Skip to content

martin-sicho/data_mining_2014

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Data mining project - 2014

This repo was created for a school project. It is an implementation of a very simple classification and QSAR modelling tool.

WARNING: The code is mostly ugly :)

How to work with it

Each module has params.py file where the parameters of the module can be specified. You will probably want to configure at least the datageneration module, which contains definitions of file paths and some basic parameters such as the protein target, clustering threshold...

Please note that you will have to download the decoys as an .sdf file and point to the proper loacation via datamanipulation.params.DECOYS_SDF_FILE_PATH. Actives should be downloaded automatically.

The modules are loaded from the main.py file in the root of the repo. The main.py file includes a method that builds models, a prediction method for pIC50 predicitons and the main method. The main method includes a simple usage example.

About

SVM classification and regression for some QSAR modelling.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages