English

Boltzmann Graph Ensemble Embeddings for Aptamer Libraries

Machine Learning 2025-10-30 v1 Probability Quantitative Methods Machine Learning

Abstract

Machine-learning methods in biochemistry commonly represent molecules as graphs of pairwise intermolecular interactions for property and structure predictions. Most methods operate on a single graph, typically the minimal free energy (MFE) structure, for low-energy ensembles (conformations) representative of structures at thermodynamic equilibrium. We introduce a thermodynamically parameterized exponential-family random graph (ERGM) embedding that models molecules as Boltzmann-weighted ensembles of interaction graphs. We evaluate this embedding on SELEX datasets, where experimental biases (e.g., PCR amplification or sequencing noise) can obscure true aptamer-ligand affinity, producing anomalous candidates whose observed abundance diverges from their actual binding strength. We show that the proposed embedding enables robust community detection and subgraph-level explanations for aptamer ligand affinity, even in the presence of biased observations. This approach may be used to identify low-abundance aptamer candidates for further experimental evaluation.

Keywords

Cite

@article{arxiv.2510.21980,
  title  = {Boltzmann Graph Ensemble Embeddings for Aptamer Libraries},
  author = {Starlika Bauskar and Jade Jiao and Narayanan Kannan and Alexander Kimm and Justin M. Baker and Matthew J. Tyler and Andrea L. Bertozzi and Anne M. Andrews},
  journal= {arXiv preprint arXiv:2510.21980},
  year   = {2025}
}
R2 v1 2026-07-01T07:04:57.315Z