An Inductive Logic Programming Approach to Validate Hexose Binding Biochemical Knowledge

TL;DR

This paper uses Inductive Logic Programming to analyze and validate biochemical knowledge about hexose binding sites, achieving comparable accuracy to black-box models while providing interpretable insights and confirming known findings.

Contribution

It introduces an ILP-based model for hexose binding site prediction that not only matches existing classifiers in accuracy but also offers interpretability and uncovers new biochemical dependencies.

Findings

ILP model achieves accuracy similar to black-box classifiers.

The model confirms existing biochemical findings.

It reveals a new Trp-Glu amino acids dependency.

Abstract

Hexoses are simple sugars that play a key role in many cellular pathways, and in the regulation of development and disease mechanisms. Current protein-sugar computational models are based, at least partially, on prior biochemical findings and knowledge. They incorporate different parts of these findings in predictive black-box models. We investigate the empirical support for biochemical findings by comparing Inductive Logic Programming (ILP) induced rules to actual biochemical results. We mine the Protein Data Bank for a representative data set of hexose binding sites, non-hexose binding sites and surface grooves. We build an ILP model of hexose-binding sites and evaluate our results against several baseline machine learning classifiers. Our method achieves an accuracy similar to that of other black-box classifiers while providing insight into the discriminating process. In addition, it confirms wet-lab findings and reveals a previously unreported Trp-Glu amino acids dependency.