An Evaluation on Different Machine Learning Algorithms for Classification and Prediction of Antifungal Peptides

Fungi are an emerging threat in medicine and agriculture and current therapeutics have proved to be insufficient and toxic. This has led to an increased interest in peptide-based therapeutics, especially antifungal peptides (AFPs), being safer and more effective drug candidates against fungal threats. However, screening for peptides with antifungal activity is costly and timeconsuming. However, by using computational techniques, we can overcome these restricting factors. The aim of the present study is to compare different machine learning algorithms in combination with Chou's pseudo amino acid composition in classifying and predicting AFPs to represent a precise model for AFP prediction.

Five different machine learning algorithms frequently used for classification of biological data were used and their performance was evaluated and compared based on their accuracy, sensitivity, specificity and Matthew's correlation coefficient. The two algorithms with the best performance were then further verified with an independent test dataset.

SVM and Bagged-C4.5 classifiers had the highest performance results among the five algorithms. Further validations showed that the model generated using SVM can be employed for precise classification and prediction of antifungal peptides. All the performance values of this model were above 80%, making the classifier highly accurate and trustable.

Using computational approaches, especially data mining techniques, we can develop a precise prediction model for antifungal peptides. The model developed in this study using SVM can be considered a powerful tool for the prediction of antifungal peptides, which can be the first step in synthesis and discovery of novel fungi targeting agents.