# Combined Modeling Approaches for Assessing Sodium-Iodide Symporter Inhibition

## TL;DR

This paper explores how inhibiting the sodium-iodide symporter during brain development may lead to neurodevelopmental disorders and introduces a new method to predict such inhibition using machine learning and docking.

## Contribution

A novel framework combining machine learning and docking for predicting sodium-iodide symporter inhibition is introduced.

## Key findings

- Combining ML and docking predictions achieved an ROC AUC of 0.77 for NIS inhibition prediction.
- Optimal thresholds yielded a balanced accuracy of 0.78 and MCC of 0.32 on the test set.
- The framework was trained on a diverse dataset of 1412 compounds.

## Abstract

The sodium-iodide symporter (NIS, SLC5A5) plays a crucial
role
in thyroid hormone synthesis. Especially during brain development,
correct thyroid signaling is of critical importance. Hence, inhibition
of this transporter can lead to neurodevelopmental disorders, such
as lowered IQ or autism. In order to uncover environmental chemicals
with the potential of causing developmental neurotoxicity (DNT), NIS
was selected for modeling. To support next-generation risk assessment,
in silico-based methods were utilized. Docking-based virtual screening
workflows of a library of compounds with experimentally determined
inhibitory activity on NIS were applied. In addition, machine learning
(ML) models based on random forest (RF), extreme gradient boosting
(XGB), and support vector machines (SVM) were trained using extended-connectivity
fingerprints 4 (ECFP4) and continuous and data-driven descriptors
(CDDDs) with 9-fold cross validation to discriminate between NIS inhibiting
and noninhibiting compounds. Ultimately, combining ML and docking
predictions improved discrimination, achieving an area under the receiver
operating characteristic curve (ROC AUC) of 0.77. Thresholds for optimal
discrimination between actives and inactives were determined using
kernel density estimate plots, at which a Matthews correlation coefficient
(MCC) of 0.32, and a balanced accuracy (BA) of 0.78 were achieved
on the internal test set. By combining ML predictions with docking
scores and training on a larger, more diverse data set of 1412 compounds,
this study provides a novel and robust framework for NIS inhibition
prediction, which constitutes a new approach method in toxicological
risk assessment.