Welcome to QSAR DataBase

QsarDB is a smart repository for (Q)SAR/QSPR models and datasets, ready for discovery, exploring, citing and predicting.

Read more about QsarDB

Transparent QSAR data

Create and upload QDB archive


The QsarDB repository requires your model and associated data to be organized. A small effort will make your research transparent and usable.

Cite QSAR data

Link repository with your publication


Include a QsarDB archive DOI in your publication. Taylor & Francis journals now automatically link to a QsarDB archive when the corresponding article DOI is included with the archive.

Explore chemicals

Search from over 66000 structures in QDB archives


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

Explore models

Browse among more than 500 interactive models


Browse the list of endpoints, corresponding QDB archives and among more than 500 models. Visualize models and predict endpoints.

Recent blog posts

On our mind

05 Nov 2021 | Support for QMRF documents in QsarDB

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.

24 Aug 2021 | The QsarDB repository & FAIR principles

In today's world of scientific infrastructure, there is a lot of talk about the compliance of data with FAIR data principles. We decided to test the QsarDB data archives for compliance with FAIR data principles and we are pleased with the FAIRness of 75% for data and models in QsarDB.

26 Oct 2020 | New community from Slovenia (NIC)

The last quarter of 2020 brought a new community from Slovenia. Laboratory for Cheminformatics at National Institute of Chemistry (NIC). NIC has a long history for providing in silico tools for mechanistic and empirical modelling applicable for drug design, assessment of toxicity, and materials optimization.

17 Sep 2020 | QsarDB predictor service supports DRAGON descriptors

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.