Reinforced Adversarial Neural Computer for <i>de Novo</i> Molecular Design

TLDR

In silico modeling is a crucial milestone in modern drug design and development, yet deep learning methods are only just beginning to be applied in this area. The authors aim to develop RANC, a deep neural network that uses a generative adversarial network and reinforcement learning to design novel small‑molecule organic structures. RANC employs a differentiable neural computer as its generator, adding an explicit memory bank to enhance generation capabilities and mitigate common adversarial problems. RANC outperforms the prior DNN‑based ORGANIC model on multiple drug‑discovery metrics, producing more unique structures that pass medicinal chemistry filters, meet Muegge criteria, achieve high QED scores, and match key chemical feature distributions, indicating its promise for generating diverse, biologically relevant molecules.

Abstract

In silico modeling is a crucial milestone in modern drug design and development. Although computer-aided approaches in this field are well-studied, the application of deep learning methods in this research area is at the beginning. In this work, we present an original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL). As a generator RANC uses a differentiable neural computer (DNC), a category of neural networks, with increased generation capabilities due to the addition of an explicit memory bank, which can mitigate common problems found in adversarial settings. The comparative results have shown that RANC trained on the SMILES string representation of the molecules outperforms its first DNN-based counterpart ORGANIC by several metrics relevant to drug discovery: the number of unique structures, passing medicinal chemistry filters (MCFs), Muegge criteria, and high QED scores. RANC is able to generate structures that match the distributions of the key chemical features/descriptors (e.g., MW, logP, TPSA) and lengths of the SMILES strings in the training data set. Therefore, RANC can be reasonably regarded as a promising starting point to develop novel molecules with activity against different biological targets or pathways. In addition, this approach allows scientists to save time and covers a broad chemical space populated with novel and diverse compounds.