Novo Nordisk, Microsoft Collaborate on Drug Discovery Using AI

Novo Nordisk and Microsoft have announced a new strategic collaboration combining Microsoft’s computational services, cloud, and artificial intelligence (AI) with Novo Nordisk’s drug discovery, development, and data science capabilities. Through the partnership, Microsoft will provide its AI technology, foundational science models, and expertise to Novo Nordisks data scientists and domain experts for early research and development. This, according to Novo Nordisks, will accelerate its R&D.

“We are very excited about this new partnership that allows us to work closely together with key experts from Microsoft as we look to expand our digital science and AI capabilities,” said Lars Fogh Iversen, senior vice president, Digital Science & Innovation at Novo Nordisk. “Together, we are on a path to enable faster and scaled use of AI in drug discovery, ultimately leading to more breakthrough innovations and efficiency gain to better serve the needs of patients.”

While the AI model will eventually be applied to a range of uses, there are two currently in execution. One use case is focused on automated summarization and analysis of information from literature, patents, scientific reports, and discussion forums to gain scientific insights. The second use case will develop models to predict an individual’s risk of developing atherosclerosis. Atherosclerosis is a cardiovascular disease caused by build-up of fats, cholesterol, and other substances in and on the artery walls. In addition to predicting risk, the AI will also be used to identify novel targets and establish biomarkers of the disease.

Using a platform approach to AI, the companies are taking a set of large models that are trained for multiple tasks. This will allow new projects and use cases to be started on a continuous basis throughout the reported multi-year collaboration.

“The collaboration with Novo Nordisk is a great opportunity for us to collectively advance the state of the art of AI itself and apply it in a way that amplifies the creativity of human experts,” said Vijay Mital, corporate vice president, AI Architecture & Strategy in Microsoft’s Technology & Research division. “To achieve this ambition, AI needs to learn from every type of information that subject matter experts find valuable and that requires the type of close interaction between multiple disciplines we see in this partnership.”