The Auto-Modeler gives both novice and expert users access to the tools needed to thoroughly analyse data and produce validated, predictive models. Output from the Auto-Modeler includes Glowing Molecule results, giving you an instant visual link between structure and properties.
For users who are not computational experts, the Auto-Modeler can:
- Automatically generate models: multiple advanced modeling techniques can be applied to data, helping you identify the most appropriate model
- Train, test and validate: split your data into sub-sets using automatic clustering to rigorously validate your models
- Descriptor libraries: molecular descriptors such as molecular weight, logP and polar surface area and 2D structural descriptors are included with the Auto-Modeler
- Manually split data sets
- Choose modeling techniques to apply
- Input your own descriptors, including experimental data
- Download data sets with cluster information, descriptor values and more.
If you would like to know more about how these models work, take a look at the FAQs. The Auto-Modeler is available as an optional module for StarDrop. To find out more about StarDrop and the Auto-Modeler module or to arrange an online demonstration please contact us.
"StarDrop Auto-Modeler Wins Environmental Toxicity Prediction Challenge - Olga Obrezanova's model came out joint winner in a challenge organised by ICANN'09, European Neural Network Society (ENNS) and CADASTER."


