Prediction of human population responses to toxic compounds by a collaborative competition

Federica Eduati, Lara M. Mangravite, Tao Wang, Hao Tang, J. Christopher Bare, Ruili Huang, Thea Norman, Mike Kellen, Michael P. Menden, Jichen Yang, Xiaowei Zhan, Rui Zhong, Guanghua Xiao, Menghang Xia, Nour Abdo, Oksana Kosyk, Stephen Friend, Allen Dearry, Anton Simeonov, Raymond R. Tice & 5 others Ivan Rusyn, Fred A. Wright, Gustavo Stolovitzky, Yang Xie, Yang Xie

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

The ability to computationally predict the effects of toxic compounds on humans could help address the deficiencies of current chemical safety testing. Here, we report the results from a community-based DREAM challenge to predict toxicities of environmental compounds with potential adverse health effects for human populations. We measured the cytotoxicity of 156 compounds in 884 lymphoblastoid cell lines for which genotype and transcriptional data are available as part of the Tox21 1000 Genomes Project. The challenge participants developed algorithms to predict interindividual variability of toxic response from genomic profiles and population-level cytotoxicity data from structural attributes of the compounds. 179 submitted predictions were evaluated against an experimental data set to which participants were blinded. Individual cytotoxicity predictions were better than random, with modest correlations (Pearson's r < 0.28), consistent with complex trait genomic prediction. In contrast, predictions of population-level response to different compounds were higher (r < 0.66). The results highlight the possibility of predicting health risks associated with unknown compounds, although risk estimation accuracy remains suboptimal.

Original languageEnglish (US)
Pages (from-to)933-940
Number of pages8
JournalNature Biotechnology
Volume33
Issue number9
DOIs
StatePublished - Sep 10 2015

Fingerprint

Poisons
Cytotoxicity
Chemical Safety
Metagenomics
Health
Population
Safety testing
Genotype
Genome
Cell Line
Health risks
Toxicity
Genes
Cells
Datasets

ASJC Scopus subject areas

  • Applied Microbiology and Biotechnology
  • Biotechnology
  • Molecular Medicine
  • Bioengineering
  • Biomedical Engineering

Cite this

Prediction of human population responses to toxic compounds by a collaborative competition. / Eduati, Federica; Mangravite, Lara M.; Wang, Tao; Tang, Hao; Bare, J. Christopher; Huang, Ruili; Norman, Thea; Kellen, Mike; Menden, Michael P.; Yang, Jichen; Zhan, Xiaowei; Zhong, Rui; Xiao, Guanghua; Xia, Menghang; Abdo, Nour; Kosyk, Oksana; Friend, Stephen; Dearry, Allen; Simeonov, Anton; Tice, Raymond R.; Rusyn, Ivan; Wright, Fred A.; Stolovitzky, Gustavo; Xie, Yang; Xie, Yang.

In: Nature Biotechnology, Vol. 33, No. 9, 10.09.2015, p. 933-940.

Research output: Contribution to journalArticle

Eduati, F, Mangravite, LM, Wang, T, Tang, H, Bare, JC, Huang, R, Norman, T, Kellen, M, Menden, MP, Yang, J, Zhan, X, Zhong, R, Xiao, G, Xia, M, Abdo, N, Kosyk, O, Friend, S, Dearry, A, Simeonov, A, Tice, RR, Rusyn, I, Wright, FA, Stolovitzky, G, Xie, Y & Xie, Y 2015, 'Prediction of human population responses to toxic compounds by a collaborative competition', Nature Biotechnology, vol. 33, no. 9, pp. 933-940. https://doi.org/10.1038/nbt.3299
Eduati, Federica ; Mangravite, Lara M. ; Wang, Tao ; Tang, Hao ; Bare, J. Christopher ; Huang, Ruili ; Norman, Thea ; Kellen, Mike ; Menden, Michael P. ; Yang, Jichen ; Zhan, Xiaowei ; Zhong, Rui ; Xiao, Guanghua ; Xia, Menghang ; Abdo, Nour ; Kosyk, Oksana ; Friend, Stephen ; Dearry, Allen ; Simeonov, Anton ; Tice, Raymond R. ; Rusyn, Ivan ; Wright, Fred A. ; Stolovitzky, Gustavo ; Xie, Yang ; Xie, Yang. / Prediction of human population responses to toxic compounds by a collaborative competition. In: Nature Biotechnology. 2015 ; Vol. 33, No. 9. pp. 933-940.
@article{4b348ca1eae94bf1b10f2f2cb7d89388,
title = "Prediction of human population responses to toxic compounds by a collaborative competition",
abstract = "The ability to computationally predict the effects of toxic compounds on humans could help address the deficiencies of current chemical safety testing. Here, we report the results from a community-based DREAM challenge to predict toxicities of environmental compounds with potential adverse health effects for human populations. We measured the cytotoxicity of 156 compounds in 884 lymphoblastoid cell lines for which genotype and transcriptional data are available as part of the Tox21 1000 Genomes Project. The challenge participants developed algorithms to predict interindividual variability of toxic response from genomic profiles and population-level cytotoxicity data from structural attributes of the compounds. 179 submitted predictions were evaluated against an experimental data set to which participants were blinded. Individual cytotoxicity predictions were better than random, with modest correlations (Pearson's r < 0.28), consistent with complex trait genomic prediction. In contrast, predictions of population-level response to different compounds were higher (r < 0.66). The results highlight the possibility of predicting health risks associated with unknown compounds, although risk estimation accuracy remains suboptimal.",
author = "Federica Eduati and Mangravite, {Lara M.} and Tao Wang and Hao Tang and Bare, {J. Christopher} and Ruili Huang and Thea Norman and Mike Kellen and Menden, {Michael P.} and Jichen Yang and Xiaowei Zhan and Rui Zhong and Guanghua Xiao and Menghang Xia and Nour Abdo and Oksana Kosyk and Stephen Friend and Allen Dearry and Anton Simeonov and Tice, {Raymond R.} and Ivan Rusyn and Wright, {Fred A.} and Gustavo Stolovitzky and Yang Xie and Yang Xie",
year = "2015",
month = "9",
day = "10",
doi = "10.1038/nbt.3299",
language = "English (US)",
volume = "33",
pages = "933--940",
journal = "Biotechnology",
issn = "0733-222X",
publisher = "Nature Publishing Group",
number = "9",

