We are pleased to announce the publication of KREATiS’ last paper, entitled “A New classification algorithm based on Mechanisms of Action”, in the journal Computational Toxicology! Authors: Franklin J. Bauer, Paul C. Thomas, Samuel Y. Fouchard, Serge J.M. Neunlist.
This article presents the results of 3 years of research in KREATiS to understand and characterize the relationships between the structure of compounds and their mechanism of toxic action (MechoA). MechoAs are related to molecular initiating events, the first step of Adverse Outcome Pathways (AOPs). A good understanding of MechoAs and appropriate methods to determine them is crucial for the accurate prediction of toxicity using in silico techniques.
In KREATiS, to ensure a high-accuracy prediction of (eco)toxicity, we first determine the MechoA of compounds, in order to apply the appropriate HA-QSAR to the substance, which will predict the E/LC50 or NOEC/EC10 with high reliability.
In the most common classification algorithms used to predict Modes of toxic Action, the prediction domain is often limited by the need to identify known structural alerts. To circumvent this limitation, we developed a new algorithm to predict MechoAs principally based on mammals and fish, using molecular modelling to obtain calculated molecular parameters. Comparing the Verhaar scheme as modified by Enoch et al. (2008) with the MechoA method for the same validation set, MechoA achieved 69% correct classifications as opposed to 45% for the Verhaar scheme, 17% misclassifications for both, 13% classifications slightly different from the literature for our algorithm. Only 1% of the molecules were out of the prediction domain of the algorithm as opposed to 38% using the Verhaar scheme. Thus, this model enhances precision of correct AOP identification for in silico toxicity predictions.
You can find the article online at http://www.sciencedirect.com/science/article/pii/S2468111317300567.
Moreover, please notice that we are preparing a second article on Mechanisms of Action, which will present a second method of prediction, simpler and more efficient. You should be able to see this in a few months time. This second method is already being implemented in our web-based tool iSafeRat® Online, and will soon be made freely available.
In the meanwhile, if you have any questions or queries, please contact us at firstname.lastname@example.org!