Awesome

bpbi

Binding Pose prediction as Best-arm Identification

Required Packages

python >= 2.7.x
numpy >= 1.11.x
pandas >= 1.11.x

Installation

Download or clone the github repository, e.g. git clone https://github.com/tsudalab/bpbi

Usage

Run test.py for searching the binding pose using best-arm identification algorithms.

References

K. Terayama, H. Iwata, M. Araki, Y. Okuno, K. Tsuda, "Machine Learning Accelerates MD-based Binding-Pose Prediction between Ligands and Proteins", Bioinformatics, 2017. (https://doi.org/10.1093/bioinformatics/btx638)

Bubeck, S.; Munos, R.; Stoltz, G. "Pure exploration in multi-armed bandits problems." ALT, pp 23–37, 2009.
Audibert, J.-Y.; Bubeck, S. "Best Arm Identification in Multi-Armed Bandits." COLT, 2010.
Gabillon, V.; Ghavamzadeh, M.; Lazaric, A. "Best arm identification: A unified approach to fixed budget and fixed confidence." NIPS, pp.3212–3220, 2012.