QSAR Model for Prediction PTP1B Inhibitor as Anti-diabetes Mellitus using Simulated Annealing-Support Vector Machine

Abstract

Diabetes mellitus or diabetes is a kind of disease characterized by a raised in blood sugar. This disease can deal with long-term damage, such as dysfunction and failure of various organs. In Indonesia, diabetes is one of the major causes of death, with more than 10 million people living with diabetes. To date, no drug can cure diabetes. So far, people with diabetes must take responsibility for their daily routine. Drug discovery is needed to find the cure for diabetes. protein tyrosine phosphatase 1B (PTP1B) is one inhibitor that proved as a promising target for anti-diabetes Mellitus. Drug discovery takes a lot of time and effort, and thus, in silico methods, such as quantitative structure-activity relationship (QSAR), can be used to accelerate this process. We aim to build a QSAR model of PTP1B inhibitor as anti-diabetes Mellitus using the simulated annealing (SA)-Support Vector Machine (SVM) method. The data were retrieved from the ChEMBL database by selecting the SMILES from each compound. By calculating the SMILES using PaDEL, we got 1443 descriptors for each compound, and by using SA, we decreased the number of descriptors. The best result shows that SA selected 600 descriptors out of 1443 descriptors for each compound. The RBF kernel on SVM has the best value with accuracy, F1 score, and AUC of 94.508%, 95.048%, and 0.943, respectively.