.

Artificial Intelligence in Interdisciplinary Life Science and Drug Discovery Research

“…Importantly, however, DL has enabled a number of applications that have so far been difficult or impossible to address using ML, which represents a major attraction. Among others, topical examples include chemical reaction modeling [ 12 , 13 ], generative compound design [ 14 ] or de novo protein structure prediction [ 15 ]. In these cases, some unprecedented advances have recently been made.…”

Deep Machine Learning for Computer-Aided Drug Design

“…In chemoinformatics and CADD, DL has in recent years substantially impacted chemical reaction prediction and automation of synthesis (e.g., Segler et al, 2018;Coley et al, 2019) as well as de novo compound design (e.g., Blaschke et al, 2020;Kotsias et al, 2020). These two areas have essentially dominated the use of DNNs in small molecule modeling and design and methodological aspects have been comprehensively reviewed (Struble et al, 2020;Tong et al, 2021). A flurry of recent publications reports different DNN architectures and protocols for generative de novo compound design.…”

Magicmol - Fast and variable synthetic accessibility molecule generative model with reinforcement learning

“…Lots of experiments [7,8,9] had confirmed the feasibility of RNN-based models, and they are capable of generating novel molecules. However, that's not the whole story.…”