Protein-protein docking using a tensor train black-box optimization method

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.

[1]  A. Sagingalieva,et al.  Hybrid Quantum Neural Network for Drug Response Prediction , 2022, Cancers.

[2]  M. Buchberger,et al.  Benchmarking simulated and physical quantum processing units using quantum and hybrid algorithms , 2022, ArXiv.

[3]  A. Perdomo-Ortiz,et al.  Decomposition of matrix product states into shallow quantum circuits , 2022, Quantum Science and Technology.

[4]  F. Neukart,et al.  Practical application-specific advantage through hybrid quantum computing , 2022, ArXiv.

[5]  David Von Dollen,et al.  Hyperparameter optimization of hybrid quantum neural networks for car classification , 2022, ArXiv.

[6]  A. Cichocki,et al.  TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning , 2022, NeurIPS.

[7]  V. Batista,et al.  Iterative Power Algorithm for Global Optimization with Quantics Tensor Trains. , 2021, Journal of chemical theory and computation.

[8]  E. Tyrtyshnikov,et al.  Global optimization based on TT-decomposition , 2020 .

[9]  Alexandre M. J. J. Bonvin,et al.  LightDock goes information-driven , 2019, bioRxiv.

[10]  K. Birgitta Whaley,et al.  Towards quantum machine learning with tensor networks , 2018, Quantum Science and Technology.

[11]  Daniel Jiménez-González,et al.  LightDock: a new multi-scale approach to protein–protein docking , 2018, Bioinform..

[12]  J. Tuszynski,et al.  Software for molecular docking: a review , 2017, Biophysical Reviews.

[13]  Ralf Blossey,et al.  Molecular docking as a popular tool in drug design, an in silico travel , 2016, Advances and applications in bioinformatics and chemistry : AABC.

[14]  Marc F. Lensink,et al.  Score_set: A CAPRI benchmark for scoring protein complexes , 2014, Proteins.

[15]  Ivan Oseledets,et al.  Tensor-Train Decomposition , 2011, SIAM J. Sci. Comput..

[16]  M. Mezei,et al.  Molecular docking: a powerful approach for structure-based drug discovery. , 2011, Current computer-aided drug design.

[17]  Xiaofan Li,et al.  Detection and refinement of encounter complexes for protein–protein docking: Taking account of macromolecular crowding , 2010, Proteins.

[18]  S. Goreinov,et al.  How to find a good submatrix , 2010 .

[19]  E. Tyrtyshnikov,et al.  TT-cross approximation for multidimensional arrays , 2010 .

[20]  Debasish Ghose,et al.  Glowworm swarm optimization for simultaneous capture of multiple local optima of multimodal functions , 2009, Swarm Intelligence.

[21]  Tammy M. K. Cheng,et al.  pyDock: Electrostatics and desolvation for effective scoring of rigid‐body protein–protein docking , 2007, Proteins.

[22]  Song Liu,et al.  Accurate and efficient loop selections by the DFIRE‐based all‐atom statistical potential , 2004, Protein science : a publication of the Protein Society.

[23]  D. Eisenberg,et al.  Protein function in the post-genomic era , 2000, Nature.

[24]  T. N. Bhat,et al.  The Protein Data Bank , 2000, Nucleic Acids Res..

[25]  M. J. D. Powell,et al.  An efficient method for finding the minimum of a function of several variables without calculating derivatives , 1964, Comput. J..