RAFP-Pred: Robust Prediction of Antifreeze Proteins using Localized Analysis of n-Peptide Compositions

TL;DR

This paper introduces RAFP-Pred, a novel machine learning approach that predicts antifreeze proteins by analyzing localized peptide compositions and selecting significant features, achieving superior accuracy over existing methods.

Contribution

The study presents a localized analysis method combined with feature selection and random forest classification for improved AFP prediction accuracy.

Findings

Achieved a Youden's index of 0.75 on standard datasets.

Reported an 83.19% verification rate on UniProKB dataset.

Outperformed existing AFP prediction methods in accuracy.

Abstract

In extreme cold weather, living organisms produce Antifreeze Proteins (AFPs) to counter the otherwise lethal intracellular formation of ice. Structures and sequences of various AFPs exhibit a high degree of heterogeneity, consequently the prediction of the AFPs is considered to be a challenging task. In this research, we propose to handle this arduous manifold learning task using the notion of localized processing. In particular an AFP sequence is segmented into two sub-segments each of which is analyzed for amino acid and di-peptide compositions. We propose to use only the most significant features using the concept of information gain (IG) followed by a random forest classification approach. The proposed RAFP-Pred achieved an excellent performance on a number of standard datasets. We report a high Youden's index (sensitivity+specificity-1) value of 0.75 on the standard independent test data set outperforming the AFP-PseAAC, AFP\_PSSM, AFP-Pred and iAFP by a margin of 0.05, 0.06, 0.14 and 0.68 respectively. The verification rate on the UniProKB dataset is found to be 83.19\% which is substantially superior to the 57.18\% reported for the iAFP method.