Our AI model KERMT is helping to advance drug discovery
Our scientists harness AI and machine learning in small molecule lead optimization
March 19, 2026
In the lead optimization phase, scientists fine-tune early molecules in the hopes of finding a molecule that might one day become a medicine.
Traditionally, this stage takes months, and most drug candidates never make it to clinical testing. But advancements in artificial intelligence and machine learning (AI/ML), including our new AI foundation model KERMT, could help change that.
What is KERMT and how is it transforming small molecule research?
Developed in collaboration with Nvidia, KERMT, pronounced “Kermit” and short for Kinetic GROVER Multi-Task, is a deep-learning computer model trained on more than 11 million molecules. It learns from patterns in vast amounts of chemical data with the goal of helping scientists better predict how a molecule will behave in the body, potentially spotting issues much earlier and reducing the need for months of lab work.
KERMT isn’t just helping our researchers; as an open-source model, its code is available to the whole scientific community.
How AI models can impact drug development timelines
In a recent interview with Healthcare Brew, Senior Director of Data Science Alan Cheng said AI is already “speeding up the early stages of drug development dramatically.”
“AI is sometimes cutting timelines by 30% or more, improving drug candidate quality and reducing costs,” Cheng said. “This is a very meaningful acceleration. While clinical trials remain lengthy, our models are enabling faster identification of disease targets and optimized compounds, which should increase probability of success and shorten preclinical phases.”
Open-source AI for the scientific community
AI/ML is evolving at an incredible pace: access to relevant data is growing, computing power is expanding and deep-learning algorithms are rapidly improving. Advances like KERMT can give teams a powerful new way to make better informed decisions and focus their time on the most promising drug candidates.
These changes have the potential to create unprecedented opportunities to speed and strengthen the discovery of new drugs — with the goal of bringing safer, more effective medicines to patients faster.
KERMT is available on Nvidia accelerated computing and software, including platforms like Nvidia BioNeMo and Clara Open Models.
