White Paper

Mining Big Data to Predict Toxicities

Mining Big Data to Predict Toxicities

This article, co-authored by UL's Senior Toxicologist, Craig Rowlands with Johns Hopkins University, addresses machine learning of toxicological big data to enable read-across structure activity relationships (RASAR) outperforming animal test reproducibility.

Earlier we created a chemical hazard database via natural language processing of dossiers submitted to the European Chemical Agency with ~10,000 chemicals. We identified repeat OECD guideline tests to establish reproducibility of acute oral and dermal toxicity, eye and skin irritation, mutagenicity and skin sensitization. Based on 350 to 700+ chemicals each, the probability that an OECD guideline animal test would output the same result in a repeat test was 78% to 96% (sensitivity 50-87%).

An expanded database with more than 866,000 chemical properties/hazards was used as training data and to model health hazards and chemical properties. The constructed models automate and extend the read-across method of chemical classification. The novel models called RASARs (read-across structure activity relationship) use binary fingerprints and Jaccard distance to define chemical similarity. A large chemical similarity adjacency matrix is constructed from this similarity metric and is used to derive feature vectors for supervised learning. We show results on nine health hazards from two kinds of RASARs – ‘Simple’ and ‘Data Fusion’. The ‘Simple’ RASAR seeks to duplicate the traditional read-across method, predicting hazard from chemical analogues with known hazard data. The ‘Data Fusion’ RASAR extends this concept by creating large feature vectors from all available property data rather than only the modeled hazard.


Simple RASAR models tested in cross-validation achieve 70-80% balanced accuracies with constraints on tested compounds. Cross validation of data fusion RASARs show balanced accuracies in the 80-95% range across 9 health hazards with no constraints on tested compounds.

  • English


The views, opinions and technical analyses presented here are those of the author, and are not necessarily those of UL LLC. All content is subject to copyright and may not be reproduced without prior authorization from UL. While the editors of this site may verify the accuracy of its content from time to time, we assume no responsibility for errors made by the author, editorial staff or any other contributor.