The QsarDB data format provides a simple framework for representing models and their associated data. This effort will make your research transparent and usable.

All models in QsarDB are represented in accordance with FAIR principles. Join QsarDB and share or cite your models, or connect them with publications using assigned DOIs.

Increase the discoverability of your QMRFs by making them available through QsarDB.

Browse among models that have descriptor calculation built in. Choose an appropriate model, make a prediction, and assess how well your chemical fits within the model's applicability domain.

Exact chemical, similarity, and substructure searches help to find QDB archives containing the query compound.

QsarDB currently includes models for various endpoint groups, including physical and chemical properties, ecotoxicity, environmental fate endpoints, human health, and toxicokinetics. Choose the most suitable model that fits your problem.

Browse QDB archives and use more than 500 interactive models. Visualize models and gather information about corresponding chemical structures.

13 May 2025

Beljkas, M.; Zukic, S.; Mirjacic Martinovic, K.; Djuric, A.; Vuletic, A.; Corinne, J.; Hölzel, J.; Böttger, E.; Gajić, M.; Santibanez F, J.; Stark, H.; Živković, A.; Srdic-Rajic, T.; Arimondo, P.; Maran, U.; Nikolic, K.; Petkovic, M.; Oljacic, S. Molecular Docking, Machine Learning-Guided Design, Synthesis, and Biological Evaluation of Novel Multitarget HDAC/ROCK Inhibitors. ChemRxiv 2025.

07 May 2025

Akinola, L. K.; Uzairu, A.; Shallangwa, G. A.; Abechi, S. E. Development of binary classification models for grouping hydroxylated polychlorinated biphenyls into active and inactive thyroid hormone receptor agonists. SAR and QSAR in Environmental Research 2023, 34, 267–284.

17 Mar 2025

Toots, K. M.; Sild, S.; Leis, J.; Acree, W. E.; Maran, U. A multicomponent QSPR approach to describe and predict gas-ionic liquid distribution of organic solutes using machine learning. J. Mol. Liq. 2025, 436, 128184.

25 Oct 2024

Käärik, M.; Krjukova, N.; Maran, U.; Oja, M.; Piir, G.; Leis, J. Nanomaterial texture-based machine learning of ciprofloxacin adsorption on nanoporous carbon. Int. J. Mol. Sci. 2024, 25, 11696.

14 Oct 2025

FAIR principles and QSAR models

19 Jun 2025

Presentation of FAIR experience with QsarDB

18 Jun 2025

QsarDB workshop at PARC Modelers Meeting

28 Sep 2023

CoreTrustSeal certificate awarded!

29 Jun 2023

Integration of QsarDB models into the OECD QSAR Toolbox