University of Notre Dame researchers developed a deep learning-based system that can accurately determine bond energies.
“Neural networks can be used to make quantitative models of chemical concepts that are not possible with just quantum mechanics,” explains John Parkhill, Assistant Professor of Chemistry & Biochemistry at the University of Notre Dame in Indiana and co-author of the paper. “[Before], I got asked all the time: ‘How much stronger is this bond?’ […] Now I can answer that question, because my machine learnt chemical bonding concepts.”
Using Tesla K80 GPUs and the cuDNN-accelerated TensorFlow deep learning framework, Parkhill and his team trained their neural network on a database of over 130,000 molecules. The trained Bonds-in-Molecules Neural Network (BIM-NN) is able to make predictions of relative bond strengths as well as a trained synthetic chemist.
“[Our network] predicts [data] quantitatively and reproducibly. It saves chemists from the impossible tedium of predicting an energy a billion times,” said Parkhill in regards to their software replacing trained chemists.
Read more >
Related resources
- GTC session: AI Driven Atomistic Simulation For Materials and Reactive Chemistry (Spring 2023)
- GTC session: Pushing Quantum Mechanics to the Exascale with JAX and Fermionic Neural Networks (Spring 2023)
- GTC session: Running 100,000-Atom Molecular Dynamics with Accurate NN Potential on a GPU using Automatic Recomputation (Spring 2023)
- NGC Containers: TorchANI
- Webinar: Reshaping Pharma: How AI, Big Data, and Technology are Revolutionizing Drug Discovery
- Webinar: De Novo Molecule Generation Using AI Transformer Models in Cheminformatics