ORIGINAL RESEARCH article
Front. Pharmacol.
Sec. Experimental Pharmacology and Drug Discovery
Volume 16 - 2025 | doi: 10.3389/fphar.2025.1605722
i-DENV: Development of QSAR based regression models for predicting inhibitors targeting non-structural (NS) proteins of dengue virus
Provisionally accepted
- 1Institute of Microbial Technology (CSIR), Chandigarh, India
- 2Academy of Scientific and Innovative Research (AcSIR), Ghaziabad-201002, India, Ghaziabad, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Dengue virus (DENV) infection is a major arboviral threat with fatal potential, lacking effective antivirals or a universal applicable vaccine. We developed the ‘i-DENV’ web server by targeting NS3 and NS5 proteins of DENV using MLTs and QSAR of compounds. 1213 and 157 unique entries along with their corresponding IC50 values targeting NS3 and NS5 proteins were taken from CHEMBL and DenvInD databases. Subsequently, molecular descriptors and fingerprints were extracted, followed by applying regression-based MLTs- SVM, RF, kNN, ANN, XGBoost, and DNN using ten-fold cross-validation. Using randomization, top SVM and ANN models achieved PCC values of 0.857/0.862 (NS3) and 0.982/0.964 (NS5) on training/testing set (TT) sets, and 0.870/0.894 (NS3) and 0.970/0.977 (NS5) on validation set (IV) sets, respectively. The developed models’ robustness was assessed through scatter plot, chemical clustering, statistical tests, decoy set analysis etc. Predictive models identified Micafungin, Oritavancin, and Iodixanol as top hits for NS2B/NS3 protease and Cangrelor, Eravacycline, and Baloxavir marboxil for NS5 polymerase. Additionally, molecular docking confirmed strong binding affinities, highlighting their potential as antiviral candidates against DENV. These findings are entirely based on in silico approaches, and we emphasize the need for subsequent in vitro and in vivo studies to validate the therapeutic potential of the predicted compounds. The ‘i-DENV’ web server is freely accessible at http://bioinfo.imtech.res.in/manojk/idenv/.
Keywords: machine learning, antivirals, artificial intelligence, algorithm, Web server, QSAR
Received: 03 Apr 2025; Accepted: 12 Jun 2025.
Copyright: © 2025 Gautam, Thakur and Kumar. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Manoj Kumar, Institute of Microbial Technology (CSIR), Chandigarh, India
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.