Search

The method of identifying the location of protein within a cell is called subcellular localization of proteins. This area of research in Bioinformatics is pivotal for protein synthesis and drug discovery of several medical conditions and diseases. This paper introduces a new machine learning approach for subcellular localization of proteins, which used 18 basic and physicochemical features novel for such methods. A model with support vector machine (SVM) was developed at first to learn these properties of proteins from 6 locations inside a cell, and then test the model on another independent set of protein sequences. The proposed multi-class classification algorithm achieved an accuracy of about 94%. The results show superior performance with minimal computations when compared to similar algorithms in the literature.

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.

Detection of different known patterns in any newly found sequence is one of the most important works in the field of Bioinformatics. Given a specific pattern, a long string has to be searched for finding that pattern. That means pattern matching is used for checking the sequence of tokens and the match has to be exact, obviously. These patterns usually have the form of either sequences or tree structures. In DNA and RNA sequences, this type of pattern searching is often needed to detect codons (both "met" and "stop" sequences) in it. This paper presents the concept and implementation of a new algorithm "codon detection in DNA and RNA using hash function (CDDRHF)" for detection of codons in long DNA and RNA sequences, using the concepts of hash function along with metaheuristic approaches. Then the gene between "met" and "stop" codons will easily be extracted to be used for proper alignment. This new algorithm works so fast that any DNA or RNA sequence of any length can be used to perfectly search for codons withinseconds.