Timezone: »
Proteins are the "building blocks of life", the most abundant organic molecules, and the central focus of most areas of biomedicine. Protein structure is strongly related to protein function, thus 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 acid constituting the protein. We use a convolutional network to calculate protein contact maps from inferred statistical coupling 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 large margin. It also allows for a great flexibility with regard to the input data, which makes it useful for studying a wide range of problems.
Author Information
Vladimir Golkov (Technical University of Munich)
Marcin Skwark (Vanderbilt University)
Dr Marcin J. Skwark is the Bioinformatics Lead at InstaDeep Ltd. Before joining InstaDeep in the beginning of 2020, he conducted academic research in computational structural biology at universities in Stockholm (Stockholm University), Helsinki (Aalto), Beijing (Tsinghua), Nashville (Vanderbilt), and Cambridge, UK (University of Cambridge). He researches on application of machine learning to modelling complex biological systems, structural bioinformatics (esp. protein design), as well as computational methods to enable groundbreaking discoveries in life sciences.
Antonij Golkov (University of Augsburg)
Alexey Dosovitskiy (University of Freiburg)
Thomas Brox (University of Freiburg)
Jens Meiler (Vanderbilt University)
Daniel Cremers (Technical University of Munich)
More from the Same Authors
-
2021 : STEP: Segmenting and Tracking Every Pixel »
Mark Weber · Jun Xie · Maxwell Collins · Yukun Zhu · Paul Voigtlaender · Hartwig Adam · Bradley Green · Andreas Geiger · Bastian Leibe · Daniel Cremers · Aljosa Osep · Laura Leal-TaixĂ© · Liang-Chieh Chen -
2021 Poster: Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation »
Florian Bernard · Daniel Cremers · Johan Thunberg -
2020 : Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning »
Marcin Skwark -
2020 Poster: COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning »
Simon Ging · Mohammadreza Zolfaghari · Hamed Pirsiavash · Thomas Brox -
2020 Poster: Deep Shells: Unsupervised Shape Correspondence with Optimal Transport »
Marvin Eisenberger · Aysim Toker · Laura Leal-TaixĂ© · Daniel Cremers -
2019 Poster: DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision »
Tam Nguyen · Maximilian Dax · Chaithanya Kumar Mummadi · Nhung Ngo · Thi Hoai Phuong Nguyen · Zhongyu Lou · Thomas Brox -
2016 : Learning 3D representations, disparity estimation, and structure from motion »
Thomas Brox -
2016 Oral: Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images »
Vladimir Golkov · Marcin Skwark · Antonij Golkov · Alexey Dosovitskiy · Thomas Brox · Jens Meiler · Daniel Cremers -
2016 Poster: Generating Images with Perceptual Similarity Metrics based on Deep Networks »
Alexey Dosovitskiy · Thomas Brox -
2016 Poster: Synthesizing the preferred inputs for neurons in neural networks via deep generator networks »
Anh Nguyen · Alexey Dosovitskiy · Jason Yosinski · Thomas Brox · Jeff Clune -
2014 Poster: Discriminative Unsupervised Feature Learning with Convolutional Neural Networks »
Alexey Dosovitskiy · Jost Tobias Springenberg · Martin Riedmiller · Thomas Brox