{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T20:56:58Z","timestamp":1762376218969,"version":"3.37.3"},"reference-count":60,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2017,7,12]],"date-time":"2017-07-12T00:00:00Z","timestamp":1499817600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004440","name":"Wellcome Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["107578\/Z\/15\/Z"],"award-info":[{"award-number":["107578\/Z\/15\/Z"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI-1149494"],"award-info":[{"award-number":["DBI-1149494"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01GM114311","P30DA035778"],"award-info":[{"award-number":["R01GM114311","P30DA035778"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Cellular Electron CryoTomography (CECT) enables 3D visualization of cellular organization at near-native state and in sub-molecular resolution, making it a powerful tool for analyzing structures of macromolecular complexes and their spatial organizations inside single cells. However, high degree of structural complexity together with practical imaging limitations makes the systematic de novo discovery of structures within cells challenging. It would likely require averaging and classifying millions of subtomograms potentially containing hundreds of highly heterogeneous structural classes. Although it is no longer difficult to acquire CECT data containing such amount of subtomograms due to advances in data acquisition automation, existing computational approaches have very limited scalability or discrimination ability, making them incapable of processing such amount of data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To complement existing approaches, in this article we propose a new approach for subdividing subtomograms into smaller but relatively homogeneous subsets. The structures in these subsets can then be separately recovered using existing computation intensive methods. Our approach is based on supervised structural feature extraction using deep learning, in combination with unsupervised clustering and reference-free classification. Our experiments show that, compared with existing unsupervised rotation invariant feature and pose-normalization based approaches, our new approach achieves significant improvements in both discrimination ability and scalability. More importantly, our new approach is able to discover new structural classes and recover structures that do not exist in training data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>Source code freely available at http:\/\/www.cs.cmu.edu\/\u223cmxu1\/software.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx230","type":"journal-article","created":{"date-parts":[[2017,4,13]],"date-time":"2017-04-13T19:11:48Z","timestamp":1492110708000},"page":"i13-i22","source":"Crossref","is-referenced-by-count":34,"title":["Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms"],"prefix":"10.1093","volume":"33","author":[{"given":"Min","family":"Xu","sequence":"first","affiliation":[{"name":"Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Xiaoqi","family":"Chai","sequence":"additional","affiliation":[{"name":"Biomedical Engineering Department, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Hariank","family":"Muthakana","sequence":"additional","affiliation":[{"name":"Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Ge","family":"Yang","sequence":"additional","affiliation":[{"name":"Biomedical Engineering Department, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Tzviya","family":"Zeev-Ben-Mordehai","sequence":"additional","affiliation":[{"name":"Division of Structural Biology, Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, UK"}]},{"given":"Eric P","family":"Xing","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, USA"}]}],"member":"286","published-online":{"date-parts":[[2017,7,12]]},"reference":[{"year":"2016","author":"Abadi","key":"2023051506463491300_btx230-B1"},{"year":"2001","author":"Aggarwal","key":"2023051506463491300_btx230-B2"},{"key":"2023051506463491300_btx230-B3","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1126\/science.1261197","article-title":"A molecular census of 26s proteasomes in intact neurons","volume":"347","author":"Asano","year":"2015","journal-title":"Science"},{"key":"2023051506463491300_btx230-B4","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.jmb.2015.09.030","article-title":"In situ cryo-electron tomography: a post-reductionist approach to structural biology","volume":"428","author":"Asano","year":"2016","journal-title":"J. Mol. Biol"},{"key":"2023051506463491300_btx230-B5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.jsb.2008.02.008","article-title":"Classification and 3D averaging with missing wedge correction in biological electron tomography","volume":"162","author":"Bartesaghi","year":"2008","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B6","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1038\/nmeth.1390","article-title":"Visual proteomics of the human pathogen Leptospira interrogans","volume":"6","author":"Beck","year":"2009","journal-title":"Nat. Methods"},{"key":"2023051506463491300_btx230-B7","doi-asserted-by":"crossref","first-page":"235.","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023051506463491300_btx230-B8","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1016\/S0091-679X(06)79025-2","article-title":"Localization of protein complexes by pattern recognition","volume":"79","author":"Best","year":"2007","journal-title":"Methods Cell Biol"},{"key":"2023051506463491300_btx230-B9","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1016\/j.str.2015.06.026","article-title":"Advances in single-particle electron cryomicroscopy structure determination applied to sub-tomogram averaging","volume":"23","author":"Bharat","year":"2015","journal-title":"Structure"},{"key":"2023051506463491300_btx230-B10","doi-asserted-by":"crossref","first-page":"14245","DOI":"10.1073\/pnas.230282097","article-title":"Toward