These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
Manuscript-Including Suppl-Material-Updated.pdf (1.62 MB)

Predicting Environmental Chemical Toxicity using a New Hybrid Deep Machine Learning Method

revised on 17.02.2021, 04:45 and posted on 17.02.2021, 09:09 by Sarita Limbu, Cyril Zakka, Sivanesan Dakshanamurthy
Humans are exposed to thousands of potentially toxic chemicals including environmental chemicals such as industrial wastes, food products, solvents, air pollutants, fertilizers, pesticides, insecticides, carcinogens, drugs, metals/metalloids, and other industrial chemicals. Approximately 300,000 such chemicals currently in use, unfortunately little is known about their potential toxicity. Determining human toxicity potential of chemicals remains a challenge due to a substantial resource required to assess a chemical in-vivo, and only a few thousand single chemicals in commercial use has been evaluated. In this study, to predict the environmental chemical toxicity, we developed a new hybrid neural network (HNN) deep learning model consisting of a Convolutional Neural Network (CNN) and multilayer perceptron (MLP) type feed forward neural network (FFNN). Our HNN deep learning model trained based on thousands of chemicals, presented the best performance for majority of the cases. Taken together, our hybrid HNN deep learning models has a wide applicability in the prediction of toxicity of any chemical category and its mixtures.


United States Department of Defense (DOD) grant CA140882

CCSG grant P30 CA051008/CA/NCI NIH HHS/United States


Email Address of Submitting Author


Georgetown University



ORCID For Submitting Author


Declaration of Conflict of Interest


Version Notes

Running text has been edited/updated and some figures has been moved to the supplementary materials. Both main manuscript and Supplementary materials are in single document and uploaded as single Pdf file. Thanks.