Application of different machine learning techniques in identifying features of protein sequence data

This study is carried out on application of different machine learning techniques for prediction of features using bioinformatics data such as that of cancer. The prediction process is undertaken based on feature extraction and then on feature selection process. After selecting the relevant features, machine learning techniques like Support vector machine (SVM), Extreme learning machine (ELM) are applied for classification of the right kind of features. The results obtained with these classifiers are then tested using various test datasets like egfr, TP53, cosmic2plus etc, in order to identify cancer-associated mutations and passenger mutations i.e. neutral polymorphism.