More than 200 biopharmaceutical companies use NVIDIA BioNeMo to scale digital biology solutions

eWEEK’s content and product recommendations are editorially independent. We may earn money when you click on links to our partners. Find out more.

At SuperComputing24 (#SC24) in Atlanta, Georgia, NVIDIA announced that more than 200 biopharmaceutical and life sciences companies, academic institutions and artificial intelligence researchers are adopting the company’s open-source BioNeMo Framework. SC24 brings together leaders from the technology, research and scientific communities to discuss the future of supercomputing and its role in solving the world’s most pressing challenges. BioNeMo combines advanced artificial intelligence models with accelerated computing to process massive data sets, offering a new level of supercomputing for pharmaceutical innovation. Kimberly Powell, NVIDIA’s vice president of healthcare, highlighted the platform’s potential to advance life-saving treatments.

“The convergence of artificial intelligence, accelerated computing and expanding data sets offers unprecedented opportunities for the pharmaceutical industry, as evidenced by the recent Nobel Prizes in Chemistry,” Powell said. “To help unravel the complexities of biological systems, we have introduced the open-source BioNeMo Framework, which will enable researchers around the world to accelerate the development of life-saving treatments.”

Industry leaders support innovation

Leading organizations have already joined BioNeMo, including Argonne National Laboratory, Genentech, Weights & Biases and other biotechnology and computational science pioneers. Researchers such as Arvind Ramanathan, leader of the computational science group at Argonne National Laboratory, have praised the framework, highlighting its ability to scale the training of biological models without requiring advanced computational knowledge.

“Argonne has provided biological models with billions of parameters that require specialized software to train in high-performance computing environments,” Ramanathan said. “With BioNeMo, Argonne and the broader biotech community have an enterprise-grade, open-source solution that allows researchers to easily scale the training of large biological models—in laboratories that might not otherwise have the computational expertise to do so.”

Learn more about AI healthcare software.

New generation BioNeMo platform

The platform also features tools such as NVIDIA NIM and BioNeMo Blueprints microservices that make it easier to deploy AI for drug discovery. NIM microservices can be deployed on-premises, in any data center or cloud, enabling rapid prediction of protein structures and molecular orientations. BioNeMo Blueprints offers customizable AI workflows that simplify complex processes such as 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. The researchers found that the tool speeds up protein structure prediction by up to five times.
• DiffDoc 2.0: This model, which predicts molecular orientation 6.2 times faster and 16 percent more accurately, is proposed by the MIT study and trained on the gold standard PLINDER dataset, providing faster and more accurate molecular docking predictions critical to drug development.
• MPNN protein and RF diffusion: These models are accelerating the development of new proteins and the development of the next generation of therapeutics.

More than 200 companies, including start-ups and global pharmaceutical leaders, have already implemented BioNeMo in their drug discovery efforts. Cloud service providers and systems integrators such as AWS, Deloitte and Accenture are also deploying BioNeMo solutions in enterprises around the world, further expanding their reach.

Learn more about how GenAI is changing healthcare.