Supercomputing for Drug Design
With the high research costs and expensive failure rates of the drug design & discovery process, computational methods have been increasingly exploited by both academia and the pharmaceutical industry. The COVID pandemic has exemplified the need for a "lightspeed approach" to drug design, a problem for which computational methods are well-suited to address.
The Big Data revolution of the past decade has hugely increased the efficacy of computational drug design and virtual screening techniques. However with the advent of faster supercomputers and exascale computation, we are witnessing a renewed look at heavier physics-based algorithms--Big Compute and the Exascale revolution. Can we take advantage of this to upgrade drug design to the next level?
I am Bharath Raghavan, a doctoral student at Forschungszentrum Jülich, one of the foremost supercomputing centers in Europe, and my research mission is to accelerate the application of high performance computing to automate drug design and discovery. Highly scalable quantum simulations, coupled with complex deep learning neural networks, can give us intricate atomic-level insights of pharmaceutically relevant enzyme function. I believe that this deep quantum-level understanding of our biology can greatly streamline the drug design process by promoting the rational and scientific design of inhibitors. The wider promulgation of supercomputing technologies will allow the scientific community to unlock the huge potential of AI-accelerated quantum simulations for pharmacology. Contact me if you wish to collaborate on these exciting ideas!
The Big Data revolution of the past decade has hugely increased the efficacy of computational drug design and virtual screening techniques. However with the advent of faster supercomputers and exascale computation, we are witnessing a renewed look at heavier physics-based algorithms--Big Compute and the Exascale revolution. Can we take advantage of this to upgrade drug design to the next level?
I am Bharath Raghavan, a doctoral student at Forschungszentrum Jülich, one of the foremost supercomputing centers in Europe, and my research mission is to accelerate the application of high performance computing to automate drug design and discovery. Highly scalable quantum simulations, coupled with complex deep learning neural networks, can give us intricate atomic-level insights of pharmaceutically relevant enzyme function. I believe that this deep quantum-level understanding of our biology can greatly streamline the drug design process by promoting the rational and scientific design of inhibitors. The wider promulgation of supercomputing technologies will allow the scientific community to unlock the huge potential of AI-accelerated quantum simulations for pharmacology. Contact me if you wish to collaborate on these exciting ideas!