Knowledge-mining software tool for automatic dataset analysis

All you need is a prepared sdf-file with compounds and their property values.

Features:

  1. Automatic models building, tuning and validation.
  2. Automatic fragments generation and contribution calculation.
  3. Plot fragment contributions and save to an external file.

In the framework of development of this project several github repositories were created:

  • spci - main module with GUI and all features written in Python
  • spci-ext - Python scripts to carry out fragmentation of compounds to further calculate descriptors and make prediction by external software tool and then calculate fragment contributions
  • rspci - R package for flexible post-processing and visualization of fragment contributions

Installation and short description of the main software tool is given in the manual

If you found bugs, have questions or propositions please don't hesitate to contact me - pavel_polishchuk@ukr.net

Quick installation notes for Windows users.
To install application just download and unzip into the same folder WinPython and sirms-spci archives.


Installation OS Size Comments
WinPython-32bit-3.5.5.7.zip Windows ~360 Mb WinPython-32bit + all dependencies. Updated 02.05.2015.
WinPython-64bit-3.5.5.7.zip Windows ~360 Mb WinPython-64bit + all dependencies. Updated 02.05.2015.
sirms-spci.zip Windows, Linux ~8 Mb Main program. Version 0.1.5. Updated 09.05.2016.

SPCI software


Alternative visualization of output
For those who dislikes Python images and is not familiar with R I recommend to use the developed online tool spci-vis - you just need to upload your text file with calculated fragment contributions and customize plot output. The plot can be saved in different formats.

Example output

SiRMS-QSAR software

How to cite

The paper which describes structural interpretation:

P. G. Polishchuk, V. E. Kuz'min, A. G. Artemenko and E. N. Muratov. Universal Approach for Structural Interpretation of QSAR/QSPR Models. Molecular Informatics 2013, 32, 843-853. - http://dx.doi.org/10.1002/minf.201300029

The paper which describes the integrated structural and physicochemical interpretation (SPCI) approach:

Polishchuk P, Tinkov O, Khristova T, Ognichenko L, Kosinskaya A, Varnek A, Kuz’min V. Structural and Physico-Chemical Interpretation (SPCI) of QSAR Models and Its Comparison with Matched Molecular Pair Analysis. Journal of Chemical Information and Modeling 2016, 56, 1455–1469 - http://dx.doi.org/10.1021/acs.jcim.6b00371

© Pavel Polishchuk 2010-2017