In Silico Prediction of Indonesian Herbs Compounds as Covid-19 Supportive Therapy using Support Vector Machine

Abstract

Many kinds of research on drug discovery using computational or in silico methods have been carried out. In this era of the Covid-19 pandemic, this research was also carried out by utilizing a commonly used technique, namely using machine learning to predict the interaction of compounds and proteins. This technique is known as Drug Target Interaction (DTI). The compounds used are herbal originating from Indonesia, and the protein used is a potential Covid-19 protein, one of which is SARS-CoV-2. The prediction process with machine learning can only be done on structured data. The data on herbal and protein were processed in this research using the Fingerprint as a descriptor compound and Pseudo Amino Acid Composition (PseAAC) as a protein descriptor technique. The result is structured data processed with the Support Vector Machine algorithm to create an interaction prediction model. The result is that the prediction accuracy is 95.96%. Furthermore, this model can predict Indonesian herbal compounds as drug candidates for Covid-19 supportive therapy.