While hazard assessment of chemicals can make direct use of descriptive adverse outcome pathways (AOPs), risk assessment requires quantitative relationships from exposure to effect timing and... Show moreWhile hazard assessment of chemicals can make direct use of descriptive adverse outcome pathways (AOPs), risk assessment requires quantitative relationships from exposure to effect timing and magnitude. To seamlessly integrate the data generated by alternative methods or in vivo testing, quantitative AOPs (qAOPs) providing dose-time-response predictions are more valuable than qualitative AOPs. Here, we compare three approaches to qAOP building: empirical dose-response modeling, Bayesian network (BN) calibration, and systems biology (SB) modeling. These methods were applied to the quantification of a simplified oxidative stress induced chronic kidney disease AOP, on the basis of in vitro data obtained on RPTEC/TERT1 cells exposed to potassium bromate. Effectopedia was used to store the experimental data and the developed models in a unified representation so they can be compared and further analyzed. We argue that despite the fact that dose-response models give adequate fits to the data they should be accompanied by mechanistic SB modeling to gain a proper perspective on the quantification. BNs can be both more precise than dose-response models and simpler than SB models, but more experience with their usage is needed. Show less
Finding subsets of a dataset that somehow deviate from the norm, i.e. where something interesting is going on, is a classical Data Mining task. In traditional local pattern mining methods, such... Show moreFinding subsets of a dataset that somehow deviate from the norm, i.e. where something interesting is going on, is a classical Data Mining task. In traditional local pattern mining methods, such deviations are measured in terms of a relatively high occurrence (frequent itemset mining), or an unusual distribution for one designated target attribute (subgroup discovery). These, however, do not encompass all forms of "interesting". To capture a more general notion of interestingness in subsets of a dataset, we develop Exceptional Model Mining (EMM). This is a supervised local pattern mining framework, where several target attributes are selected, and a model over these attributes is chosen to be the target concept. Then, subsets are sought on which this model is substantially different from the model on the whole dataset. For instance, we can find parts of the data where two target attributes have an unusual correlation, a classifier has a deviating predictive performance, or a Bayesian network fitted on several target attributes has an exceptional structure. We will discuss some real-world applications of EMM instances, including using the Bayesian network model to identify meteorological conditions under which food chains are displaced, and using a regression model to find the subset of households in the Chinese province of Hunan that do not follow the general economic law of demand. Show less
