Protein Classification Using Machine Learning and Statistical Techniques

Abstract

Background: In the recent era, the prediction of enzyme class from an unknown protein is one of the challenging tasks in bioinformatics. Day-to-day, the number of proteins increases which causes difficulties in clinical verification and classification; as a result, the prediction of enzyme class gives a new opportunity to bioinformatics scholars. The machine learning classification technique helps in protein classification and predictions. But it is imperative to know which classification technique is more suited for protein classification. This study used human proteins data that is extracted from the UniProtKB databank. A total of 4368 protein data with 45 identified features were used for experimental analysis. Objective: The prime objective of this article is to find an appropriate classification technique to classify the reviewed as well as un-reviewed human enzyme class of protein data. Also, find the significance of different features in protein classification and prediction. Methods: In this article, the ten most significant classification techniques such as CRT, QUEST, CHAID, C5.0, ANN, SVM, Bayesian, Random Forest, XgBoost, and CatBoost have been used to classify the data and discover the importance of features. To validate the result of different classification techniques, accuracy, precision, recall, F-measures, sensitivity, specificity, MCC, ROC, and AUROC were used. All experiments were done with the help of SPSS Clementine and Python. Results: Above discussed classification techniques give different results and found that the data are imbalanced for class C4, C5, and C6. As a result, all of the classification techniques give acceptable accuracy above 60% for these classes of data, but their precision value is very less or negligible. The experimental results highlight that the Random forest gives the highest accuracy as well as AUROC among all, i.e., 96.84% and 0.945, respectively, and also has high precision and recall value. Conclusion: The experiment conducted and analyzed in this article highlights that the Random Forest classification technique can be used for protein of human enzyme classification and predictions.