What question did this study set out to answer?

The aim is to create a method that derives geometry-based descriptors to improve enzyme-substrate interaction predictions.

March 24, 2026ChemPhysChem

Toward Automatic Derivation of Geometry‐Based Descriptors as Surrogates for Complex Computational Approaches in Enzyme–Substrate Prediction

View Full Paper

Ask AI

Bookmark

The aim is to create a method that derives geometry-based descriptors to improve enzyme-substrate interaction predictions.
Developed geometric filters from enzyme-substrate complex structures.
Validated approach using haloalkane dehalogenases and aldehyde reductases.
Evaluated performance using minimal training data across multiple enzyme and substrate types.
Achieved average accuracy of 77% and sensitivity of 94% for haloalkane dehalogenases.
Obtained an average recall of 57% for aldehyde reductases in substrate predictions.
Filters provided mechanistic insights directly linked to catalytic requirements.

No takes yet. Share an insight, caveat, or question.

This methodology predicts substrate specificity in enzyme families, suggesting a new tool for enzyme engineering.

Sequeiros‐Borja et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark