Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images

Golkov V, Skwark MJ, Golkov A, Dosovitskiy A, Brox T, Meiler J, Cremers D (2016)

Publication Type: Conference contribution

Publication year: 2016

Publisher: Neural information processing systems foundation

Pages Range: 4222-4230

Conference Proceedings Title: Advances in Neural Information Processing Systems

Event location: Barcelona, ESP

Abstract

Proteins are responsible for most of the functions in life, and thus are the central focus of many areas of biomedicine. Protein structure is strongly related to protein function, but is difficult to elucidate experimentally, therefore computational structure prediction is a crucial task on the way to solve many biological questions. A contact map is a compact representation of the three-dimensional structure of a protein via the pairwise contacts between the amino acids constituting the protein. We use a convolutional network to calculate protein contact maps from detailed evolutionary coupling statistics between positions in the protein sequence. The input to the network has an image-like structure amenable to convolutions, but every "pixel" instead of color channels contains a bipartite undirected edge-weighted graph. We propose several methods for treating such "graph-valued images" in a convolutional network. The proposed method outperforms state-of-the-art methods by a considerable margin.

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) Vanderbilt University US United States (USA) (US) Universität Augsburg DE Germany (DE) Albert-Ludwigs-Universität Freiburg DE Germany (DE)

How to cite

APA:

Golkov, V., Skwark, M.J., Golkov, A., Dosovitskiy, A., Brox, T., Meiler, J., & Cremers, D. (2016). Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images. In Roman Garnett, Daniel D. Lee, Ulrike von Luxburg, Isabelle Guyon, Masashi Sugiyama (Eds.), Advances in Neural Information Processing Systems (pp. 4222-4230). Barcelona, ESP: Neural information processing systems foundation.

MLA:

Golkov, Vladimir, et al. "Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images." Proceedings of the 30th Annual Conference on Neural Information Processing Systems, NIPS 2016, Barcelona, ESP Ed. Roman Garnett, Daniel D. Lee, Ulrike von Luxburg, Isabelle Guyon, Masashi Sugiyama, Neural information processing systems foundation, 2016. 4222-4230.

BibTeX: Download