{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T15:06:40Z","timestamp":1776870400267,"version":"3.51.2"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1008227","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000}}],"reference-count":24,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T00:00:00Z","timestamp":1605052800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P41GM103712 and R01GM134020"],"award-info":[{"award-number":["P41GM103712 and R01GM134020"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI-1949629 and IIS-2007595"],"award-info":[{"award-number":["DBI-1949629 and IIS-2007595"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Carnegie Mellon University (US), Center for Machine Learning and Health"},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004052","name":"King Abdullah University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mark Foundation","award":["19-044-ASP"],"award-info":[{"award-number":["19-044-ASP"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Cryo-electron tomography (cryo-ET) provides 3D visualization of subcellular components in the near-native state and at sub-molecular resolutions in single cells, demonstrating an increasingly important role in structural biology <jats:italic>in situ<\/jats:italic>. However, systematic recognition and recovery of macromolecular structures in cryo-ET data remain challenging as a result of low signal-to-noise ratio (SNR), small sizes of macromolecules, and high complexity of the cellular environment. Subtomogram structural classification is an essential step for such task. Although acquisition of large amounts of subtomograms is no longer an obstacle due to advances in automation of data collection, obtaining the same number of structural labels is both computation and labor intensive. On the other hand, existing deep learning based supervised classification approaches are highly demanding on labeled data and have limited ability to learn about new structures rapidly from data containing very few labels of such new structures. In this work, we propose a novel approach for subtomogram classification based on few-shot learning. With our approach, classification of unseen structures in the training data can be conducted given few labeled samples in test data through instance embedding. Experiments were performed on both simulated and real datasets. Our experimental results show that we can make inference on new structures given only five labeled samples for each class with a competitive accuracy (&gt; 0.86 on the simulated dataset with SNR = 0.1), or even one sample with an accuracy of 0.7644. The results on real datasets are also promising with accuracy &gt; 0.9 on both conditions and even up to 1 on one of the real datasets. Our approach achieves significant improvement compared with the baseline method and has strong capabilities of generalizing to other cellular components.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1008227","type":"journal-article","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T18:46:05Z","timestamp":1605120365000},"page":"e1008227","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Few-shot learning for classification of novel macromolecular structures in cryo-electron tomograms"],"prefix":"10.1371","volume":"16","author":[{"given":"Ran","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3302-4100","authenticated-orcid":true,"given":"Liangyong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2906-0897","authenticated-orcid":true,"given":"Bo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8589-4474","authenticated-orcid":true,"given":"Xiangrui","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8546-3589","authenticated-orcid":true,"given":"Xiaoyan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7108-3574","authenticated-orcid":true,"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0881-5891","authenticated-orcid":true,"given":"Min","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2020,11,11]]},"reference":[{"issue":"3","key":"pcbi.1008227.ref001","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1242\/jcs.171967","article-title":"Cellular structural biology as revealed by cryo-electron tomography","volume":"129","author":"RN Irobalieva","year":"2016","journal-title":"Journal of Cell Science"},{"issue":"2","key":"pcbi.1008227.ref002","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":"S Asano","year":"2016","journal-title":"Journal of Molecular Biology"},{"issue":"4","key":"pcbi.1008227.ref003","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1083\/jcb.201005007","article-title":"Structure of hibernating ribosomes studied by cryoelectron tomography in vitro and in situ","volume":"190","author":"JO Ortiz","year":"2010","journal-title":"Journal of Cell Biology"},{"issue":"1","key":"pcbi.1008227.ref004","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.jsb.2011.08.012","article-title":"Automated segmentation of electron