TandemAI and Mila are collaborating to apply machine learning approaches to drug discovery challenges. These frameworks have previously been successful in fields such as video game design and self-driving cars, but are being explored for the first time in molecular science to enable broader and more accurate virtual experiments and accelerate laboratory workflows. The partnership will also prioritize open science and responsible AI development, promoting transparency and knowledge sharing within the scientific community. “TandemAI was built on the belief that the marriage of AI and physically-based modeling can play a key role in shaping the future of drug discovery,” said Albert Pan, Chief Technology Officer (CTO) of TandemAI, outlining the partnership’s purpose to translate advances in AI to improved medicines for patients.
TandemAI and Mila advance AI for drug discovery
Thanks to a new partnership between TandemAI and Mila, World Model, a machine learning framework traditionally used in fields such as robotics and gaming, is now geared toward accelerating drug discovery. This represents a major departure from traditional approaches, as the application of these models to molecular science has so far been little explored. Researchers aim to simulate complex chemical interactions with greater accuracy. This ambition goes beyond simply accelerating research. The model is designed to provide a more comprehensive understanding of molecular behavior, potentially revealing previously inaccessible insights. Both TandemAI and Mila recognize the importance of broad access to research results and are committed to contributing to the open exchange of information in line with the organization’s values. This partnership will enable TandemAI to leverage Mila’s extensive network of deep learning experts and established innovation ecosystem to further strengthen its research capabilities.
Founded by Professor Yoshua Bengio, Quebec’s Mira Institute for Artificial Intelligence has established itself as the world’s largest academic AI research center dedicated to deep learning, with a very large community. “At Mila, we are focused on AI research that connects to real-world challenges,” said Mila Executive Vice President Stéphane Letourneau, highlighting the institute’s commitment to the practical application of artificial intelligence. TandemAI’s integrated platform, TandemViz, is expected to provide Mila researchers with a hands-on environment to translate basic AI research into tangible results, potentially leading to improved medicines for patients.
World models applied to chemical and atomic systems
Although these models have shown success in simulating dynamic environments, their use in understanding chemical and atomic-level systems remains a largely unexplored area, prompting a new collaboration between TandemAI and Mila. This partnership aims to bridge the gap between established AI technologies and the nuanced demands of pharmaceutical research, and has the potential to reshape the way new treatments are identified and developed. Central to this effort is the development of world models that can accurately capture the physical principles governing chemical interactions. The collaboration between TandemAI and Mila is focused on technological advancement and the commitment to open science and responsible AI development that underpins the entire project. Stéphane Letourneau, executive vice president at Mila, emphasized this point, saying, “Drug discovery is an area where machine learning can make real and lasting contributions to human health and beyond.” This commitment to responsible innovation suggests an intentional approach that prioritizes ethical considerations alongside scientific advances and ensures that the benefits of these advances are widely available.
Drug discovery is an area where machine learning can make real and lasting contributions to human health and beyond.
Stéphane Letourneau, Mila Executive Vice President
