CarbPred
Using machine learning to predict nuclear magnetic resonance spectra for carbohydrates via graph neural networks
Categories: CS Honours , CS Honours Project
Abstract
Carbohydrates are complex molecules, critical to drug and vaccine development. Their study often involves the analysis of nuclear magnetic resonance (NMR) spectra, which are challenging to interpret, even for experts. We build upon prior work, GeqShift, employing E(3)-equivariant graph neural networks (GNNs) to automate this process. We explore a variety of methods and accomplish accuracy and computational efficiency improvements in multiple categories.
Videos 1
Watch presentations, demos, and related content
Overview of results for each approach at building on GeqShift
Like, comment, and subscribe on YouTube to support the creator!
Overview of results for each approach at building on GeqShift
Gallery 1
Explore the visual story of this exhibit
Title Image