Machine Learning for Classification of Protein Helix Capping Motifs

TL;DR

This paper applies deep learning, specifically BiLSTM models, to classify protein helix capping motifs using structural data, achieving high accuracy and offering a more robust alternative to heuristic methods.

Contribution

The study introduces a deep learning approach for classifying helix capping motifs directly from structural data, improving accuracy over traditional heuristic methods.

Findings

Achieved 85% class-balanced accuracy with BiLSTM.

Compared deep learning model performance with baseline SVC.

Utilized structural features like torsion angles and physicochemical properties.

Abstract

The biological function of a protein stems from its 3-dimensional structure, which is thermodynamically determined by the energetics of interatomic forces between its amino acid building blocks (the order of amino acids, known as the sequence, defines a protein). Given the costs (time, money, human resources) of determining protein structures via experimental means such as X-ray crystallography, can we better describe and compare protein 3D structures in a robust and efficient manner, so as to gain meaningful biological insights? We begin by considering a relatively simple problem, limiting ourselves to just protein secondary structural elements. Historically, many computational methods have been devised to classify amino acid residues in a protein chain into one of several discrete secondary structures, of which the most well-characterized are the geometrically regular $\alpha$-helix and $\beta$-sheet; irregular structural patterns, such as 'turns' and 'loops', are less understood. Here, we present a study of Deep Learning techniques to classify the loop-like end cap structures which delimit $\alpha$-helices. Previous work used highly empirical and heuristic methods to manually classify helix capping motifs. Instead, we use structural data directly--including (i) backbone torsion angles computed from 3D structures, (ii) macromolecular feature sets (e.g., physicochemical properties), and (iii) helix cap classification data (from CAPS-DB)--as the ground truth to train a bidirectional long short-term memory (BiLSTM) model to classify helix cap residues. We tried different network architectures and scanned hyperparameters in order to train and assess several models; we also trained a Support Vector Classifier (SVC) to use as a baseline. Ultimately, we achieved 85% class-balanced accuracy with a deep BiLSTM model.