Auto-Modeller
Build and validate robust QSAR models tailored to your chemistry and data
![]() | This module gives both novice and expert users access to the tools needed to produce validated, predictive models. Output from the Auto-Modeller includes Glowing Molecule results that help to visualise the structure-activity relationships captured from your chemistry and data. |
Even if you are not an expert in modelling you can:
- Automatically generate predictive models
- Use multiple advanced modelling techniques, including Gaussian Processes, Random Forests, Radial Basis Functions, PLS and Decision Trees
- Train, test and validate: automatically split your data into sub-sets to rigorously choose and validate the best model
- Use a suite of built-in descriptors; MWt, logP, polar surface area and many other 2D structural descriptors are included with the Auto-Modeller
If you would like to know more about the Auto-Modeler, take a look at the FAQs.
The Auto-Modeller is available as an optional module for StarDrop. To find out more about StarDrop and the Auto-Modeller, to arrange an online demonstration or to try StarDrop for yourself, please contact us.


"Take a look at our ACS presentation where we describe the Gaussian Processes method, discuss its strengths and weaknesses and compare its results with other QSAR modelling methods. This is illustrated by several examples applications to different QSAR modelling problems."
