Antifp SRF: Identifying Antifungal Peptides by Sequence Statistical Moments and Random Forest Classifier

Abstract

Numerous types of fungus are unhealthy and can lead to life-threatening conditions in people. A fungal infection that targets specific bodily regions and that the immune system is unable to fight off. Numerous studies have been conducted on the topic, but due to its negative side effects, medications, chemicals, and conventional techniques have not proven effective enough. Due to the rapidly invading fungus species, antimicrobial peptides having antifungal properties have emerged as a new and powerful candidate due to their efficiency and selectivity. Many mathematical models are being developed for their identification, including Deep-AntiFP and AntiFP, the most recent. However, it has limited performance in accuracy, sensitivity, precision, and MCC. This study investigates an efficient and accurate computational model for the prediction of antifungal peptides (AFPs) using machine learning approaches. The model uses the statistical moment as feature extraction and Random Forest (RF) as a predictor to predict AFPs from non-AFPs. 10-fold cross-validation, independent tests, and self-consistency tests are used to validate the performance of the model. Three datasets are used for model training and its evaluation, namely Antifp Main, Antifp DS1, and Independent Main. The model achieved an accuracy of 95.73%, 97.01%, and 99.15% for Antifp Main, Antifp DS1, and Independent Main, respectively, through independent testing; 97.4%, 97.3%, and 97.4% by 10-fold cross-validation; and 99.74%, 99.87%, and 99.83 by self-consistency testing. The proposed model has shown excellent results for all three datasets as compared to the existing models available in the literature.