Deep Learning-based QSAR Model for Therapeutic Strategies Targeting SmTGR Protein's Immune Modulating Role in Host-Parasite Interaction

TL;DR

This paper presents a deep learning-based QSAR model to identify potential inhibitors of the SmTGR protein in Schistosoma parasites, aiding drug discovery for schistosomiasis treatment.

Contribution

It introduces a novel deep learning QSAR approach validated with molecular docking, enhancing prediction accuracy for SmTGR inhibitors.

Findings

High predictive accuracy of the QSAR model.

Identification of novel potential inhibitors with strong binding affinities.

Visualization confirmed similar interactions to known drugs.

Abstract

Schistosomiasis, a neglected tropical disease caused by Schistosoma parasites, remains a major global health challenge. The Schistosoma mansoni thioredoxin glutathione reductase (SmTGR) is essential for parasite redox balance and immune evasion, making it a key therapeutic target. This study employs predictive Quantitative Structure-Activity Relationship (QSAR) modeling to identify potential SmTGR inhibitors. Using deep learning, a robust QSAR model was developed and validated, achieving high predictive accuracy. The predicted novel inhibitors were further validated through molecular docking studies, which demonstrated strong binding affinities, with the highest docking score of -10.76+-0.01kcal/mol. Visualization of the docked structures in both 2D and 3D confirmed similar interactions for the inhibitors and commercial drugs, further supporting their therapeutic effectiveness and the predictive ability of the model. This study demonstrates the potential of QSAR modeling in accelerating drug discovery, offering a promising avenue for developing novel therapeutics targeting SmTGR to improve schistosomiasis treatment.