Please use this identifier to cite or link to this item: https://hdl.handle.net/11681/41302
Title: Deep learning-based structure-activity relationship modeling for multi-category toxicity classification : a case study of 10K Tox21 chemicals with high-throughput cell-based androgen receptor bioassay data
Authors: Idakwo, Gabriel.
Thangapandian, Sundar.
Luttrell, Joseph.
Zhou, Zhaoxian.
Zhang, Chaoyang.
Gong, Ping.
Keywords: Deep neural networks
Deep learning
Random forest
Androgen receptor
Structure-activity relationship
Multi-class classification
Agonist
Antagonist
Publisher: Environmental Laboratory (U.S.)
Engineer Research and Development Center (U.S.)
Series/Report no.: Miscellaneous Paper (Engineer Research and Development Center (U.S.)) ; no. ERDC/EL MP-21-3
Is Version Of: Idakwo, Gabriel, Sundar Thangapandian, Joseph Luttrell IV, Zhaoxian Zhou, Chaoyang Zhang, and Ping Gong. "Deep learning-based structure-activity relationship modeling for multi-category toxicity classification: a case study of 10K Tox21 chemicals with high-throughput cell-based androgen receptor bioassay data." Frontiers in physiology 10 (2019): 1044. https://doi.org/10.3389/fphys.2019.01044
Abstract: Deep learning (DL) has attracted the attention of computational toxicologists as it offers a potentially greater power for in silico predictive toxicology than existing shallow learning algorithms. However, contradicting reports have been documented. To further explore the advantages of DL over shallow learning, we conducted this case study using two cell-based androgen receptor (AR) activity datasets with 10K chemicals generated from the Tox21 program. A nested double-loop cross-validation approach was adopted along with a stratified sampling strategy for partitioning chemicals of multiple AR activity classes (i.e., agonist, antagonist, inactive, and inconclusive) at the same distribution rates amongst the training, validation and test subsets. Deep neural networks (DNN) and random forest (RF), representing deep and shallow learning algorithms, respectively, were chosen to carry out structure-activity relationship-based chemical toxicity prediction. Results suggest that DNN significantly outperformed RF (p < 0.001, ANOVA) by 22–27% for four metrics (precision, recall, F-measure, and AUPRC) and by 11% for another (AUROC). Further in-depth analyses of chemical scaffolding shed insights on structural alerts for AR agonists/antagonists and inactive/inconclusive compounds, which may aid in future drug discovery and improvement of toxicity prediction modeling.
Description: Miscellaneous Paper
Gov't Doc #: ERDC/EL MP-21-3
URI: https://hdl.handle.net/11681/41302
http://dx.doi.org/10.21079/11681/41302
Appears in Collections:Documents

Files in This Item:
File Description SizeFormat 
ERDC-EL MP-21-3.pdf2.26 MBAdobe PDFThumbnail
View/Open