Black-box optimization methods play an important role in many fields of computational simulation. In particular, such methods are often used in the design and modelling of biological systems, including proteins and their complexes with various ligands. This work is mainly focused on the protein-protein docking that plays a key role in modern drug-design workflows. We develop a black-box approach for such docking problems using a novel technique based on the tensor-train decomposition of high-dimensional interaction functions. Our method shows an advantage in terms of the discovered global minima and has a high potential for further implementation on a wide range of devices, including graphical processing units and quantum processing units.
@article{arxiv.2302.03410,
title = {Protein-protein docking using a tensor train black-box optimization method},
author = {Dmitry Morozov and Artem Melnikov and Vishal Shete and Michael Perelshtein},
journal= {arXiv preprint arXiv:2302.03410},
year = {2023}
}