Predicting the DPP-IV Inhibitory ActivitypIC50Based on Their Physicochemical Properties

Abstract

The second development program developed in this work was introduced to obtain physicochemical properties of DPP-IV inhibitors. Based on the computation of molecular descriptors, a two-stage feature selection method called mRMR-BFS (minimum redundancy maximum relevance-backward feature selection) was adopted. Then, the support vector regression (SVR) was used in the establishment of the model to map DPP-IV inhibitors to their corresponding inhibitory activity possible. The squared correlation coefficient for the training set of LOOCV and the test set are 0.815 and 0.884, respectively. An online server for predicting inhibitory activity pIC50 of the DPP-IV inhibitors as described in this paper has been given in the introduction.

MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics

“…Molecular Informatics is an emerging interdisciplinary that addresses mathematical and computational problems, related to molecule-based information encoding and processing, oriented to the discovery of new knowledge in several fields as pharmacology, material engineering, or environmental sciences [1–4] In particular, Quantitative Structure-Activity Relationships (QSAR) modelling constitutes active area of research in Molecular Informatics. QSAR models have been proposed in order to estimate several biological properties, such as activity [5, 6] or ADMET properties [7, 8], providing relevant information to support drug discovery projects [9, 10]. The advantages of having QSAR models for drug design are numerous: reduction of the time spent during the discovery phase, reduction of economic and material resources required due to a decrease in the number of traditional tests, reduction of animal testing, among others.…”

SVMDLF: A novel R‐based Web application for prediction of dipeptidyl peptidase 4 inhibitors

“…Another drawback of all these studies is the inaccessibility of the generated models, which is restricted to the respective authors because most of them were made from proprietary software. Some in silico machine learning‐based studies were also carried out to identify DPP4 inhibitors, which utilized the support vector regression and decision tree . But, none of these studies were used for virtual screening and subsequent inhibitor identification.…”