Purpose of this project is to provide the reader with a general view of the HP model for protein folding. Firstly, the report will focus on an overview of proteins and, in particular, why it's important to study how they fold. Next, the HP model will be presented in its mathematical form, introducing the two main approaches to this problem: the PERM algorithm and the Reinforcement Learning technique. Then, applications of the PERM algorithm to some real world sequence of amino acids will prove to be capable of obtaining outcomes compatible with the well known benchmarks. The comparison of these results to the ones produced by Deep Reinforced Learning will display the computational efficiency and precision of the latter algorithms. Lastly, a brief discussion of the results is given, together with a global resume on the whole topic.
All the code has been taken from an article (see bibliography). In particular, one can get it on this repository and on this site.
@misc{HP_model,
author = {Berselli, Gregorio and Faglioni, Isacco},
title = {HP model for protein folding: an overview and some applications.},
year = {2023},
url = {https://github.com/Grufoony/HP_model},
publisher = {GitHub},
howpublished = {\url{https://github.com/Grufoony/HP_model}}
}