Quantitative Structure-activity Relationship-based Neural Network Model in Screening Potential Inhibitors from Brown Algae against RelA in Oral Squamous Cell Carcinoma.

INTRODUCTION AND AIM

Oral squamous cell carcinomas (OSCCs) are one of the most frequently diagnosed head and neck cancers with a poor prognosis despite the advancements in diagnostic techniques and treatment strategies. The progression of OSCC is driven by several molecular mechanisms, among them the overexpression of transcription factor RelA, which plays a crucial role by correlating with the clinicopathological characteristics.

METHODS

This systematic investigation focused on identifying the top 25 crucial molecular descriptors to predict the RelA inhibitor through the quantitative structure-activity relationship (QSAR)-based artificial neural network model.

RESULTS

In this study, the developed multilayer perceptron model showed an accuracy of 91.37% in the classification of active inhibitors, with a Matthews correlation coefficient (MCC) of 0.89. Then the model was assessed for the 1221 brown algae-derived compounds, identifying 1014 as the most active RelA inhibitors. Further, molecular docking revealed that phlorethopentafuhalol-A had a higher affinity based on the binding energy of -8.45 kcal/mol than the known RelA inhibitors (-5.30 to -1.31 kcal/mol). Molecular dynamics (MD) simulation confirmed that phlorethopentafuhalol-A formed a stable conformation with the RelA based on the trajectory analysis.

CONCLUSIONS

Overall, this analysis demonstrated that phlorethopentafuhalol-A could be a potential RelA inhibitor that may be useful in the treatment of OSCC on further investigation.

CLINICAL RELEVANCE

The multilayer perceptron model extracted relevant descriptors to predict the inhibitory properties of each compound. Using these descriptors, potential inhibitory molecules were predicted from a dataset of compounds sourced from brown algae. The predicted molecule was then evaluated for its interaction with the RelA protein through molecular docking and MD simulations.