Computational Science Accelerates Research Innovation at Bristol Myers Squibb

BMS knew it needed to change how it provided compute for research, as neither traditional cloud nor traditional on-prem approaches were fully serving scientific needs. “To guarantee GPU availability and maximize computational resources, we decided to establish a centralized and modernized infrastructure for drug discovery. To pull this off, we needed a proven platform that could scale with us as we progressed along this journey. That is why we chose the NVIDIA DGX SuperPOD architecture, which included the capability to expand to cloud as needed, a colocation strategy for hosting, and an acceleration partner to clear all the early hurdles,” said Mayo.

NVIDIA DGX™ partner Equinix expertly managed the DGX SuperPOD infrastructure, colocation data center, and interconnectivity, while Mark III, an NVIDIA solutions partner, delivered crucial AI and operational expertise.

“Mark III’s expertise was the catalyst behind our rapid evolution from isolated, single-node use case to seamless, high-performance multi-node training, and it ensured we not only optimized our systems but continuously advanced through routine updates and adequate workload sizing,” said Brian Wong, Director of Research Computing at BMS. “The Equinix Private AI with DGX solution provided a ready-to-run AI platform without the operational headaches commonly associated with on-premises equipment,” added Wong.

As a result, scientists gained computational resources to scale up and out without additional headcount or expenses for system administration. Wong added, “Leveraging DGX SuperPOD with Equinix’s seamless integrations with public cloud providers ensured cost-effective data movement while achieving 55% overall cost savings compared to the prior model. Our scientists can now easily adjust resources to meet workload demands, increasing nodes for large language model (LLM) training when needed and reallocating them to deep learning tasks as required.”

After becoming operational in March 2024, the DGX SuperPOD has served as a centralized AI platform for BMS research teams, significantly enhancing capabilities in analyzing large-scale medical imaging data. One key project involves developing foundational AI models for oncology, leveraging CT and MR scans from clinical trials.

The BMS team utilized NVIDIA MONAI and the DGX SuperPOD for inference tasks to automatically segment lesions. To enhance robustness, the team trained the models using internal datasets through a self-supervised learning approach, employing mask image modeling.

The outcomes significantly accelerated research timelines, improving segmentation accuracy and processing efficiency. Additionally, BMS benchmarked its foundational model, trained on internal data, by fine-tuning it on public datasets for downstream tasks where it demonstrated strong performance. The foundational model now supports various downstream applications, providing a strong platform for continued innovation in oncology research and clinical decision-making. The DGX SuperPOD provided BMS with a centralized platform supporting the full AI lifecycle—from rapid model development and training to scalable, production-grade inference.

In immuno-oncology, predicting who will respond to a treatment is a major challenge. BMS researchers tackled this using large language models and transformers to analyze complex clinical trial data. The innovation was to treat diverse data—including genomics, lifestyle, and treatment details—as grammatical sentences, similar to natural language processing. By embedding this data alongside outcomes like survival and adverse events, BMS built a model that predicts patient outcomes with unprecedented accuracy.

Success ultimately hinged on training models with extensive data, combining internal clinical data, public datasets, and scientific literature. Leveraging the DGX SuperPOD’s computational power, BMS models outperformed standard baseline transformers, transforming their data into actionable insights that could revolutionize oncology treatment strategies.

With dedicated compute resources, extensive data, deep technical expertise, and urgent scientific questions,  researchers can now easily launch high-potential experiments. “By combining curiosity and courage with technology skills and capacity, we have assisted our research community in making innovative discoveries, all in the service of our patients,” adds Mayo. Looking forward, the successful implementation of the DGX SuperPOD has positioned BMS to leverage AI for continued innovation and advancements in drug discovery across all therapeutic areas and scientific functions.