Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modeling

Aaron Feller, Kris Deibler, Maxim Secor|July 23, 2026arXiv

Key Takeaway

Modeling molecules as conformational ensembles rather than single structures substantially improves property prediction—pretraining on ensemble data is critical, as the model fails from scratch but reaches strong performance when pretrained.

Summary

This paper introduces EnsembleEGNN, a neural network model that predicts molecular properties by learning from multiple 3D structures (conformations) of cyclic peptides simultaneously, rather than just one.

architecture multimodal

Key Terms

equivariant-graph-neural-networks conformational-ensemble self-supervised-pretraining set-attention-block