Transforming drug discovery: Novo Nordisk uses the power of AI and Azure with Microsoft Research

Developing high-quality medicine is a resource-intensive endeavor that requires collaboration across Novo Nordisk.  Novo Nordisk aimed to scale a pipeline of drug discovery, development, and data science capabilities with AI and machine learning. 

In partnership with Microsoft Research, the teams built a Novo Nordisk AI platform on Azure AI and data stacks.  Novo Nordisk amplified its culture of innovation by leveraging Microsoft Azure platform’s AI capabilities across many use cases.

The teams recently published initial results with predictive AI models for advanced risk detection in cardiovascular diseases, including an algorithm that can predict patients’ cardiovascular risk better than the best clinical standards. 

As the researcher steps into the lab, donning their white coat, the room buzzes with the energy of advancement. This is a place where human curiosity and technology coalesce, and it’s where AI isn’t just a concept, but a trusted partner in the pursuit of better medicine. Here at Novo Nordisk, a culture of innovation is unlocking potential through transformation at scale.

Recently named one the world's most innovative companies, Novo Nordisk is taking a holistic approach to problem solving. Rather than isolating one or two specific use cases, focus is placed on amplifying an existing culture of innovation where life scientists, computational biologists, and data scientists use and contribute to the Microsoft Azure platform’s AI capabilities across many use cases. Their efforts have been collaborative with Microsoft Research and evolved to incorporate AI as a key business asset.

With this approach, Novo Nordisk is pioneering the discovery of innovative medicines. Welcome to the future of research and development.

Deep collaboration between Novo Nordisk and Microsoft

The combination of Novo Nordisk’s industry-leading domain expertise and Microsoft’s industry-leading applied AI expertise is opening new and exciting possibilities to shape the future of life sciences. Novo Nordisk life scientists and data scientists worked closely with Microsoft Research colleagues and tackled multiple use cases, including regulatory affairs, early research, drug discovery, and trial design. The teams collaboratively built a Novo Nordisk AI platform on Azure AI and data stacks:

Unification: A single place to discover data and models.
Advanced reasoning: A copilot tool for researchers to conduct reasoning with data and AI.
Collaboration: A means for experts to share their reasoning chains as templates to help others.
Governance: Auditing of reasoning chains and tracking of how data and models are used.
Build bigger: An AI factory allowing data scientists and computational biologists to use these learnings to build new and more powerful models and share them with subject matter experts.

Microsoft Azure OpenAI Service is used alongside a wide array of additional core infrastructure, such as Azure Cosmos DB for developing AI-powered apps and Azure Kubernetes Service (AKS) for deploying containers on managed Kubernetes. While scientific discoveries transpire in labs, learning and collaboration are amplified through a range of Microsoft Power Platform tools like Power BI and Power Apps.

More about this diagram

Altogether, this unique AI platform empowers cross-functional stakeholders across the organization with a scalable and generalizable end-to-end science and research platform that can adapt to meet evolving needs. The partnership between Novo Nordisk and Microsoft Research is highly collaborative, and both teams work closely together to develop and build these pipelines and models so that Novo Nordisk can use, reuse, and fine-tune even beyond the partnership.

Accelerating scientific discovery: AI and more than 100 years of data

With more than 100 years of insulin research, Novo Nordisk has an extensive amount of data and core expertise around diabetes. This has stimulated an expansion into patient care areas adjacent to diabetes, such as obesity, heart disease, and liver disease. Now, initial results from Azure are encouraging the team to push beyond what was previously possible. “Using data with AI to define patients' risk of developing diseases will help us provide better treatments. This is precision medicine, and it's going to be important for us to operate in the future,” says Karin Conde-Knape, Senior Vice President of Global Drug Discovery at Novo Nordisk.

Using data with AI to define patients’ risk of developing diseases will help us provide better treatments. This is precision medicine, and it’s going to be important for us to operate in the future.

Karin Conde-Knape, Senior Vice President of Global Drug Discovery, Novo Nordisk

Novo Nordisk’s innovative culture lends itself to iterative improvement, where continual progress materializes into significant steps forward. The teams recently published some of the early results with predictive AI models that center around advanced risk detection in cardiovascular diseases, the leading cause of death globally. ¹ “I'm proud of what the teams are doing in cardiovascular disease. They've brought forward an algorithm that can predict patients' cardiovascular risk better than the best clinical standards out there,” says Lars Fogh Iversen, Senior Vice President of Digital Science and Innovation at Novo Nordisk.

I’m proud of what the teams are doing in cardiovascular disease. They’ve brought forward an algorithm that can predict patients’ cardiovascular risk better than the best clinical standards out there.

Lars Fogh Iversen, Senior Vice President of Digital Science & Innovation, Novo Nordisk

The intersection of human curiosity and technology is accelerating how innovative medicine is discovered. In Novo Nordisk's labs, scientists, researchers, and collaborators alike are bringing forward the next generation of medicine.

1 - Cardiovascular diseases (CVDs) (who.int) 

 Discover more about Novo Nordisk on Facebook, Instagram, LinkedIn, X/Twitter, and YouTube. 