Researchers at the EPA’s National Center for Computational Toxicology integrate advances in biology, chemistry, and computer science to examine the toxicity of chemicals and help prioritize chemicals for further research based on potential human health risks. The intention of this research program is to quickly evaluate thousands of chemicals for potential risk but with much reduced cost relative to historical approaches. This work involves computational and data driven approaches including high-throughput screening, modeling, text-mining and the integration of chemistry, exposure and biological data. We have developed a number of databases and applications that are delivering on the vision of developing a deeper understanding of chemicals and their effects on exposure and biological processes that are supporting a large community of scientists in their research efforts. This presentation will provide an overview of our work to bring together diverse large scale data from the chemical and biological domains, our approaches to integrate and disseminate these data, and the delivery of models supporting computational toxicology. This abstract does not reflect U.S. EPA policy.

1. Delivering The Benefits of Chemical-Biological
Integration in Computational Toxicology
at the EPA
Antony Williams†, Kamel Mansouri, Chris Grulke, Keith Houck,
Ann Richard, Jeff Edwards, Matt Martin, John Wambaugh,
Grace Patlewicz, Imran Shah, Richard Judson, Kevin Crofton
and Russell Thomas
National Center for Computational Toxicology
U.S. Environmental Protection Agency, RTP, NC
August 21-25, 2016
ACS Fall Meeting, Philadelphia, PA
This work was reviewed by the U.S. EPA and approved for presentation but does not necessarily reflect official Agency policy.
http://www.orcid.org/0000-0002-2668-4821

2. Who is NCCT?
• National Center for Computational Toxicology – part of EPA’s
Office of Research and Development
• Research driven by EPA’s Chemical Safety for Sustainability
Research Program
– Develop new approaches to evaluate the safety of chemicals
– Integrate advances in biology, biotechnology, chemistry, exposure
science and computer science
• Goal - To identify chemical exposures that may disrupt
biological processes and cause adverse outcomes.
1

3. Scientific leadership
https://www.epa.gov/chemical-research/toxicity-forecasting
2

4. Our Bioassay Data
https://www.epa.gov/chemical-research/downloadable-computational-toxicology-data
3

5. Our Exposure Predictions
4

6. Our Dashboard Applications
5

7. ACToR
https://actor.epa.gov/actor/
• Aggregated Computational Toxicology
Resource
• A warehouse of publicly available chemical
toxicity data
• Aggregates data from >1000 public sources
on >500,000 chemicals
6

8. ACToR
https://actor.epa.gov/actor/
7

9. ACToR
https://actor.epa.gov/actor/
8

10. CPCat
https://actor.epa.gov/actor/
9
Chemical and Product Categories is a
database containing information mapping
>43,000 chemicals to a set of terms
categorizing their usage or function.

11. Toxcast Dashboard
https://actor.epa.gov/dashboard/
• To interrogate chemical screening data from
ToxCast and the Tox21 collaboration
10

12. Our Developing Architecture

13. Our Latest Dashboard
https://comptox.epa.gov
• Providing access to our “curated chemistry”
• Database of chemicals, mapped to identifiers,
and tens of thousands of experimental
physchem properties
• Predictive models and calculation details
• An integration hub for NCCT applications
• A link farm across 10s of EPA and Public
websites
12

14. Our Latest Dashboard
https://comptox.epa.gov
13
>720,000 chemicals
>14 years of assembled data
An Integration Hub

15. 15 years of Curated Data
14

16. Bisphenol A
(Accessing DSSTox Data)
15

17. Physicochemical Properties
16

18. Data Downloads
17

19. Data Download: Excel
18

20. Predictions for >720,000 Chemicals
• NCCT_Model predictions built on curated data
• All chemicals in CompTox Dashboard pushed
through all predictive models
• Predicted data made available, with detailed
MODEL REPORTS
19

21. Predicted Data
20
Calculation Result
for a chemical
Model Performance
with full QMRF
Nearest Neighbors
from Training Set

22. Prediction Details and
QMRF Report
21

23. External Links
22

24. Synonyms
23
Over a million synonyms, different
levels of curation and validation

25. Functional Use and Composition
(Integrating CPCat Data)
24

26. Bioassay Screening Data
(Integrating ToxCast Data)
25

27. Bioassay Screening Data
(Integrating ToxCast Data)
26

28. Exposure Data – NHANES and
ExpoCast Predictions
27
Environ. Sci. Technol., 2013, 47 (15), pp 8479–8488

29. PubChem integration
28

30. Work in Progress: Environmental
Fate, Transport and Toxicity
29

31. Work in Progress: Analog
Identification and Similarity Search

32. Conclusions
• NCCT has been delivering data, algorithms,
models and software tools for a decade
• A new flexible architecture to support
multiple both internal and external apps
• First iteration of CompTox dashboard
supports chemistry based searches
• Future concept…
31

33. Future Search Possibilities
32
Chemicals Products Targets Assays Literature

34. Acknowledgements
Kamel Mansouri
Chris Grulke
Keith Houck
Ann Richard
Jeff Edwards
Matt Martin
John Wambaugh
Grace Patlewicz
Imran Shah
Richard Judson
Kevin Crofton
Russell Thomas