A Comparative Analysis of SVM Random Forest Methods for Protein Function Prediction

Data mining methods were applying almost everywhere and it give benefits in commercial and scientific uses. In health care by providing decision support data-mining can help in saving human life. There are various methods in data mining which can be used for data sets analysis and prediction and the methods are Support vector machine, Decision Tree, Random Forest, ANN etc. As we all know that protein function prediction is very important and challenging area of bioinformatics field. We can also apply data-mining methods in bioinformatics field for protein function prediction as it is less time consuming and give approximately the correct result. In this paper we had compare the two methods i.e S.V.M and Random Forest of data-mining in predicting the protein function. Here we had taken the protein data sets on the basis of enzymes classification and found that the overall accuracy of SVM (88.49%) is better than the Random Forest (53.9%).