detecting and identifying macromolecules in a cellular context: template matching applied to electron tomograms","volume":"97","author":"B\u00f6hm","year":"2000","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051506463491300_btx230-B11","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.sbi.2013.02.003","article-title":"Structural biology in situthe potential of subtomogram averaging","volume":"23","author":"Briggs","year":"2013","journal-title":"Curr. Opin. Struct. Biol"},{"key":"2023051506463491300_btx230-B12","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1038\/nmeth.2961","article-title":"Correlated cryogenic photoactivated localization microscopy and cryo-electron tomography","volume":"11","author":"Chang","year":"2014","journal-title":"Nat. Methods"},{"year":"2012","author":"Chen","key":"2023051506463491300_btx230-B13"},{"key":"2023051506463491300_btx230-B14","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1016\/j.str.2014.08.007","article-title":"Autofocused 3d classification of cryoelectron subtomograms","volume":"22","author":"Chen","year":"2014","journal-title":"Structure"},{"article-title":"GitHub repository","year":"2015","author":"Chollet","key":"2023051506463491300_btx230-B15"},{"key":"2023051506463491300_btx230-B16","doi-asserted-by":"crossref","first-page":"4729.","DOI":"10.1073\/pnas.0409178102","article-title":"Retrovirus envelope protein complex structure in situ studied by cryo-electron tomography","volume":"102","author":"F\u00f6rster","year":"2005","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051506463491300_btx230-B17","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.jsb.2007.07.006","article-title":"Classification of cryo-electron sub-tomograms using constrained correlation","volume":"161","author":"F\u00f6rster","year":"2008","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B18","doi-asserted-by":"crossref","first-page":"14153","DOI":"10.1073\/pnas.172520299","article-title":"Identification of macromolecular complexes in cryoelectron tomograms of phantom cells","volume":"99","author":"Frangakis","year":"2002","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051506463491300_btx230-B19","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780195182187.001.0001","volume-title":"Three-Dimensional Electron Microscopy of Macromolecular Assemblies","author":"Frank","year":"2006"},{"key":"2023051506463491300_btx230-B20","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1038\/256376a0","article-title":"Signal-to-noise ratio of electron micrographs obtained by cross correlation","volume":"256","author":"Frank","year":"1975","journal-title":"Nature"},{"key":"2023051506463491300_btx230-B21","doi-asserted-by":"crossref","DOI":"10.1016\/j.str.2017.04.016","article-title":"Tomominer and tomominer cloud: A software platform for large-scale subtomogram structural analysis","author":"Frazier","year":"2017","journal-title":"Structure"},{"key":"2023051506463491300_btx230-B22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.jsb.2015.04.016","article-title":"Single particle tomography in eman2","volume":"190","author":"Galaz-Montoya","year":"2015","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B23","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1017\/S0033583511000102","article-title":"Electron tomography of cells","volume":"45","author":"Gan","year":"2012","journal-title":"Quart. Rev. Biophys"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"2023051506463491300_btx230-B24"},{"key":"2023051506463491300_btx230-B25","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/S0301-4622(02)00307-1","article-title":"Prospects of electron cryotomography to visualize macromolecular complexes inside cellular compartments: implications of crowding","volume":"100","author":"Gr\u00fcnewald","year":"2002","journal-title":"Biophys. Chem"},{"key":"2023051506463491300_btx230-B26","doi-asserted-by":"crossref","first-page":"16580","DOI":"10.1073\/pnas.0813068106","article-title":"Survey of large protein complexes in d. vulgaris reveals great structural diversity","volume":"106","author":"Han","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"year":"2016","author":"He","key":"2023051506463491300_btx230-B27"},{"key":"2023051506463491300_btx230-B28","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/j.jsb.2007.10.007","article-title":"Applications of direct detection device in transmission electron microscopy","volume":"161","author":"Jin","year":"2008","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B29","doi-asserted-by":"crossref","DOI":"10.1038\/srep09583","article-title":"Correlative in-resin super-resolution and electron microscopy using standard fluorescent proteins","volume":"5","author":"Johnson","year":"2015","journal-title":"Sci. Rep"},{"key":"2023051506463491300_btx230-B31","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky","year":"2012"},{"key":"2023051506463491300_btx230-B32","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.jsb.2015.08.016","article-title":"M-free: Mask-independent scoring of the reference bias","volume":"192","author":"Kunz","year":"2015","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B33","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"2023051506463491300_btx230-B34","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1016\/j.str.2010.05.008","article-title":"Definition and estimation of resolution in single-particle reconstructions","volume":"18","author":"Liao","year":"2010","journal-title":"Structure"},{"key":"2023051506463491300_btx230-B35","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1083\/jcb.201304193","article-title":"Cryo-electron tomography: The challenge of doing structural biology in situ","volume":"202","author":"Lu\u010di\u0107","year":"2013","journal-title":"J. Cell Biol"},{"key":"2023051506463491300_btx230-B36","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res"},{"key":"2023051506463491300_btx230-B37","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.jsb.2005.07.007","article-title":"Automated