Genentech, a prominent member of the Roche Group, is at the forefront of utilizing generative AI to revolutionize the process of discovering and developing new therapeutics, ultimately enhancing the efficiency of delivering treatments to patients. In a strategic collaboration with NVIDIA, a leading technology company, Genentech is set to optimize and accelerate its proprietary algorithms by leveraging the expertise of both entities. The collaboration will specifically focus on enhancing Genentech’s drug discovery AI models within its innovative “lab in a loop” framework.
NVIDIA will play a pivotal role in accelerating these models using the advanced capabilities of the NVIDIA DGX Cloud, providing dedicated instances of AI supercomputing and software. Genentech plans to leverage NVIDIA BioNeMo, a domain-specific platform that facilitates the customization of models at scale, streamlining the application of generative AI in computational drug discovery.
Key elements of the collaboration include:
Accelerating Models with DGX Cloud: NVIDIA will collaborate with Genentech to optimize and speed up its models on the NVIDIA DGX Cloud, which offers dedicated instances of AI supercomputing.
Utilizing BioNeMo for Customization: Genentech intends to utilize NVIDIA BioNeMo, a versatile platform, to customize generative AI models and integrate them into computational drug discovery workflows.
Focus on “Lab in a Loop” Framework: The primary focus of the collaboration will be on optimizing Genentech’s drug discovery AI models within its “lab in a loop” framework. This iterative framework aims to generate and explore molecular designs with predicted properties, utilizing experimental data to inform generative computational models.
The goal of this collaboration is to enhance the efficiency of drug discovery and development by leveraging AI to bridge the gap between laboratory experiments and computational algorithms. By optimizing and customizing generative AI models, the collaboration seeks to significantly shorten the timeline of drug discovery, leading to greater success in developing novel therapeutics.
Aviv Regev, Executive Vice President and Head of Genentech Research & Early Development (gRED), expressed the potential of this collaboration, stating, “Collaborating with NVIDIA, and introducing generative AI, has the power to turbocharge the discovery and design of therapeutics that will improve the lives of patients across the world.”
The collaboration aligns with the broader industry goal of streamlining drug discovery processes, making them more efficient, cost-effective, and impactful. The integration of AI models into drug discovery workflows has the potential to revolutionize the pharmaceutical landscape, offering scientists the tools to rapidly identify potential drug molecules and interactions, ultimately benefiting patients worldwide.
As both teams work together to optimize Genentech’s custom-developed models, the collaboration is poised to uncover new insights, improve existing frameworks, and contribute to the continuous evolution of AI applications in the biotech industry. Kimberly Powell, Vice President of Healthcare at NVIDIA, emphasized the transformative role of AI in healthcare and life sciences, stating, “Together, NVIDIA and Genentech are unlocking scientific innovation by developing and implementing AI models and algorithms that enable us to rapidly iterate and unearth insights.”
