The Convergence of HPC, AI and Big Data in Rapid-Response to the COVID-19 Pandemic

The “Force for Good” pledge of intellectual property to fight COVID-19 brought into action HPE products, resources and expertise to the problem of drug/vaccine discovery. Several scientists and technologists collaborated to accelerate efforts towards a cure. This paper documents the spirit of such a collaboration, the stellar outcomes and the technological lessons learned from the true convergence of high-performance computing (HPC), artificial intelligence (AI) and data science to fight a pandemic. The paper presents technologies that assisted in an end-to-end edge-to-supercomputer pipeline - creating 3D structures of the virus from CryoEM microscopes, filtering through large cheminformatics databases of drug molecules, using artificial intelligence and molecular docking simulations to identify drug candidates that may bind with the 3D structures of the virus, validating the binding activity using in-silico high-fidelity multi-body physics simulations, combing through millions of literature-based facts and assay data to connect-the-dots of evidence to explain or dispute the in-silico predictions. These contributions accelerated scientific discovery by: (i) identifying novel drug molecules that could reduce COVID-19 virality in the human body, (ii) screening drug molecule databases to design wet lab experiments faster and better, (iii) hypothesizing the cross-immunity of Tetanus vaccines based on comparisons of COVID-19 and publicly available protein sequences, and (iv) prioritizing drug compounds that could be repurposed for COVID-19 treatment. We present case studies around each of the aforementioned outcomes and posit an accelerated future of drug discovery in an augmented and converged workflow of data science, high-performance computing and artificial intelligence. © 2022, Springer Nature Switzerland AG.

Massively Parallel Processing Database for Sequence and Graph Data Structures Applied to Rapid-Response Drug Repurposing

In this paper, we present the application of a massively parallel-processing graph database for rapid-response drug repurposing. The novelty of our approach is that the scalable graph database is able to host a knowledge graph of medically relevant facts integrated from multiple knowledge sources and also act as a computational engine capable of in-database protein sequence analytics. We demonstrate the performance of the graph database on a real-world use-case to hypothesize cures for COVID-19, leveraging its built-in accelerated protein-sequence matching capabilities at unprecedented scale (to simultaneously handle data size and query latency requirements for interactive research). Based on supporting evidence from medical literature, we show that results generated by computing similarity of COVID-19 virus proteins across 4 million other open-science sequences and intelligently traversing over a 150 billion facts from open-science medical knowledge produces biologically insightful results. By presenting sample queries and extending application to use-cases beyond COVID-19, we demonstrate the use and value of the novel database for hypotheses generation in reducing the time-to-insight and increasing researcher productivity with interactivity. © 2020 IEEE.

Deep Learning Predicts Protein-Ligand Interactions

This paper presents results from a rapid-response industry-academia collaboration for virtual screening of chemical, natural and virtual drug ligands towards identifying potential therapeutics for COVID-19. Compared to resource-intensive traditional approaches of either conducting high- throughput screening in a lab or in-silico molecular dynamics simulations on supercomputers, we have developed an open- source framework that leverages artificial intelligence (AI) to accurately and quickly predict the binding potential of a drug ligand with a target protein. We have trained a novel molecular-highway graph neural network architecture using the entirety of the BindingDB database to predict the probability of a drug ligand binding to a protein target. Our approach achieves a prodigious 98.3% accuracy with its predictions. Through this paper, we disseminate our source code and use the AI model to screen both public (ChEMBL, DrugBank) and proprietary databases. Compared to other AI-based methods, our approach outperforms the state-of-the-art on the following metrics - (i) number of molecules currently undergoing active clinical trials, (ii) number of antiviral drugs correctly identified, (iii) accuracy despite not needing active-site priors, and (iv) ability to screen more compounds in unit time. © 2020 IEEE.