Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modeling
2026-07-23 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed EnsembleEGNN, a model that predicts molecular properties by considering multiple shapes (conformations) a molecule can have, instead of just one. They use a special type of neural network (EGNN) to analyze each shape and then combine the information to get a comprehensive understanding. By training the model on data of cyclic peptide shapes, they showed it predicts molecular properties better than models using only sequence information. Their results suggest that including shape variations helps improve molecular predictions.
Molecular property predictionConformational ensembleEquivariant Graph Neural Network (EGNN)Set Attention BlockCyclic peptidesSelf-supervised learningMasked token recoveryPairwise distance reconstructionBERT sequence encoder
Authors
Aaron Feller, Kris Deibler, Maxim Secor
Abstract
Molecular property prediction from structure often uses a single representative conformation, even though many molecules exist as conformational ensembles in solution. We introduce EnsembleEGNN, a molecular ensemble foundation model that encodes an ensemble by first encoding each conformer with shared Equivariant Graph Neural Network (EGNN) layers, then pooling the resulting conformer representations with a Set Attention Block. We pretrain the model on CREMP, a cyclic peptide ensemble dataset, using a multi-task self-supervised objective combining masked token recovery, noisy-coordinate reconstruction, and pairwise distance reconstruction. On the CREMP-CycPeptMPDB dataset, training EnsembleEGNN from scratch fails entirely ($R^2=0.005$). However, the pretrained model reaches $R^2=0.477$ and Pearson $r=0.699$, outperforming the sequence-only BERT baseline ($R^2=0.439$, Pearson $r=0.667$). When EnsembleEGNN is co-trained end-to-end with the BERT sequence encoder, the hybrid model improves further to $R^2=0.538$ and Pearson $r=0.737$. These results demonstrate that encoding conformational ensembles into a single thermodynamically informed embedding improves cyclic-peptide property prediction.