# EnsembleEGNN: Set-Based Graph Learning for Thermodynamic Ensembles of Cyclic Peptides

arXiv: https://arxiv.org/abs/2607.21561 · HTML: https://mlsanity.com/paper/2607.21561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [Directional Message Passing for Molecular Graphs](https://mlsanity.com/paper/2003.03123/) (2020)
- [Equivariant message passing for the prediction of tensorial properties and molecular spectra](https://mlsanity.com/paper/2102.03150/) (2021)
- [Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs](https://mlsanity.com/paper/2206.11990/) (2022)
- [Torsional Diffusion for Molecular Conformer Generation](https://mlsanity.com/paper/2206.01729/) (2022)
- [3D Infomax improves GNNs for Molecular Property Prediction](https://mlsanity.com/paper/2110.04126/) (2021)
- [GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles](https://mlsanity.com/paper/2106.07802/) (2021)
- [Graph Foundation Models: Concepts, Opportunities and Challenges](https://mlsanity.com/paper/2310.11829/) (2023)
- [Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks](https://mlsanity.com/paper/2310.00115/) (2023)
- [CREMP: Conformer-rotamer ensembles of macrocyclic peptides for machine learning](https://mlsanity.com/paper/2305.08057/) (2023)
- [Boltzmann Graph Ensemble Embeddings for Aptamer Libraries](https://mlsanity.com/paper/2510.21980/) (2025)

## Abstract (arXiv)

Molecular graph encoding often relies on a single, static structure, ignoring the thermodynamic ensemble of molecules that are present in solution. Here, we introduce EnsembleEGNN, a foundation model that encodes structural ensembles by processing individual conformers through shared equivariant graph neural network layers, pooled with a set attention block, to make property predictions from the whole ensemble. Pretrained on the CREMP cyclic peptide dataset using multi-task self-supervision, the model is trained to encode the conformational variability of each molecule. When predicting membrane permeability from the CycPeptMPDB benchmark, EnsembleEGNN achieves an R2 of 0.477 under random cross-validation, outperforming a sequence-only BERT baseline (R2=0.439). This representation advantage persists under rigorous out-of-distribution Butina splits (R2=0.401 versus 0.354). Finally, a hybrid architecture co-training EnsembleEGNN with the BERT model achieves the highest overall accuracy across both random (R2=0.538) and structural holdout evaluations (R2=0.444). These results demonstrate that encoding conformational ensembles into latent representations improves predictions for properties governed by thermodynamics.