Molecular Image-Based Prediction Models of Nuclear Receptor Agonists and Antagonists Using the DeepSnap-Deep Learning Approach with the Tox21 10K Library

Abstract

The interaction of nuclear receptors (NRs) with chemical compounds can cause dysregulation of endocrine signaling pathways, leading to adverse health outcomes due to the disruption of natural hormones. Thus, identifying possible ligands of NRs is a crucial task for understanding the adverse outcome pathway (AOP) for human toxicity as well as the development of novel drugs. However, the experimental assessment of novel ligands remains expensive and time-consuming. Therefore, an in silico approach with a wide range of applications instead of experimental examination is highly desirable. The recently developed novel molecular image-based deep learning (DL) method, DeepSnap-DL, can produce multiple snapshots from three-dimensional (3D) chemical structures and has achieved high performance in the prediction of chemicals for toxicological evaluation. In this study, we used DeepSnap-DL to construct prediction models of 35 agonist and antagonist allosteric modulators of NRs for chemicals derived from the Tox21 10K library. We demonstrate the high performance of DeepSnap-DL in constructing prediction models. These findings may aid in interpreting the key molecular events of toxicity and support the development of new fields of machine learning to identify environmental chemicals with the potential to interact with NR signaling pathways.

Predictive Capability of QSAR Models Based on the CompTox Zebrafish Embryo Assays: An Imbalanced Classification Problem

“…Moreover, MCC Test values obtained in this study are noticeably higher than in the study by Idakwo et al [ 34 ] (0.29, 016, 0.62, and 0.55) and for endpoint no. 3 in Uesawa et al [ 45 ] being 0.5 and 0.48 for two cases of dichotomization of toxicity of endpoint SR-MMP (Stress response panel - mitochondrial membrane potential). The comparison of our results with the corresponding models developed by other methodologies [ 31 , 33 , 34 , 37 ] by the BA gives analogous results ( Table S3 ).…”

The Role of Androgens and Androgen Receptor in Human Bladder Cancer

“…In the search for new therapy alternatives, male predominance is one of the important features which requires the consideration of the AR as a pharmacological target [ 82 ]. Nuclear receptors consist of a superfamily of proteins that includes receptors for steroids (androgens, estrogens, glucocorticoids, progesterone) and non-steroid receptors (thyroid hormones, vitamin D, retinoids, farnesoids, and others such as the peroxisome proliferator-activated receptors); steroids modulate (directly or indirectly by activation of their receptors) several key molecules, such as UDP-glucuronosyltransferases (UGTs), GATA3 zinc-finger transcription factor, FOXO1 forkhead transcription factor, CD24 cell adhesion molecule, β-catenin key component for Wnt signaling pathway, ELK1 transcription factor, ATF2 leucine zipper transcription factor, and NF-kB transcription factor [ 111 , 112 ].…”

Toxicity prediction based on artificial intelligence: A multidisciplinary overview

“…Lee et al 110 predicted in vitro pulmonary toxicity using high throughput imaging and AI, accurately classifying a number of chemicals with 89% balance accuracy, 85% sensitivity and 93% specificity. Other researchers, such as Yuan et al 111 used DL to predict toxicity through stress response effects and nuclear receptor effects, whereas Matsuzaka and Uesawa 112 used molecular image‐based DL to anticipate chemical compounds that can cause dysregulation of endocrine signaling pathways, to name but a few. Lagares et al 113 used a counter‐propagation ANN (CP ANN) based on 2D molecular descriptors, to develop an in silico multiclass classification model capable of predicting the probability of a compound to interact with P‐gp, which is highly important in the early stages of toxicological assessment during drug discovery, because of its role in defense against toxicants in the body.…”