GTC -- NVIDIA today announced a strategic partnership with Schrödinger that harnesses NVIDIA DGX A100™ systems to further expand the speed and accuracy of Schrödinger’s computational drug discovery platform and enable rapid, accurate evaluation of billions of molecules for potential development of therapeutics.
The companies will optimize Schrödinger’s software platform — designed to model and predict the properties of novel molecules — for the NVIDIA DGX SuperPOD™, which is built with NVIDIA DGX A100 systems and NVIDIA InfiniBand HDR networking.
The work includes the physics-based modeling in Schrödinger’s product suite, as well as support for NVIDIA Clara™ Discovery, a collection of state-of-the-art AI frameworks, applications and pre-trained models for the most advanced computational drug discovery. Additionally, the companies will partner on scientific and research breakthroughs to further advance physics-based computing and machine learning for drug discovery.
For each potential drug candidate, Schrödinger routinely evaluates tens of thousands of molecules with its most computationally intensive physics-based approaches. This requires hundreds of thousands of hours of GPU time on high-performance computers.
Through the collaboration, the entire pharmaceutical industry comprising over 3,000 companies — from startups to multinationals — will be able to further accelerate drug discovery at supercomputing scale. The joint solution will enable companies of all sizes to simulate molecular combinations with physics and AI to identify and optimize the most promising compounds for potential therapeutic use. Pharmaceutical companies can run this research on their own easy-to-deploy private clouds featuring the Schrödinger platform running on NVIDIA DGX SuperPOD, which is available to install on premises or in a colocation facility.
“The predictive modeling built into our platform is designed to dramatically expand and accelerate the search for high-quality therapeutic molecules, and NVIDIA is a key technology partner in this work,” said Patrick Lorton, chief technology officer at Schrödinger. “Our advanced computational software helps the world’s biggest pharma companies explore more of the chemical space and reach high-quality candidates more quickly, with far less compute cost, than traditional methods. We’re proud to be working with NVIDIA to make that process run even more smoothly.”
NVIDIA research and engineering teams are working to advance and optimize the Schrödinger suite to take advantage of the NVIDIA Ampere architecture and its Multi-Instance GPU technology. Customers will be able to easily deploy Schrödinger software on a single DGX system or a cluster of 20 or more to create a DGX SuperPOD. This allows scaling the Schrödinger platform to dozens of drug programs and screening and evaluating billions of molecules a week.
“Computational drug discovery is improving accuracy with Schrödinger’s advanced combination of simulation with machine learning,” said Kimberly Powell, vice president of healthcare at NVIDIA. “Together, we’re giving the pharmaceutical industry a scientific instrument that delivers super-high-throughput lead generation to improve and accelerate the success of drug candidates.”