Each model in QsarDB can be used for prediction if the user calculates or determines experimentally the descriptors in the model and enters them in the “QDB Predictor” application  or via the REST service . For some models, the prediction service also works directly from the structure. In this case, the QsarDB repository calculates the required molecular descriptors on the fly. Currently, QsarDB supports this functionality for a limited number of models, and they use open source software (Chemistry Development Kit, PaDEL-Descriptor and XlogP3) to calculate molecular descriptors.
In 2020, the QsarDB team celebrated Europe Day (May 9) in a modest but professional way. Namely, on that day, a new community was opened for the European Union Reference Laboratory for Alternatives to Animal Testing (EURL ECVAM), which is a part of the European Commission's Joint Research Center (JRC) in Ispra, Italy.
The topic of Big Data has strongly entered into predictive and computational toxicology, and is here in order to stay. However, not only the data is big, large are also computational models (the so-called QSAR models) derived from these data. Therefore, the management of computational models in the context of Big Data needs more attention and efforts, so that the models remain transparent and independently verifiable.
The last quarter of 2019 brought two new communities to the QsarDB, namely, Ineris (France) and Chemoinformatics Research Group from Liverpool John Moores University (England).
19th International Workshop on (Quantitative) Structure-Activity Relationships in Environmental and Health Sciences will be in Durham, NC, June 8-11, 2020.