For huge language models that produce high-quality proteins that can expedite medication creation and contribute to a more sustainable environment, scientists employ NVIDIA BioNeMo. Startup Evozyne developed two proteins with tremendous promise in healthcare and sustainable energy using a pretrained AI model from NVIDIA. One is intended to treat a congenital ailment, while the other is built to absorb carbon dioxide to slow global warming. Initial findings point to new ways to speed up drug discovery, among other things.
“It’s been really encouraging that even in this first round the AI model has produced synthetic proteins as good as naturally occurring ones,” said Andrew Ferguson, Evozyne’s co-founder and a co-author of the paper. “That tells us it’s learned nature’s design rules correctly.”
ProtT5, a transformer model that is a component of NVIDIA BioNeMo, a software platform and service for developing AI models for healthcare, was utilized by Evozyne. “BioNeMo really gave us everything we needed to support model training and then run jobs with the model very inexpensively — we could generate millions of sequences in just a few seconds,” said Ferguson, a molecular engineer working at the intersection of chemistry and machine learning.
