Biotechnology company Genentech is partnering with Nvidia to accelerate the discovery and development of new medicines using generative AI.
The collaboration will optimize Genentech's proprietary algorithms on Nvidia's DGX Cloud. Genentech also plans to use Nvidia's BioNeMo, a platform that simplifies and scales generative AI applications for computational drug discovery.
The initial focus will be on optimizing Genentech’s drug discovery AI models in its “lab in a loop” framework, which aims to understand complex biomolecular patterns and relationships to improve the success rate of R&D. The partnership hopes to streamline the lengthy and complex process of drug discovery and development.
Founded more than 45 years ago, Genentech discovers, develops, and commercializes medicines for serious medical conditions.
Using Large Language Models in Medicine
Large Language Models (LLMs) could help process medical information by translating medical reports into everyday language or generating structured, machine-readable data from recorded doctor-patient conversations.
Despite privacy concerns, LLMs have the potential to alleviate staff shortages in the healthcare sector and make medical care more humane by relieving medical staff of administrative tasks, says Prof. Dr. Felix Nensa, a radiologist and professor at the Institute for Artificial Intelligence in Medicine at Essen University Hospital.
Many major tech companies are also investing in medical AI. Deepmind and Google, for example, have formed Isomorphic Labs to bring AI to medical practice. Microsoft is exploring the use of GPT-4 to answer medical questions. Many experiments are also underway with chatbots for psychotherapy.