Amgen needed to train custom protein language models on proprietary biologics data, but sparse public models, long screening cycles, and expensive post-training analysis slowed its ability to evaluate and optimize candidate molecules.
Reported impact
Amgen shortened the path from initial access to model training to just a few days, achieved up to 100x faster post-training analysis with RAPIDS, and reported protein structure predictions as fast as 20 seconds per structure, enabling faster and more iterative biologics discovery.
Amgen used NVIDIA DGX Cloud and the NVIDIA BioNeMo service to build and fine-tune custom biomolecular language models for biologics discovery. Researchers start with vast protein-sequence and proprietary assay datasets, then use DGX Cloud instances with eight A100 80GB GPUs to pretrain and adapt models that can reason about protein properties, structures, and side effects. NVIDIA Base Command Platform handles job scheduling and orchestration, while RAPIDS accelerates post-training analysis such as large-input reading and clustering of generated results. The resulting workflow lets Amgen move from raw data to large-model training in a matter of days, generate candidate molecules more quickly, and run protein structure predictions in seconds instead of waiting on much slower conventional analysis. That gives the biologics organization a reusable AI platform for design, screening, and optimization across multiple therapeutic programs.
Protein-sequence and proprietary biologics data are loaded into DGX Cloud training jobs, BioNeMo models are pretrained and fine-tuned, Base Command orchestrates the work, RAPIDS accelerates post-training analysis, and the outputs feed biologics design and structure-prediction workflows.
BioNeMo on DGX Cloud is a turnkey solution that enabled Amgen to get up and running quickly, moving from initial login to training large models in just a few days.
Faster protein structure predictions-as fast as 20 seconds per structure.
They leveraged NVIDIA DGX Cloud and NVIDIA BioNeMo for rapid training and fine-tuning of protein LLMs and NVIDIA RAPIDS for up to 100X faster post-training analysis.
Using NVIDIA DGX Cloud and BioNeMo, Amgen trains large language models on their proprietary data to help predict properties of proteins.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Sep 22, 2026 DELFI Diagnostics DELFI Diagnostics needed to speed genomic analysis for cancer screening and therapeutic monitoring, but CPU-bound alignment and somatic variant-calling steps created turnaround-time and cost bottlenecks that limited how… 10–20 business days DeepSomatic · MutectCaller · NVIDIA Parabricks NVIDIA Sample Jul 10, 2026 Astellas Pharma Inc. Astellas needed to shorten the slow handoff between experimental scientists and computational chemists in early drug discovery so more researchers could use structure prediction and affinity screening without waiting on… More than 50 regular users and over 2,000 total users within four months NVIDIA BioNeMo · NVIDIA Boltz-2 NIM · NVIDIA DGX H100/H200 NVIDIA Sample Apr 23, 2026 Biofy Hospitals needed pathogen identification and antibiotic-resistance analysis much faster than five-day culture and antibiogram workflows, but CPU-bound genomic processing and limited AI expertise made it hard to turn… 100,000+ synthetic DNA sequences generated by the biology model Abby · H100 Tensor Core GPUs · NVIDIA CUDA-accelerated libraries 