Amgen trained antibody language models on NVIDIA BioNeMo and DGX Cloud, reaching three-month goals in four weeks.
Biologics discovery is slow and costly across huge molecule spaces. Amgen used NVIDIA DGX Cloud, BioNeMo and RAPIDS to train and analyse protein language models, five of them antibody-specific. The page reports three-month objectives met in four weeks, structure predictions in as little as 20 seconds, 20-30x faster multiple sequence alignments and up to 100x faster post-training analysis.
NVIDIA is a computing and AI company whose BioNeMo and Clara platforms provide models and accelerated tools for drug discovery, genomics and medical imaging.
This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.
Published by NVIDIA on its own site — read the original case study on nvidia.com ↗
Related use cases
- 01Biofy cut infectious disease diagnosis from five days to four hours with an NVIDIA-accelerated genome pipeline.
- 02A nonprofit built a medical knowledge LLM platform on NVIDIA NIM for 17,000+ practitioners in 19 countries.
- 03Astellas trained its own antibody language models on NVIDIA BioNeMo to predict antibody properties before measurement.
- 04Deloitte built its Quartz Atlas AI drug discovery platform on NVIDIA BioNeMo, DGX Cloud and NIM microservices.
- 05OpenAI's dedicated healthcare vertical page/launch post.
- 06Frontier reasoning model built for biology, drug discovery and translational medicine; named qualified customers include Amgen, Moderna, Allen Institute, and Thermo Fisher Scientific.