Physiological variables in machine learning QSARs allow for both cross-chemical and cross-species predictions

A major challenge in ecological risk assessment is estimating chemical-induced effects across taxa without species-specific testing. Where ecotoxicological data may be more challenging to gather, information on species physiology is more available for a broad range of taxa. Physiology is known to drive species sensitivity but understanding about the relative contribution of specific underlying processes is still elusive. Consequently, there remains a need to understand which physiological processes lead to differences in species sensitivity. The objective of our study was to utilize existing knowledge about organismal physiology to both understand and predict differences in species sensitivity. Machine learning models were trained to predict chemical-and species -specific endpoints as a function of both chemical fingerprints/descriptors and physiological properties repre-sented by dynamic energy budget (DEB) parameters. We found that random forest models were able to predict chemical-and species-specific endpoints, and that DEB parameters were relatively important in the models, particularly for invertebrates. Our approach illuminates how physiological properties may drive species sensi-tivity, which will allow more realistic predictions of effects across species without the need for additional animal testing.

Automated summary

A major challenge in ecological risk assessment is estimating chemical-induced effects across taxa without species-specific testing. Our study utilized existing knowledge about organismal physiology to understand and predict differences in species sensitivity. Machine learning models were trained to predict chemical- and species-specific endpoints based on both chemical fingerprints and physiological properties.