Bayer and Google partner to use TPUs for quantum chemistry calculations to accelerate drug discovery.
The partnership between Bayer and Google Cloud is set to leverage the power of Google’s Tensor Processing Units (TPUs) to accelerate and scale Bayer’s quantum chemistry calculations. This will involve quantum mechanics being applied to computer-aided drug discovery, enabling the in-silico modelling of biological and chemical systems. The two companies aim to demonstrate that fully quantum mechanical modelling of protein-ligand interactions is possible, as well as determine the scientific and economic viability of large-scale density functional theory calculations for practical applications.
The collaboration is part of Bayer’s ambition to be among the leading innovators, investing in novel and disruptive technologies to solve complex problems. The company has previously employed Accenture’s AI clinical data collection and management tool to accelerate drug development and improve patient outcomes.
Biogen and Accenture Labs have also signed a collaboration agreement to develop a quantum-enabled molecular comparison application, and the industry is exploring the potential for AI to improve manufacturing processes by predicting when upkeep work would be necessary.
The use of AI and machine learning for drug discovery is becoming increasingly popular in the industry, in order to make the drug development process more effective. Google Cloud’s TPUs are custom-developed, application-specific circuits that are designed to minimize the time-to-accuracy when training large, complex network models.
Thomas Kurian, CEO of Google Cloud, outlined that accelerating drug discovery may be one of the most important applications for AI and high-performance computing in the healthcare industry. The partnership between Bayer and Google Cloud is set to provide the necessary computing power to make this possible, with the aim being to make new discoveries with greater accuracy and speed.