Published January 26, 2021 | Version v3
Dataset Open

Sampling enhancement by metadynamics driven by machine learning and de novo protein modelling

  • 1. Department of Biochemistry and Microbiology, Universiy of Chemistry and Technology, Prague, Czech Republic

* Contact person

Description

Folding of villin miniprotein was studied by parallel tempering metadynamics driven by machine learning. To obtain a training set for machine learning, we generated a large series of structures of the protein by the de novo protein structure prediction package Rosetta. A neural network was trained to approximate the Rosetta score. Parallel tempering metadynamics driven by this approximated Rosetta score successfully predicted the native structure and the free energy surface of the studied system. These files make it possible to rerun all simulations. The directory METAD contains input files for metadynamics (no folding events observed). The directory PT-METAD contains input files for parallel tempering metadynamics. All simulations were done using Gromacs 2016.4, Anncolvar 0.8, Plumed 2.4 and OpenMPI 4.0.0.

Files

File preview

files_description.md

All files

Files (12.5 MiB)

Name Size
md5:18ebed6955c1809ebbe2a7962c153a7f
369 Bytes Preview Download
md5:2fb78e3d844c6b59a6bee5e86c4960cf
2.3 KiB Preview Download
md5:54d65f663b98755791d10b44c0a7ed94
12.5 MiB Preview Download

References

Journal reference (Manuscript to be submitted where the input data were used.)
K. Tomášková, D. Trapl, V. Spiwok (in preparation)