AFP-SRC: Identification of Antifreeze Proteins Using Sparse Representation Classifier

TL;DR

This paper introduces a novel computational method using sparse representation classification to predict antifreeze proteins, addressing the challenge of their structural diversity and improving accuracy over existing methods.

Contribution

The study presents a new sparse reconstruction-based classifier for AFP prediction, outperforming current approaches in accuracy metrics.

Findings

Outperforms contemporary methods in balanced accuracy and Youden's index.

Uses a sample-specific classification approach with sparse reconstruction.

Provides MATLAB implementation on GitHub.

Abstract

Species living in the extreme cold environment fight against the harsh conditions using antifreeze proteins (AFPs), that manipulates the freezing mechanism of water in more than one way. This amazing nature of AFP turns out to be extremely useful in several industrial and medical applications. The lack of similarity in their structure and sequence makes their prediction an arduous task and identifying them experimentally in the wet-lab is time-consuming and expensive. In this research, we propose a computational framework for the prediction of AFPs which is essentially based on a sample-specific classification method using the sparse reconstruction. A linear model and an over-complete dictionary matrix of known AFPs are used to predict a sparse class-label vector that provides a sample-association score. Delta-rule is applied for the reconstruction of two pseudo-samples using lower and upper parts of the sample-association vector and based on the minimum recovery score, class labels are assigned. We compare our approach with contemporary methods on a standard dataset and the proposed method is found to outperform in terms of Balanced accuracy and Youden's index. The MATLAB implementation of the proposed method is available at the author's GitHub page (\{https://github.com/Shujaat123/AFP-SRC}{https://github.com/Shujaat123/AFP-SRC}).