eTOXlab is a flexible modeling framework. It was developed for supporting models predicting the biological properties of chemical compounds (e.g. QSAR models) in production environments. It is distributed embedded within a virtual machine containing all required software for building models and using them for prediction. Together, the ensemble eTOXlab-VM constitutes a portable, self-contained prediction engine that can be easily distributed and installed.
Carrió P, López O, Sanz F, Pastor M. eTOXlab, an open source modeling framework for implementing predictive models in production environments. J Cheminform 2015; 7: 8. doi:10.1186/s13321-015-0058-6 on-line access
eTOXlab is distributed here pre-installed in a Linux virtual machine. It was tested and works well with VirtualBox and QEMU under Linux and Windows OS, but other virtual machine players can be suitable as well.
The minimum hardware requirements are a computer with 1 CPU supporting virtualization and 2Gb RAM.
Once the VM is running, the pre-loaded models are accessible immediately as web-services at address http://localhost:9001/predictform. The prediction results are provided in JSON format and can be easily exported, formatted and integrated using a large variety of tools.
From outside the VM you can also access the webservice from the host computer at address http://localhost:7000/predictform
Advanced users can login into the VM as “modeler” (no password) and make full use of eTOXlab. Root password is "envoy1900".
A very simple HOW-TO explaining how building and using simple models can be accessed here. The Supplementary Information of the original article has also been updated to the latest version and can be downloaded here
Please be patient. The files are huge (nearly 3Gb) and the downloading can take some time, depending of the speed of your connection.
Please feel free to contact us (firstname.lastname@example.org) for any question regarding eTOXlab. We do not promise to provide full technical support but will do our best.
eTOXlab was developed by the PharmacoInformatics Group, in the framework of the eTOX project and with the financial support from the IMI, under grant agreement nº 115002 (eTOX), resources of which are composed of financial contribution from the EU’s FP7 and EFPIA companies’ in kind contributions.