News Release

Big data approach can predict toxicity of chemicals, save animals

PETA India will present findings at national conference

Peer-Reviewed Publication

People for the Ethical Treatment of Animals (PETA)

Delhi -- Experts from across India will gather from July 31 to August 1 at the Indian Institute of Technology Delhi for a national conference, "Breaking Barriers Through Bioinformatics and Computational Biology," to share information on the latest developments in this area.

Several international data-sharing projects have resulted in large amounts of publicly available data that can now be used to predict the toxicity of chemicals without conducting animal tests. The enormous size of these databases makes them difficult to process using conventional data-analysis tools. However, recent advances in big-data analytics offer new methods for data-driven predictions of chemical toxicity.

PETA India will describe how companies can use these advances to reduce animal testing and will provide the government with suggestions on promoting these methods among researchers and companies. This approach can be adopted by various international regulatory agencies as an animal-free alternative for predicting a chemical's toxicity.

A PETA India poster will discuss the drawbacks of traditional animal-based approaches to determining toxicity, the progress on data-sharing projects to date, and how data available in public repositories (e.g., PubChem, ChEMBL, and TOXNET) can be used to develop models to predict the toxicity profile of chemical compounds. Also discussed will be steps that the government and regulatory authorities can take to adopt this methodology and reduce animal testing. A copy of the poster is available upon request.

According to PETA India's Dr. Rohit Bhatia, "Replacing animal-based methods of predicting toxicity with an advanced big data analytics approach will save time, money, and many animals' lives."

###


Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.