At SuperComputing24 (#SC24) in Atlanta, Georgia, NVIDIA announced that over 200 biopharma and techbio companies, academic institutions, and AI researchers are adopting the company’s open-source BioNeMo Framework. The SC24 conference brings together leaders from tech, research, and scientific communities to discuss the future of supercomputing and its role in solving the world’s most pressing challenges. BioNeMo integrates advanced AI models with accelerated computing to handle massive datasets, offering a new level of supercomputing for pharmaceutical innovation. Kimberly Powell, NVIDIA’s vice president of healthcare, emphasized the framework’s potential to drive advancements in life-saving treatments.
“The convergence of AI, accelerated computing, and expanding datasets offers unprecedented opportunities for the pharmaceutical industry, as evidenced by recent Nobel Prize wins in chemistry,” Powell said. “To help unravel the complexities of biological systems, we’ve introduced the open-source BioNeMo Framework, which will enable researchers worldwide to accelerate the development of life-saving treatments.”
Industry Leaders Backing the Innovation
Leading organizations have already embraced BioNeMo, including Argonne National Laboratory, Genentech, Weights & Biases, and other biotech and computational science pioneers. Researchers like Arvind Ramanathan, a computational science group leader at Argonne National Laboratory, praised the framework, emphasizing its ability to scale biological model training without requiring advanced computational expertise.
“Argonne has contributed billion-parameter biological models that require specialized software to train across high-performance computing environments,” said Ramanathan. “With BioNeMo, Argonne and the broader biotech community gain an enterprise-level, open-source solution that enables researchers to easily scale the training of large biological foundation models—in labs that otherwise wouldn’t have the computational expertise to do so.”
Read more about AI healthcare software.
The Next-Generation BioNeMo Platform
This platform also introduces tools like NVIDIA NIM microservices and BioNeMo Blueprints, which simplify the deployment of AI for drug discovery. The NIM Microservices can be deployed on-premises or in any data center or cloud, offering rapid predictions for protein structures and molecule orientations. The BioNeMo Blueprints offer customizable AI workflows that simplify complex processes like virtual screening, reducing time and costs.
The platform supports the following industry-leading models:
- AlphaFold2: This deep learning model developed by Google DeepMind is designed to transform protein structure prediction. Researchers found that the tool accelerates protein structure predictions by up to five times.
- DiffDock 2.0: This model, which predicts molecular orientations 6.2 times faster and 16 percent more accurately, is offered by MIT research and trained on the gold-standard PLINDER dataset, delivering quicker and more accurate molecular docking predictions critical for drug design.
- ProteinMPNN and RFdiffusion: These models speed up novel protein design and development of next-generation therapeutics.
More than 200 companies, including startups and global pharma leaders, have already adopted BioNeMo to power their drug discovery efforts. Cloud providers and system integrators like AWS, Deloitte, and Accenture also deploy BioNeMo solutions to enterprises worldwide, further expanding its reach.
Learn more about how GenAI is transforming healthcare.