PBKB: Peptide bioactivity kernel based

This package contains tools to learn peptide bioactivity predictor and find the peptides that maximize the output of the predictor

-------
How to install
-------

To ease the utilization, we have programmed a pure python implementation and very optimized version of this work in Cython that is faster than the pure python version.

To install this module (*recommended*), simply run the following command:
> pip install -e PBKB

-------
Usage
-------

The easiest way to use the  ....
#todo

-------
More information
-------

All files have a good amount of comments to explain how everything works.
Details of the methods implemented are available from:

Giguère, S., Marchand, M., Laviolette, F., Drouin, A., & Corbeil, J. (2012).
Learning a peptide-protein binding affinity predictor with kernel ridge regression.

Sébastien Giguère et al. “Machine learning assisted design of highly active
peptides for drug discovery”. In: PLoS Comput Biol 11.4 (2015), e1004074.

Sébastien Giguere et al. “Algorithms for the Hard Pre-Image Problem of String
Kernels and the General Problem of String Prediction”. In: Proceedings of
the 32nd International Conference on Machine Learning (ICML-15). 2015,
pp. 2021–2029

If you have concerns, questions, comments ... well anything,
contact the author at: tossouprudencio@gmail.com