Graph Neural Networks for COVID-19 Drug Discovery
Authors:
- 10 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5646-5648
Abstract
Deep learning has led to major advances in fields like natural language processing, computer vision, and other Euclidean data domains. Yet, many important fields have data defined on irregular domains, requiring graphs to be explicitly modeled. One such application is drug discovery. Recently, research has found that using graph neural network (GNN) models, given enough data, can perform better than using human-engineered fingerprints or descriptors in predicting molecular properties of potential antibiotics.We explore these state-of-the-art AI models on predicting desirable molecular properties for drugs that can inhibit SARS-CoV-2. We build upon the GNN models with ideas from recent breakthroughs in geometric deep learning, inspired by the topologies of the molecules. In this poster paper, we present an overview of the drug discovery framework, drug-target interaction framework, and GNNs. Preliminary results on two COVID-19 related datasets are encouraging, achieving a ROC-AUC of 0.72 for FDA-approved chemical library screened against SARS-CoV-2 in vitro.Keywords
Funding Information
- Carnegie Mellon University
This publication has 7 references indexed in Scilit:
- Artificial intelligence in COVID-19 drug repurposingThe Lancet Digital Health, 2020
- Graph Signal Processing and Deep Learning: Convolution, Pooling, and TopologyIEEE Signal Processing Magazine, 2020
- Artificial intelligence, drug repurposing and peer reviewNature Biotechnology, 2020
- A Deep Learning Approach to Antibiotic DiscoveryCell, 2020
- Analyzing Learned Molecular Representations for Property PredictionJournal of Chemical Information and Modeling, 2019
- Machine learning in chemoinformatics and drug discoveryDrug Discovery Today, 2018
- Molecular graph convolutions: moving beyond fingerprintsJournal of Computer-Aided Molecular Design, 2016