TP-ML: A Machine-Learning-Based Tool to Identify Threonine Proteases Using Sequence-Derived Optimal Features

Threonine proteases (TPs) are enzymes vital for several biological processes and diseases including Alzheimer’s disease and cancer. Their potential to target and degrade proteins intracellularly makes them valuable for various therapeutic and industrial applications. However, traditional experimental methods for identifying and characterizing novel TPs are exhaustive, time-consuming, and expensive. To address this, we developed TP-ML, a support vector machine-based prediction tool that can differentiate TP from non-TP sequences. We generated a benchmark dataset and calculated the physicochemical and compositional features using primary amino acid sequences. Subsequently, a comparison was made between the two feature selection approaches to identify the optimal feature sets from the original encodings. These optimal features were then used to train five different machine-learning classifiers, each assessed independently. TP-ML was selected as the best model showing consistent performance during cross-validation and independent evaluation, and achieved an accuracy of 0.934 and 0.888, respectively. We anticipate TP-ML to be a powerful tool for identifying TPs, aiding in their experimental characterization and industrial application exploration.