}

TY - JOUR

T1 - Prediction of human population responses to toxic compounds by a collaborative competition

AU - Eduati, Federica

AU - Mangravite, Lara M.

AU - Wang, Tao

AU - Tang, Hao

AU - Bare, J. Christopher

AU - Huang, Ruili

AU - Norman, Thea

AU - Kellen, Mike

AU - Menden, Michael P.

AU - Yang, Jichen

AU - Zhan, Xiaowei

AU - Zhong, Rui

AU - Xiao, Guanghua

AU - Xia, Menghang

AU - Abdo, Nour

AU - Kosyk, Oksana

AU - Friend, Stephen

AU - Dearry, Allen

AU - Simeonov, Anton

AU - Tice, Raymond R.

AU - Rusyn, Ivan

AU - Wright, Fred A.

AU - Stolovitzky, Gustavo

AU - Xie, Yang

AU - Xie, Yang

PY - 2015/9/10

Y1 - 2015/9/10

N2 - The ability to computationally predict the effects of toxic compounds on humans could help address the deficiencies of current chemical safety testing. Here, we report the results from a community-based DREAM challenge to predict toxicities of environmental compounds with potential adverse health effects for human populations. We measured the cytotoxicity of 156 compounds in 884 lymphoblastoid cell lines for which genotype and transcriptional data are available as part of the Tox21 1000 Genomes Project. The challenge participants developed algorithms to predict interindividual variability of toxic response from genomic profiles and population-level cytotoxicity data from structural attributes of the compounds. 179 submitted predictions were evaluated against an experimental data set to which participants were blinded. Individual cytotoxicity predictions were better than random, with modest correlations (Pearson's r < 0.28), consistent with complex trait genomic prediction. In contrast, predictions of population-level response to different compounds were higher (r < 0.66). The results highlight the possibility of predicting health risks associated with unknown compounds, although risk estimation accuracy remains suboptimal.

AB - The ability to computationally predict the effects of toxic compounds on humans could help address the deficiencies of current chemical safety testing. Here, we report the results from a community-based DREAM challenge to predict toxicities of environmental compounds with potential adverse health effects for human populations. We measured the cytotoxicity of 156 compounds in 884 lymphoblastoid cell lines for which genotype and transcriptional data are available as part of the Tox21 1000 Genomes Project. The challenge participants developed algorithms to predict interindividual variability of toxic response from genomic profiles and population-level cytotoxicity data from structural attributes of the compounds. 179 submitted predictions were evaluated against an experimental data set to which participants were blinded. Individual cytotoxicity predictions were better than random, with modest correlations (Pearson's r < 0.28), consistent with complex trait genomic prediction. In contrast, predictions of population-level response to different compounds were higher (r < 0.66). The results highlight the possibility of predicting health risks associated with unknown compounds, although risk estimation accuracy remains suboptimal.

UR - http://www.scopus.com/inward/record.url?scp=84941076570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941076570&partnerID=8YFLogxK

U2 - 10.1038/nbt.3299

DO - 10.1038/nbt.3299

M3 - Article

VL - 33

SP - 933

EP - 940

JO - Biotechnology

JF - Biotechnology

SN - 0733-222X

IS - 9

ER -