Subcellular localization of proteins is the process of identifying its location within a cell which is crucial for protein synthesis and drug discovery of medical conditions and diseases. This paper introduces a specific machine learning approach in bioinformatics for classifying protein sequences found in a cell according to their locations. The proposed method used basic features of protein, such as amino acid counts, and several other physical and chemical properties. Support vector machine (SVM) algorithm of machine learning has been utilized to learn the properties of protein sequences from 6 target locations of a cell, and tested on an independent set of protein sequences. The proposed multi-class classification algorithm achieved an average accuracy of 90%. The results indicate superior performance with minimal computations when compared to similar algorithms in the literature.
Paper
Full text
Prediction of Protein Subcellular Localization using Machine Learning
Semantic Scholar · Computer Science · 2018
Abstract
Subcellular localization of proteins is the process of identifying its location within a cell which is crucial for protein synthesis and drug discovery of medical conditions and diseases. This paper introduces a specific machine learning approach in bioinformatics for classifying protein sequences found in a cell according to their locations. The proposed method used basic features of protein, such as amino acid counts, and several other physical and chemical properties. Support vector machine (SVM) algorithm of machine learning has been utilized to learn the properties of protein sequences from 6 target locations of a cell, and tested on an independent set of protein sequences. The proposed multi-class classification algorithm achieved an average accuracy of 90%. The results indicate superior performance with minimal computations when compared to similar algorithms in the literature.