Predicting Endocrine Disruptors: A Deep Learning QSAR Model for Estrogen Receptor Activity

TL;DR

This paper presents a deep learning QSAR model that accurately predicts estrogen receptor activity of chemicals, enabling faster screening of endocrine disruptors and aiding in risk assessment and conservation efforts.

Contribution

The authors developed a novel deep neural network model using molecular descriptors to predict EDC activity, achieving high accuracy and ROC-AUC, and validated predictions with molecular docking.

Findings

Model achieved 96.65% training accuracy and 91.30% test accuracy.

ROC-AUC of 0.81 indicates good predictive performance.

Docking confirmed several predicted compounds bind effectively to estrogen receptor.

Abstract

Endocrine-disrupting chemicals (EDCs) threaten human health, ecosystems, and biodiversity by interfering with hormonal signaling pathways conserved across vertebrates. Traditional in vivo assays are costly and time-consuming, limiting their capacity to screen the growing number of chemicals. To address this, we developed a deep learning-based QSAR model to predict estrogen receptor (ER) binding molecules. Using a curated dataset of 224 compounds and 2,944 molecular descriptors and fingerprints, a deep neural network (DNN) incorporating dropout and batch normalization was trained and validated. The model achieved training and test accuracies of 96.65% and 91.30%, respectively, with an ROC-AUC of 0.81, a precision of 0.82, and a recall of 0.88 for the active class. Molecular docking against estrogen receptor (PDB ID: 5TOA) confirmed that several predicted compounds exhibited binding comparable to Estradiol, sharing key interactions. This model enables rapid screening of potential EDCs, supporting efficient chemical risk assessment and contributing to biodiversity conservation by identifying compounds that may disrupt reproduction and population stability in humans and wildlife.