DETERMINATION OF PROTEIN-PROTEIN INTERACTION THROUGH ARTIFICIAL NEURAL NETWORK AND SUPPORT VECTOR MACHINE: A COMPARATIVE STUDY

Protein-protein interactions (PPI) plays considerable role in most of the cellular processes and study of PPI enhances understanding of molecular mechanism of the cells. After emergence of proteomics, huge amount of protein sequences were generated but there interaction patterns are still unrevealed. Traditionally various techniques were used to predict PPI but are deficient in terms of accuracy. To overcome the limitations of experimental approaches numerous computational approaches were developed to find PPI. However previous computational approaches were based on descriptors, various external factors and protein sequences. In this article, a sequence based prediction model is proposed by using various machine learning approaches. A comparative study was done to understand efficiency of various machine learning approaches. Large amount of yeast PPI data have been analyzed. Same data has been incorporated for different classification approach like Artificial Neural Network (ANN) and Support Vector Machine (SVM), and compared their results. Existing methods with additional features were implemented to enhance the accuracy of the result. Thus it was concluded that efficiency of this model was more admirable than those existing sequence-based methods; therefore it can be effective for future proteomics research work.