Reinforcement Learning and Graph Neural Networks for Designing Novel Drugs with Optimized Affinity: Application to SARS-CoV-2

Drugs are generally designed for a specific target protein. Recent studies have demonstrated the capability of deep learning-based models to accelerate and cheapen the drug development process. The proposed deep learning models can generate novel molecules with optimized drug-like properties. However, the properties addressed are often limited and may be misleading. This is because they do not reflect the complete information about the binding affinity of the designed drug and the target protein. In this work, we exploit the state-of-The-Art progress made in drug-Target-Affinity (DTA) prediction to assess the binding affinity of drugs generated by a developed molecular generator against the corona-virus main protease (SARS-CoV-2 Mpro). The molecular generator is a recurrent neural network-based model, while the DTA predictor is a graph neural network (GNN), famously known as GraphDTA. We train the molecular generator using reinforcement learning (RL) to optimize the GraphDTA-predicted score. As this is the first benchmark of this kind (to the best of our knowledge), we report our benchmarking results;of 1.79% desirability;with the hope of motivating future improvements in this regard. © 2022 IEEE.

ELECTRA-DTA: a new compound-protein binding affinity prediction model based on the contextualized sequence encoding.

MOTIVATION: Drug-target binding affinity (DTA) reflects the strength of the drug-target interaction; therefore, predicting the DTA can considerably benefit drug discovery by narrowing the search space and pruning drug-target (DT) pairs with low binding affinity scores. Representation learning using deep neural networks has achieved promising performance compared with traditional machine learning methods; hence, extensive research efforts have been made in learning the feature representation of proteins and compounds. However, such feature representation learning relies on a large-scale labelled dataset, which is not always available. RESULTS: We present an end-to-end deep learning framework, ELECTRA-DTA, to predict the binding affinity of drug-target pairs. This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding. In addition, ELECTRA-DTA leverages a squeeze-and-excitation (SE) convolutional neural network block stacked over three fully connected layers to further capture the sequential and spatial features of the protein sequence and SMILES for the DTA regression task. Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset. In target selection and drug repurposing for COVID-19, ELECTRA-DTA also offers competitive performance, suggesting its potential in speeding drug discovery and generalizability for other compound- or protein-related computational tasks.

Generating novel molecule for target protein (SARS-CoV-2) using drug-target interaction based on graph neural network.

The transmittable spread of viral coronavirus (SARS-CoV-2) has resulted in a significant rise in global mortality. Due to lack of effective treatment, our aim is to generate a highly potent active molecule that can bind with the protein structure of SARS-CoV-2. Different machine learning and deep learning approaches have been proposed for molecule generation; however, most of these approaches represent the drug molecule and protein structure in 1D sequence, ignoring the fact that molecules are by nature in 3D structure, and because of this many critical properties are lost. In this work, a framework is proposed that takes account of both tertiary and sequential representations of molecules and proteins using Gated Graph Neural Network (GGNN), Knowledge graph, and Early Fusion approach. The generated molecules from GGNN are screened using Knowledge Graph to reduce the search space by discarding the non-binding molecules before being fed into the Early Fusion model. Further, the binding affinity score of the generated molecule is predicted using the early fusion approach. Experimental result shows that our framework generates valid and unique molecules with high accuracy while preserving the chemical properties. The use of a knowledge graph claims that the entire generated dataset of molecules was reduced by roughly 96% while retaining more than 85% of good binding desirable molecules and the rejection of more than 99% of fruitless molecules. Additionally, the framework was tested with two of the SARS-CoV-2 viral proteins: RNA-dependent-RNA polymerase (RdRp) and 3C-like protease (3CLpro).