EncoderMap(II): Visualizing Important Molecular Motions with Improved Generation of Protein Conformations
- 24 October 2019
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 59 (11) , 4550-4560
Abstract
Dimensionality reduction can be used to project high-dimensional molecular data into a simplified, low-dimensional map. One feature of our recently introduced dimensionality reduction technique EncoderMap, which relies on the combination of an autoencoder with multidimensional scaling, is its ability to do the reverse. It is able to generate conformations for any selected points in the low-dimensional map. This transfers the simplified, low-dimensional map back into the high-dimensional conformational space. Although the output is again high-dimensional, certain aspects of the simplification are preserved. The generated conformations only mirror the most dominant conformational differences that determine the positions of conformational states in the low-dimensional map. This allows to depict such differences and - in consequence - visualize molecular motions and gives a unique perspective on high-dimensional conformational data. In our previous work protein conformations described in backbone dihedral angle space were used as input for EncoderMap, and conformations were also generated in this space. For large proteins, however, the generation of conformations is inaccurate with this approach due to the local character of backbone dihedral angles. Here, we present an improved variant of EncoderMap which is able to generate large protein conformations that are accurate in short-range and long-range order. This is achieved by differentiable reconstruction of Cartesian coordinates from the generated dihedrals, which allows to add a contribution to the cost function that monitors the accuracy of all pairwise distances between the C α -atoms of the generated conformations. The improved capabilities to generate conformations of large, even multidomain, proteins are demonstrated for two examples: diubiquitin and a part of the Ssa1 Hsp70 yeast chaperone. We show that the improved variant of EncoderMap can nicely visualize motions of protein domains relative to each other but is also able to highlight important conformational changes within the individual domains.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (INST 37/935-1 FUGG, INST35/1134-1 FUGG, SFB969)
This publication has 38 references indexed in Scilit:
- Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networksBMC Bioinformatics, 2014
- Molecular chaperones in protein folding and proteostasisNature, 2011
- Simplifying the representation of complex free-energy landscapes using sketch-mapProceedings of the National Academy of Sciences, 2011
- Improving protein fold recognition and template-based modeling by employing probabilistic-based matching between predicted one-dimensional structural properties of query and corresponding native properties of templatesBioinformatics, 2011
- A generative, probabilistic model of local protein structureProceedings of the National Academy of Sciences, 2008
- A comprehensive assessment of sequence-based and template-based methods for protein contact predictionBioinformatics, 2008
- GROMACS 4: Algorithms for Highly Efficient, Load-Balanced, and Scalable Molecular SimulationJournal of Chemical Theory and Computation, 2008
- Energy landscape of a small peptide revealed by dihedral angle principal component analysisProteins: Structure, Function, and Bioinformatics, 2004
- Global Fold Determination from a Small Number of Distance RestraintsJournal of Molecular Biology, 1995
- Comparative Protein Modelling by Satisfaction of Spatial RestraintsJournal of Molecular Biology, 1993