Format

Send to

Choose Destination
Regul Toxicol Pharmacol. 2014 Aug;69(3):443-50. doi: 10.1016/j.yrtph.2014.05.010. Epub 2014 May 17.

Developing scientific confidence in HTS-derived prediction models: lessons learned from an endocrine case study.

Author information

1
Cox Associates, 503 Franklin St, Denver, CO 80218, USA. Electronic address: tcoxdenver@aol.com.
2
Cox Associates, 503 Franklin St, Denver, CO 80218, USA. Electronic address: doug@cox-associates.com.
3
The Dow Chemical Company, Toxicology & Environmental Research & Consulting, 1803 Building Washington Street, Midland, MI 48674, USA. Electronic address: MSMarty@dow.com.
4
The Dow Chemical Company, Toxicology & Environmental Research & Consulting, 1803 Building Washington Street, Midland, MI 48674, USA. Electronic address: JCRowlands@dow.com.
5
DuPont Haskell Global Centers for Health and Environmental Sciences, Stine 320/212, 1090 Elkton Road, Newark, DE 19711, USA. Electronic address: patlewig@hotmail.com.
6
ExxonMobil Biomedical Sciences Inc., 1545 Route 22, East Annandale, NJ 08801, USA. Electronic address: katy.o.goyak@exxonmobil.com.
7
Regulatory and Technical Affairs Department, American Chemistry Council (ACC), 700, 2nd Street NE, Washington, DC 20002, USA. Electronic address: Rick_Becker@americanchemistry.com.

Abstract

High throughput (HTS) and high content (HCS) screening methods show great promise in changing how hazard and risk assessments are undertaken, but scientific confidence in such methods and associated prediction models needs to be established prior to regulatory use. Using a case study of HTS-derived models for predicting in vivo androgen (A), estrogen (E), thyroid (T) and steroidogenesis (S) endpoints in endocrine screening assays, we compare classification (fitting) models to cross validation (prediction) models. The more robust cross validation models (based on a set of endocrine ToxCastâ„¢ assays and guideline in vivo endocrine screening studies) have balanced accuracies from 79% to 85% for A and E, but only 23% to 50% for T and S. Thus, for E and A, HTS results appear promising for initial use in setting priorities for endocrine screening. However, continued research is needed to expand the domain of applicability and to develop more robust HTS/HCS-based prediction models prior to their use in other regulatory applications. Based on the lessons learned, we propose a framework for documenting scientific confidence in HTS assays and the prediction models derived therefrom. The documentation, transparency and the scientific rigor involved in addressing the elements in the proposed Scientific Confidence Framework could aid in discussions and decisions about the prediction accuracy needed for different applications.

KEYWORDS:

Adverse outcome pathways; Endocrine; High throughput/high content assays; Prediction models; Validation framework

PMID:
24845243
DOI:
10.1016/j.yrtph.2014.05.010
[Indexed for MEDLINE]
Free full text

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center