The IMPECCABLE workflow integrates machine learning (ML) and physics-based (PB) methods to accelerate drug discovery. By incorporating multiple ML and PB approaches, it leverages their strengths while mitigating individual limitations. The workflow is being scaled on exascale machines to efficiently identify potential drug candidates for various target proteins. Image: Peter V. Coveney, University College London
This project is using exascale supercomputers to develop a personalized digital twin (DT) of the human body. The team will simulate the entire cardiovascular system of the human body, and thus will afford clinicians the ability to make personalized predictions about treatment outcomes. Further they will combine machine learning and physics-based methods to accelerate the process of drug discovery.
The advent of exascale computing has opened up immense possibilities to realize a fully personalized DT of the human body. DT technology will not only enable clinicians to make reliable and actionable predictions to support clinical decision making, but it will also facilitate the adoption of informed lifestyle choices that support healthy ageing and wellbeing. To address any challenges, the INCITE team’s goal is to advance the modeling and simulation of the human body in health and disease such that they are at the forefront of the development of human DTs for applications in personalized medicine and healthcare. This requires access to large-scale computing resources. The team developed a method called IMPECCABLE that couples ML and PB methods to accelerate the drug discovery process, each compensating for the limitations of the other. The main goal of this project is to implement IMPECCABLE at scale on exascale machines and identify potential drug candidates for various target proteins. In addition to the drug design aspect, the team also aims to develop a related method enabling them to assess drug resistance in target proteins.
