×

Recommended by

Indexed by

Local kernel regression and neural network approaches to the conformational landscapes of oligopeptides

Raimon Fabregat1, Alberto Fabrizio1, Edgar Engel2, Benjamin Meyer1, Veronika Juraskova1, Michele Ceriotti2, Clemence Corminboeuf1*

1 Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering, École Polytechnique Fédérale de Lausanne, CH-1015 Lausanne, Switzerland

2 Laboratory of Computational Science and Modeling, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland

* Corresponding authors emails: clemence.corminboeuf@epfl.ch
DOI10.24435/materialscloud:kp-82 [version v1]

Publication date: Aug 10, 2021

How to cite this record

Raimon Fabregat, Alberto Fabrizio, Edgar Engel, Benjamin Meyer, Veronika Juraskova, Michele Ceriotti, Clemence Corminboeuf, Local kernel regression and neural network approaches to the conformational landscapes of oligopeptides, Materials Cloud Archive 2021.130 (2021), doi: 10.24435/materialscloud:kp-82.

Description

The application of machine learning to theoretical chemistry has made it possible to combine the accuracy of quantum chemical energetics with the thorough sampling of finite-temperature fluctuations. To reach this goal, a diverse set of methods has been proposed, ranging from simple linear models to kernel regression and highly nonlinear neural networks. Here we apply two widely different approaches to the same, challenging problem - the sampling of the conformational landscape of polypeptides at finite temperature. We develop a Local Kernel Regression (LKR) coupled with a supervised sparsity method and compare it with a more established approach based on Behler-Parrinello type Neural Networks. In the context of the LKR, we discuss how the supervised selection of the reference pool of environments is crucial to achieve accurate potential energy surfaces at a competitive computational cost and leverage the locality of the model to infer which chemical environments are poorly described by the DFTB baseline. We then discuss the relative merits of the two frameworks and perform Hamiltonian-reservoir replica-exchange Monte Carlo sampling and metadynamics simulations, respectively, to demonstrate that both frameworks can achieve converged and transferable sampling of the conformational landscape of complex and flexible biomolecules with comparable accuracy and computational cost.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.

Files

File name Size Description
peptide_data.tar.gz
MD5md5:fd02dc313c1ed58160338bab2d0a3063
126.1 MiB Compressed tar ball containing the molecular structures and energies necessary to reproduce the results in the manuscript
README
MD5md5:17e60e6a43fffb1eb096c90f25d31f2f
1.3 KiB README

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Journal reference
R. Fabregat, A. Fabrizio, E. Engel, B. Meyer, V. Juraskova, M. Ceriotti, C. Corminboeuf, J. Chem. Theory Comput., submitted, (2021)

Keywords

Local Kernel Regression Behler-Parrinello Neural Network Oligopeptides Enhanced Sampling Hamiltonian Replica Exchange Machine Learning Supervised Sparsity EPFL MARVEL/DD1 ERC SNSF

Version history:

2021.130 (version v1) [This version] Aug 10, 2021 DOI10.24435/materialscloud:kp-82