Exposure to external toxicants (cigarette smoke, pollutants, pesticides etc.) can induce significant molecular changes in human blood. Given that blood is easily accessible, it would be advantageous to identify specific markers in blood cells that could predict whether an individual had been exposed to a given toxicant. Such knowledge would have valuable implications for the toxicological risk-assessment of chemicals, drugs and consumer products, as well as for diagnostics.
However, blood is a complex tissue to analyze, primarily due to the many different cell sub-populations it contains. Molecular changes brought about by exposure to a toxicant may involve a complex interplay of a sub-set of the chemicals present in the toxicant itself, molecules produced by the exposed organ (e.g., the lungs or the gut), and chemical-derived metabolites.
Furthermore, the real-world application of models based on blood markers for predictive classification of individuals is uniquely challenging. The difficulty resides in the identification of relevant markers in blood after chemical exposure, the low success of correct classification when predictive models are applied on new individual blood samples, and the translation of these techniques into practical ready-to-use tools. In addition, most pre-clinical toxicological in vivo studies are conducted in rodents, adding a degree of complexity when applying the results to humans.
The Systems Toxicology Computational Challenge
The sbv IMPROVER Systems Toxicology Computational Challenge was designed to explore these issues and to help increase scientists’ understanding of what is necessary to reach higher levels of predictability and robustness in predictive toxicology. Specifically, the scientific questions raised in the challenge concerned the identification of blood response markers and models that can predict smoking exposure or cessation status.
The challenge was open to anyone working in computational sciences who develops predictive modeling techniques. Provided with blood transcriptomics datasets, participants were asked to solve two tasks. First, they were asked to derive predictive classification models that would distinguish current tobacco smokers from non current smokers (prediction of smoking exposure status). Second, they were asked to discriminate non current smokers as former smokers and never smokers (prediction of cessation status). Anonymized participants’ submissions were then scored against a gold-standard dataset, with final results and rankings approved by an independent expert scoring review panel.
To read the full contents of this article click here.