Genentech, a member of the Roche Group, is pioneering the use of generative AI to discover and develop new therapeutics and deliver treatments to patients more efficiently.
A new collaboration between Genentech, the biotechnology pioneer, and NVIDIA aims to transform the discovery and development of new medicines by bringing together experts from each company to optimize and accelerate Genentech’s proprietary algorithms.
NVIDIA will work with Genentech to accelerate these models on NVIDIA DGX Cloud, which provides dedicated instances of AI supercomputing and software hosted by NVIDIA cloud service provider partners.
Genentech plans to use NVIDIA BioNeMo, which enables biotech companies to customize models at scale, and integrate BioNeMo cloud application programming interfaces directly into computational drug discovery workflows.
BioNeMo, now generally available as a training service, is a domain-specific platform that simplifies, accelerates and scales generative AI applications for computational drug discovery. It allows researchers to pretrain or fine-tune state-of-the-art models on DGX Cloud.
The collaboration will initially focus on optimizing Genentech’s drug discovery AI models in its “lab in a loop” framework. The goal: To allow its researchers to understand complex biomolecular patterns and relationships to truly disrupt drug development and improve the success rate of R&D, and to empower scientists to deliver multiplicative, rather than linear or additive, benefits for patients and the broader healthcare ecosystem.
“Our collaboration with NVIDIA builds on our long history of successfully inventing and deploying technology in ways that were not initially apparent to others,” said Aviv Regev, executive vice president and head of Genentech Research & Early Development (gRED). “We were the first biotech company to leverage molecular biology for drug discovery and development, which changed the world. We pioneered antibody therapeutics that became the paradigm of treatment. And now, we have brought AI, the lab and the clinic together to uncover otherwise inaccessible patterns in vast quantities of data, and to design experiments to test those patterns. 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.”
Streamlining Drug Discovery With Computation
Drug discovery and development is currently a lengthy, complicated and costly process. Drug targets for novel medicines are difficult to predict, as is successfully developing a molecule as a potential therapeutic. AI can play a transformational role because generative and other AI models can help scientists rapidly identify potential drug molecules and interactions by training on large-scale datasets.
For Genentech, using AI helps bridge the gap between lab experiments and computational algorithms.
The company’s R&D group, gRED, has already done significant work using AI — across multiple modalities — to discover and develop novel therapeutics while learning more about the building blocks of biology and diseases.
Teams from Genentech and NVIDIA will now work together to optimize Genentech’s custom-developed models to shorten this time-consuming process of drug discovery and development and lead to greater success.
Putting AI in a Loop
Genentech’s “lab in a loop” is an iterative framework for generating and exploring molecular designs with predicted properties. It aims to use experimental data to inform generative computational models and better optimize future molecular designs. NVIDIA will help Genentech optimize its framework by accelerating training and inference of Genentech’s drug discovery models.
Through this collaboration, NVIDIA AI experts will gain insights into AI-related challenges in drug discovery and development. NVIDIA plans to use these insights to improve its BioNeMo platform and others to further accommodate the requirements of models used by the biotech industry.
“AI can play a transformational role in accelerating drug discovery and development — as it has across many parts of healthcare and life sciences,” said Kimberly Powell, vice president of healthcare at NVIDIA. “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.”