Chemistry for qsar modeling

Application note

QSAR Modeling of ErbB1 Inhibitors Using Genetic Algorithm-Based Regression

Why use reaxys medicinal chemistry for qsar modeling?

The database of this research solution is organized around compounds, targets and biological activities. Each element is described and organized into logical hierarchies according to experimental protocols appearing in the literature. Taken as a whole, the information compiled by Reaxys Medicinal Chemistry creates a global pharmacology space encompassing more than 447,000 literature sources, 12,700 targets and over 29 million biological activities.

The user interface enables scientists to navigate this pharmacology space and conduct a variety of searches, including substructure, chemical similarity and target-specific searches to explore the bioactivity profile for targets, cell lines or drugs/compounds. Retrieved data is displayed in the interactive results screen, where the user can filter data to exclude or limit certain data sets, focus on compounds or targets or view a complete list of citations.

Reaxys Medicinal Chemistry displays compound–target data as an interactive Heatmap so that researchers can rapidly visualize, navigate and filter results based on various parameters such as activity, species, bioassay protocols, publication type and standard target classification hierarchies.

Importantly for QSAR and other chemoinformatics modeling, Reaxys Medicinal Chemistry provides multiple options to use and integrate the content into existing tools and in-house systems. Data can easily be exported for use in a number of popular modeling packages such as MOE™ (Molecular Operating Environment, Chemical Computing Group), Schrödinger® Small-Molecule Drug Discovery Suite, Biovia® (Dassault Systèmes) and ChemAxon products or integrated into in-house software. The extensive database can be used to conduct pharmacophoric similarity searches, chemical space analyses, structural analog searching, virtual screening and quantitative structure–activity or structure–property relationship (QSAR/QSPR) modeling.

Essential drug discovery solution

Reaxys Medicinal Chemistry is an extensive database containing chemical information linked to in vitro and in vivo biological activities extracted from over 300,000 articles, 90,000 patents and 5,000 journals. More than 6 million chemical compounds are associated with their biological data (> 29 million bioactivity data points) and linked to information on 12,700 pharmacological targets, allowing the scientists to reveal connections between compounds, effects and targets. The data is indexed and normalized for maximum searchability and consistency.

Note: This application note is for illustrative purposes only: the information in this report should not be referenced or relied upon as a basis for further research and development.


  1. Engel, T. (2006) Basic Overview of Cheminformatics. J. Chem. Inf. Model. 46: 2267–2277.
  2. Polanski, J. Bak, A., Gielciak, R. and Magdiarz, T. (2006) Modeling robust QSAR. J. Chem. Inf. Model. 46: 2310–2318.
  3. Szántai-Kis, C., Kövesdi, I., Eros, D., Bánhegyi, P., Ullrich, A. (2006) Prediction oriented QSAR modelling of EGFR inhibition. Current Medicinal Chemistry 13: 277–287.