Peptide structure models improve by combining multiple shapes for predictions

Ensemble-Aware Structural Encoding (EASE): Conditioning Protein Encoders on Peptide Conformational Ensembles

Machine Learning

Summary

Peptides can take multiple shapes, but most computer models look at only one shape to predict properties like how well they fight bacteria or how toxic they are. The authors created a method called EASE that looks at many possible peptide shapes, picks important ones, and combines their information to get a better picture. This helps predictions about peptides improve by about 3% compared to using just one shape. This shows that using multiple forms of peptide structures is more useful than looking at just one.

What this means in practice

  • For biotech product developers: Design better peptide-based drugs by improving predictions of their activity and stability using multiple structural conformations.$Commercial implications: Enables peptide drug makers to create more effective therapeutics by providing enhanced predictive models that incorporate peptide shape variability.
  • For computational biology teams: Generate more accurate peptide property predictions for research by using ensemble structural information instead of single conformations.

Authors

Ruoyao Zhang, Hongxuan Li, Jie Peng, Tianlong Chen

Abstract

Protein foundation models provide transferable representations for downstream peptide prediction tasks. However, existing representations typically reduce a peptide to a single sequence or structure, which may miss conformational variability relevant to key peptide properties, including antibacterial activity, hemolysis, toxicity, stability, and binding. For example, protease resistance correlates more strongly with conformational dynamics measured by hydrogen exchange than with average helicity. Therefore, we introduce Ensemble-Aware Structural Encoding (EASE), a framework for effectively extracting structural information from conformational ensembles for peptide representation. To extract useful information from noisy conformers, EASE selects central conformers representing a peptide's major structural states and fuses their individual representations with a permutation-invariant operator to produce a peptide-level representation for downstream prediction. We then evaluate our framework on six peptide property-prediction tasks under leakage-controlled splits. Against matched single-structure baselines, EASE improves performance consistently on six tasks with a mean absolute gain of about 3.0% across two structural encoders. Gains keep growing as we add conformers through K=20. A single peptide conformer therefore provides a limited basis for structural representation, whereas our framework distilling and fusing multiple conformers yields a more informative representation.