Abstract
Various computational methods have been used for predicting protein function from clues contained in protein sequence. A particular challenge is the functional prediction of proteins that show low or no sequence similarity to proteins of known function. Recently, machine learning methods have been explored for predicting functional class of proteins from a variety of sequence-derived structural and physicochemical properties independent of sequence similarity, which showed promising potential for a broad spectrum of proteins including those that show low and no similarity to other proteins. These methods can thus be explored as potential tools to complement similarity-based, clustering-based and structure-based methods for predicting protein function. This article reviews the strategies, algorithms, current progresses, available software and web-servers, and underlying difficulties in using machine learning methods for predicting the functional class of proteins and peptides, and protein-protein interactions. The reported prediction performances in the application of these methods are also presented.
Keywords: Machine learning method, neural network, support vector machine, protein function prediction, protein-protein interaction, peptide prediction
Related Books
In Vitro Propagation and Secondary Metabolite Production from Medicinal Plants: Current Trends (Part 2)
Micropropagation of Medicinal Plants
Software and Programming Tools in Pharmaceutical Research
Biotechnology and Drug Development for Targeting Human Diseases
In Vitro Propagation and Secondary Metabolite Production from Medicinal Plants: Current Trends (Part 1)
Molecular and Physiological Insights into Plant Stress Tolerance and Applications in Agriculture- Part 2
Micropropagation of Medicinal Plants
Genome Editing in Bacteria (Part 1)
Data Science for Agricultural Innovation and Productivity
Animal Models In Experimental Medicine
2