ALLO
----
ALLO is a tool for dicriminating and prioritizing allosteric pockets. The tool
comprises two methods: naive bayes (NB) and artificial neural networks (ANN).
The former is used to classify a pocket as allosteric or orthosteric and the
later is used to rank allosteric pockets from a set of pockets. The main
program along with some helper scripts can be found in the directory src. Whereas
data can be found in the directory data.



PREQUISITES
-----------
Python libraries: Numpy, scipy
Output file from the program DoGSiteScorer.

nb.py
-------
An implementation of a naive bayes model.


predict_nb.py
-------
labels input as allosteric (A) or orthostreic (O)
Uses NB model (nb.py)
Uses ao.tsv
Usage: python predict_nb.py input_file.txt


example:

In your terminal, navigate to the directory src and execute the following
command:
 
python predict_nb.py test_input/A_ASD0023_2_1N5M_1_desc.txt 

the output file is written in the same directory as the input file.


nn.py
-------
An implementation of a neural network model.


rank_nn.py
-------
ranks a set of pockets based on their allostery
Uses ANN  model (nn.py)
Uses aplc.tsv
Usage: python rank_nn.py input_file.txt

example: 

In your terminal, navigate to the directory src and execute the following
command:

python rank_nn.py test_input/AS091022202_3PJG_complex.txt 

the output file is written in the same directory as the input file.