Convolutional Neural Networks for Automated Annotation of Cellular Cryo-Electron Tomograms

Cellular electron cryotomography offers researchers the ability to observe macromolecules frozen in action in situ, but a primary challenge with this technique is identifying molecular components within the crowded cellular environment. We introduce a method that uses neural networks to dramatically reduce the time and human effort required for subcellular annotation and feature extraction. Subsequent subtomogram classification and averaging yield in situ structures of molecular components of interest. The method is available in the EMAN2.2 software package.

[1]  Yuxiang Chen,et al.  Fast and accurate reference-free alignment of subtomograms. , 2013, Journal of structural biology.

[2]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[3]  V. Lučić,et al.  Cryo-electron tomography: The challenge of doing structural biology in situ , 2013, The Journal of cell biology.

[4]  Shoh M. Asano,et al.  A molecular census of 26S proteasomes in intact neurons , 2015, Science.

[5]  F. Förster,et al.  Identification of macromolecular complexes in cryoelectron tomograms of phantom cells , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[7]  Daniel Baum,et al.  Automated segmentation of electron tomograms for a quantitative description of actin filament networks. , 2012, Journal of structural biology.

[8]  James E Bear,et al.  A cell-based assay for aggregation inhibitors as therapeutics of polyglutamine-repeat disease and validation in Drosophila , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Wah Chiu,et al.  Zernike phase-contrast electron cryotomography applied to marine cyanobacteria infected with cyanophages , 2014, Nature Protocols.

[10]  J. Frank,et al.  High-resolution cryo-electron microscopy structure of the Trypanosoma brucei ribosome , 2013, Nature.

[11]  Wen Jiang,et al.  EMAN2: an extensible image processing suite for electron microscopy. , 2007, Journal of structural biology.

[12]  Simon Scheuring,et al.  Chromatic Adaptation of Photosynthetic Membranes , 2005, Science.

[13]  Christopher Page,et al.  Accurate membrane tracing in three-dimensional reconstructions from electron cryotomography data. , 2015, Ultramicroscopy.

[14]  G. Cross,et al.  Trypanosoma brucei , 1998 .

[15]  J. Valpuesta,et al.  Faculty Opinions recommendation of Proteasomes. A molecular census of 26S proteasomes in intact neurons. , 2015 .

[16]  William J Rice,et al.  Structural model for tubulin recognition and deformation by kinesin-13 microtubule depolymerases. , 2013, Cell reports.

[17]  Niels Galjart,et al.  Cryo electron tomography of vitrified fibroblasts: microtubule plus ends in situ. , 2008, Journal of structural biology.

[18]  F. Förster,et al.  Organization of the mitochondrial translation machinery studied in situ by cryoelectron tomography , 2015, Nature Communications.

[19]  Grant J Jensen,et al.  The Caltech Tomography Database and Automatic Processing Pipeline. , 2015, Journal of structural biology.

[20]  Wah Chiu,et al.  Visualizing Virus Assembly Intermediates Inside Marine Cyanobacteria , 2013, Nature.

[21]  A S Frangakis,et al.  Toward detecting and identifying macromolecules in a cellular context: template matching applied to electron tomograms. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Sander Dieleman,et al.  Rotation-invariant convolutional neural networks for galaxy morphology prediction , 2015, ArXiv.

[23]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[24]  Corey W. Hecksel,et al.  Alignment algorithms and per-particle CTF correction for single particle cryo-electron tomography. , 2016, Journal of structural biology.

[25]  J. Dubochet,et al.  Luminal particles within cellular microtubules , 2006, The Journal of cell biology.

[26]  Matthias P Lutolf,et al.  Synthesis and characterization of well-defined hydrogel matrices and their application to intestinal stem cell and organoid culture , 2017, Nature Protocols.

[27]  Wah Chiu,et al.  Electron cryotomography reveals ultrastructure alterations in platelets from patients with ovarian cancer , 2015, Proceedings of the National Academy of Sciences.

[28]  R. Kaminsky,et al.  Cultivation of the life cycle stages of Trypanosoma brucei sspp. , 1988, Acta tropica.

[29]  O. Troyanskaya,et al.  Predicting effects of noncoding variants with deep learning–based sequence model , 2015, Nature Methods.

[30]  Yuxiang Chen,et al.  PyTom: a python-based toolbox for localization of macromolecules in cryo-electron tomograms and subtomogram analysis. , 2012, Journal of structural biology.

[31]  Edgar Garduño,et al.  Segmentation of electron tomographic data sets using fuzzy set theory principles. , 2008, Journal of structural biology.

[32]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[33]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[34]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[35]  Wei Dai,et al.  Quantifying Variability of Manual Annotation in Cryo-Electron Tomograms , 2016, Microscopy and Microanalysis.