electron microscope tomography using robust prediction of specimen movements","volume":"152","author":"Mastronarde","year":"2005","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B38","doi-asserted-by":"crossref","first-page":"1126","DOI":"10.1016\/j.ultramic.2009.04.002","article-title":"Detective quantum efficiency of electron area detectors in electron microscopy","volume":"109","author":"McMullan","year":"2009","journal-title":"Ultramicroscopy"},{"key":"2023051506463491300_btx230-B39","first-page":"e53608","article-title":"Using tomoautoa protocol for high-throughput automated cryo-electron tomography","volume":"107","author":"Morado","year":"2016","journal-title":"J. Vis. Exp"},{"key":"2023051506463491300_btx230-B40","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1016\/j.str.2010.06.006","article-title":"Zernike phase contrast cryo-electron microscopy and tomography for structure determination at nanometer and subnanometer resolutions","volume":"18","author":"Murata","year":"2010","journal-title":"Structure"},{"key":"2023051506463491300_btx230-B41","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.jsb.2004.10.006","article-title":"TOM software toolbox: acquisition and analysis for electron tomography","volume":"149","author":"Nickell","year":"2005","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B42","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1038\/nrm1861","article-title":"A visual approach to proteomics","volume":"7","author":"Nickell","year":"2006","journal-title":"Nat. Rev. Mol. Cell Biol"},{"key":"2023051506463491300_btx230-B43","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"2023051506463491300_btx230-B44","doi-asserted-by":"crossref","first-page":"405.","DOI":"10.1186\/s12859-016-1283-3","article-title":"Simulating cryo electron tomograms of crowded cell cytoplasm for assessment of automated particle picking","volume":"17","author":"Pei","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2023051506463491300_btx230-B45","doi-asserted-by":"crossref","first-page":"4449","DOI":"10.1073\/pnas.1201333109","article-title":"Focused ion beam micromachining of eukaryotic cells for cryoelectron tomography","volume":"109","author":"Rigort","year":"2012","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051506463491300_btx230-B46","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis"},{"key":"2023051506463491300_btx230-B47","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.jsb.2003.09.013","article-title":"A fast reconstruction algorithm for electron microscope tomography","volume":"144","author":"Sandberg","year":"2003","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B48","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1016\/j.str.2009.10.009","article-title":"Averaging of electron subtomograms and random conical tilt reconstructions through likelihood optimization","volume":"17","author":"Scheres","year":"2009","journal-title":"Structure"},{"year":"2014","author":"Simonyan","key":"2023051506463491300_btx230-B49"},{"key":"2023051506463491300_btx230-B50","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"year":"2016","author":"Szegedy","key":"2023051506463491300_btx230-B51"},{"year":"2016","author":"Szegedy","key":"2023051506463491300_btx230-B52"},{"year":"2016","author":"Wieczorek","key":"2023051506463491300_btx230-B53"},{"key":"2023051506463491300_btx230-B54","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1006\/jsbi.1998.4080","article-title":"Situs: a package for docking crystal structures into low-resolution maps from electron microscopy","volume":"125","author":"Wriggers","year":"1999","journal-title":"J. Struct. Biol"},{"key":"2023051506463491300_btx230-B55","first-page":"521","volume-title":"Advances in Neural Information Processing Systems 15","author":"Xing","year":"2002"},{"year":"2009","author":"Xu","key":"2023051506463491300_btx230-B56"},{"key":"2023051506463491300_btx230-B57","doi-asserted-by":"crossref","first-page":"i69","DOI":"10.1093\/bioinformatics\/btr207","article-title":"Template-free detection of macromolecular complexes in cryo electron tomograms","volume":"27","author":"Xu","year":"2011","journal-title":"Bioinformatics"},{"key":"2023051506463491300_btx230-B58","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.jsb.2012.02.014","article-title":"High-throughput subtomogram alignment and classification by Fourier space constrained fast volumetric matching","volume":"178","author":"Xu","year":"2012","journal-title":"J. Struct. Biol"},{"year":"2015","author":"Xu","key":"2023051506463491300_btx230-B59"},{"key":"2023051506463491300_btx230-B60","doi-asserted-by":"crossref","first-page":"i274","DOI":"10.1093\/bioinformatics\/btt225","article-title":"Automated target segmentation and real space fast alignment methods for high-throughput classification and averaging of crowded cryo-electron subtomograms","volume":"29","author":"Xu","year":"2013","journal-title":"Bioinformatics"},{"key":"2023051506463491300_btx230-B61","doi-asserted-by":"crossref","first-page":"4176","DOI":"10.1073\/pnas.1523234113","article-title":"Two distinct trimeric conformations of natively membrane-anchored full-length herpes simplex virus 1 glycoprotein b","volume":"113","author":"Zeev-Ben-Mordehai","year":"2016","journal-title":"Proc. Natl. Acad. Sci"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/14\/i13\/50314944\/bioinformatics_33_14_i13.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/14\/i13\/50314944\/bioinformatics_33_14_i13.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T06:47:17Z","timestamp":1684133237000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/14\/i13\/3953944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,12]]},"references-count":60,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2017,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx230","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2017,7,15]]},"published":{"date-parts":[[2017,7,12]]}}}