After a long period of development and testing, the QsarDB repository has added support for the Open Neural Network Exchange (ONNX) format. Please note that the preferred and core model representation format for QsarDB is still Predictive Model Markup Language (PMML). PMML works well for represent...
As part of our ongoing operations, we have upgraded the web interface of the QsarDB repository with a range of updates that improve its usability. We have modernized page layouts and made them more friendly for mobile devices. Also, we have upgraded the repository software to version 6.4 of the DSpa...
At the end of the 2021, we looked back to evolution of QsarDB webpage, and discovered that every couple of years we tend to refresh the appearance of it. Therefore, we decided to start year 2022 with new visual look for QsarDB main webpage! To share the journey with you, we made a gallery of QsarDB webpage changes over the years.
Many proprietary QSAR models are readily available and easy to use, but often lack transparency and are like “black boxes” to end users. QSAR Model Reporting Format (QMRF)[1] documents address this issue by providing a template for summarizing key information on QSAR models, where the information is structured according to the OECD (Q)SAR validation principles. In order to improve the availability and findability of QMRFs, we improved support for QMRFs in the QsarDB repository.
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 [1] or via the REST service [2]. 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.