Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets-Reference-Cited by-同舟云学术

Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets

Published:2021-01-29 Issue:2 Volume:34 Page:541-549
ISSN:0893-228X
Container-title:Chemical Research in Toxicology
language:en
Short-container-title:Chem. Res. Toxicol.

Author:

Wu Leihong¹,Huang Ruili²,Tetko Igor V.³⁴^ORCID,Xia Zhonghua³,Xu Joshua¹,Tong Weida¹^ORCID

Affiliation:

1. Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, FDA, 3900 NCTR Road, Jefferson, Arkansas 72079, United States

2. Division of Preclinical Innovation, National Center for Advancing Translational Sciences, National Institutes of Health, 9800 Medical Center Drive, Rockville, Maryland 20850, United States

3. Institute of Structural Biology, Helmholtz Zentrum München-Research Center for Environmental Health (GmbH), Ingolstädter Landstraße 1, 85764 Neuherberg, Germany

4. BIGCHEM GmbH, Valerystraße 49, DE-85716 Unterschleißheim, Germany

Funder

National Center for Advancing Translational Sciences

China Scholarship Council

National Institutes of Health

CONCERT REACH project

Publisher

American Chemical Society (ACS)

Subject

Toxicology,General Medicine

Link

https://pubs.acs.org/doi/pdf/10.1021/acs.chemrestox.0c00373