Evaluation of Standard Classifiers for Protein Subcellular Localization

Finding subcellular location of protein is a well-known problem in the field of biological science. Finding out the location of protein inside the cell helps in understanding cell function, drug development, etc. This paper presents a comparison between three standard classifiers: Classification And Regression Tree (CART), K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) that are used to predict protein location. The Hold-out method is used for testing the classification models. The experiment is carried out on Yeast Dataset. The results are evaluated under four metrics: Accuracy, Macro-average Precision, Macro-average Recall and Macro-F1 Score. According to results, SVM shows better Accuracy and Macro-average Precision than other two, whereas CART shows better Macro-average Recall and Macro-F1 Score.