Timezone: »

 
A 3D-Shape Similarity-based Contrastive Approach to Molecular Representation Learning
Austin Atsango · Nathaniel Diamant · Ziqing Lu · Tommaso Biancalani · Gabriele Scalia · Kangway Chuang
Event URL: https://openreview.net/forum?id=lT3jXy8hPKI »

Molecular shape and geometry dictate key biophysical recognition processes, yet many modern graph neural networks disregard 3D information for molecular property prediction. Here, we propose a new contrastive-learning procedure for graph neural networks, Molecular Contrastive Learning from Shape Similarity (MolCLaSS), that implicitly learns a three-dimensional representation. Rather than directly encoding or targeting three-dimensional poses, MolCLaSS matches a similarity objective based on Gaussian overlays to learn a meaningful representation of molecular shape. We demonstrate how this framework naturally captures key aspects of three-dimensionality that two-dimensional representations cannot and provides an inductive framework for scaffold hopping.

Author Information

Austin Atsango (Stanford University)
Nathaniel Diamant (genentech)
Ziqing Lu
Tommaso Biancalani (Genentech)
Gabriele Scalia (Genentech)
Kangway Chuang (Genentech Research and Early Development)

More from the Same Authors