Tox21Challenge to Build Predictive Models of Nuclear Receptor and Stress Response Pathways as Mediated by Exposure to Environmental Chemicals and Drugs

Ruili Huang,Tongan Zhao,Sampada A Shahane,Jinghua Zhao,Anton Simeonov,Anna Rossoshek,Dac-Trung Nguyen,Menghang Xia,Srilatha Sakamuru

doi:10.3389/fenvs.2015.00085

Abstract

Tens of thousands of chemicals with poorly understood biological properties are released into the environment each day. High-throughput screening (HTS) is potentially a more efficient and cost-effective alternative to traditional toxicity tests. Using HTS, one can profile chemicals for potential adverse effects and prioritize a manageable number for more in-depth testing. Importantly, it can provide clues to mechanism of toxicity. The Tox21 program has generated >50 million quantitative high-throughput screening (qHTS) data points. A library of several thousands of compounds, including environmental chemicals and drugs, is screened against a panel of nuclear receptor and stress response pathway assays. The National Center for Advancing Translational Sciences (NCATS) has organized an International data challenge in order to “crowd-source” data and build predictive toxicity models. This Challenge asks a “crowd” of researchers to use these data to elucidate the extent to which the interference of biochemical and cellular pathways by compounds can be inferred from chemical structure data. The data generated against the Tox21 library served as the training set for this modeling Challenge. The competition attracted participants from 18 different countries to develop computational models aimed at better predicting chemical toxicity. The winning models from nearly 400 model submissions all achieved >80% accuracy. Several models exceeded 90% accuracy, which was measured by area under the receiver operating characteristic curve (AUC-ROC). Combining the winning models with the knowledge already gained from Tox21 screening data are expected to improve the community’s ability to prioritize novel chemicals with respect to potential human health concern.

Highlights

Humans are exposed to many different chemicals during the course of their lifetimes through various sources including food, household cleaning products, and medicines
The quantitative high-throughput screening (qHTS) data generated on the Tox21 10K compound collection are publicly available (PubChem, 2013a,b)
Ci = wj · Pj j=1 where n is the total number of models that provided predictions for chemical i, Pj is the predicted probability of chemical i being active by model j, and wj is the weight of model j, which is the area under the receiver operating characteristic curve (AUC-Receiver Operating Characteristic (ROC)) score on the final evaluation set obtained by model j

Summary

INTRODUCTION

Humans are exposed to many different chemicals during the course of their lifetimes through various sources including food, household cleaning products, and medicines. The Tox21 10K library has been tested in a quantitative high-throughput screening (qHTS) format against a panel of nuclear receptor (NR) (Huang et al, 2011, 2014; Hsu et al, 2014; Chen et al, 2015) and stress response (SR) pathway assays (Attene-Ramos et al, 2015; Nishihara et al, 2016), producing over 50 million data points to date (PubChem, 2013b) These data can serve as a knowledge-base to correlate chemical structures to their biological activities to develop QSAR models. For final model evaluation and scoring, a new set of compounds provided by the EPA, for which no experimental data were available at the time of the Challenge, was screened against the 12 assays. Three hundred and seventy eight model submissions from 40 teams were received for final evaluation (Figure 1)

METHODS

RESULTS AND DISCUSSION

Methods used by Winning Teams