SMIREP is a system for predicting the structural activity of chemical compounds. For that it can be categorized as a SAR/QSAR tool. The advantages of SMIREP are that it is failry fast, due to a heuristic approach of identifying the main features of active versus inactive compounds. The system is written in Python and makes use of the OpenBabel library. In its current version it still uses an old incarnation of OpenBabel. This page provides all neccessary files to compile and run the system on a Linux machine. I have not even tried to make it work on a Windows PC.
The program:Links to older versions:
The OBGrep module for python and openbabel 1.100.2:
The data used in our publication:
In case you need Python:
Go to www.python.org and get the latest release.
None so far.
Download all files above. You need a working version of Python. After downloading, unzip the OpenBabel tar files (tar -xvfz openbabel-1.100.2.tar.gz) and compile the library (use the --prefix="XXX" option to install it to your preferred system directory called XXX). After this you will need to install the python library OBGrep. For this extract the gzipped tar file as before, and go to the OBGrep subdirectory. The command "python setup.py install" should compile the library and install it to the python lib directory.Known Issues:
After this OpenBabel specific installation you can simply unpack the SMIREP program and data files, descend into the subdirectory SMIREP_V1.0 and read the instructions (README file).
The QSAR version is slower than the SAR version. This is also mentioned in the arcticle.
A. Karwath and L. De Raedt: Predicting Chemical Activities with SMIREP, Journal of Chemical Information and Modelling, TBP 2006Contact:
A. Karwath and L. De Raedt: Predictive Graph Mining. In: E. Suzuki and S. Arikawa (Eds.): Proc. 7th International Conference of Discovery Science, DS 2004. October. Lecture Notes in Artificial Intelligence 3245. pp. 1-15. Springer-Verlag.(2004)
andreas AT karwath.org : A. Karwath