tomograms for a quantitative description of actin filament networks","volume":"177","author":"A Rigort","year":"2012","journal-title":"Journal of structural biology"},{"issue":"2","key":"pcbi.1008227.ref005","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.jsb.2009.01.006","article-title":"Induced membrane domains as visualized by electron tomography and template matching","volume":"166","author":"MN Lebbink","year":"2009","journal-title":"Journal of structural biology"},{"issue":"1","key":"pcbi.1008227.ref006","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.ceb.2011.11.002","article-title":"Putting structure into context: fitting of atomic models into electron microscopic and electron tomographic reconstructions","volume":"24","author":"N Volkmann","year":"2012","journal-title":"Current opinion in cell biology"},{"issue":"12","key":"pcbi.1008227.ref007","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":"SH Scheres","year":"2009","journal-title":"Structure"},{"key":"pcbi.1008227.ref008","doi-asserted-by":"crossref","unstructured":"Xu M, Zhang S, Alber F. 3d rotation invariant features for the characterization of molecular density maps. In: 2009 IEEE International Conference on Bioinformatics and Biomedicine. IEEE; 2009. p. 74\u201378.","DOI":"10.1109\/BIBM.2009.32"},{"issue":"2","key":"pcbi.1008227.ref009","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.jsb.2011.12.003","article-title":"PyTom: a python-based toolbox for localization of macromolecules in cryo-electron tomograms and subtomogram analysis","volume":"178","author":"T Hrabe","year":"2012","journal-title":"Journal of structural biology"},{"issue":"2","key":"pcbi.1008227.ref010","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":"M Xu","year":"2012","journal-title":"Journal of structural biology"},{"issue":"4","key":"pcbi.1008227.ref011","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/j.str.2019.01.005","article-title":"De Novo Structural Pattern Mining in Cellular Electron Cryotomograms","volume":"27","author":"M Xu","year":"2019","journal-title":"Structure"},{"key":"pcbi.1008227.ref012","unstructured":"Gubins I, van der Shot G, Veltkamp RC, Foerster F, Du X, Zeng X, et al. SHREC\u201919 Track: Classification in Cryo-Electron Tomograms. 12th EG Workshop 3D Object Retrieval 2019. 2019;."},{"key":"pcbi.1008227.ref013","article-title":"Convolutional Neural Networks for Automated Annotation of Cellular Cryo-Electron Tomograms","author":"M Chen","year":"2017","journal-title":"Nature Methods"},{"issue":"S3","key":"pcbi.1008227.ref014","article-title":"Automatic localization and identification of mitochondria in cellular electron cryo-tomography using faster-RCNN","volume":"20","author":"R Li","year":"2019","journal-title":"Bmc Bioinformatics"},{"issue":"14","key":"pcbi.1008227.ref015","doi-asserted-by":"crossref","first-page":"i13","DOI":"10.1093\/bioinformatics\/btx230","article-title":"Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms","volume":"33","author":"M Xu","year":"2017","journal-title":"Bioinformatics"},{"issue":"8","key":"pcbi.1008227.ref016","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1007\/s00138-018-0949-4","article-title":"Improved deep learning-based macromolecules structure classification from electron cryo-tomograms","volume":"29","author":"C Che","year":"2018","journal-title":"Machine Vision and Applications"},{"issue":"4","key":"pcbi.1008227.ref017","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1016\/j.cell.2017.12.030","article-title":"In situ structure of neuronal C9orf72 poly-GA aggregates reveals proteasome recruitment","volume":"172","author":"Q Guo","year":"2018","journal-title":"Cell"},{"issue":"39","key":"pcbi.1008227.ref018","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":"H Bong-Gyoon","year":"2009","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"pcbi.1008227.ref019","first-page":"3630","volume-title":"Advances in neural information processing systems","author":"O Vinyals","year":"2016"},{"key":"pcbi.1008227.ref020","unstructured":"Snell J, Swersky K, Zemel R. Prototypical Networks for Few-shot Learning. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, et al., editors. Advances in Neural Information Processing Systems 30. Curran Associates, Inc.; 2017. p. 4077\u20134087. http:\/\/papers.nips.cc\/paper\/6996-prototypical-networks-for-few-shot-learning.pdf."},{"key":"pcbi.1008227.ref021","unstructured":"Ye HJ, Hu H, Zhan DC, Sha F. Learning Embedding Adaptation for Few-Shot Learning. arXiv preprint arXiv:181203664. 2018;."},{"issue":"1","key":"pcbi.1008227.ref022","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"HM Berman","year":"2000","journal-title":"Nucleic acids research"},{"key":"pcbi.1008227.ref023","doi-asserted-by":"crossref","first-page":"e34257","DOI":"10.7554\/eLife.34257","article-title":"Routine single particle CryoEM sample and grid characterization by tomography","volume":"7","author":"AJ Noble","year":"2018","journal-title":"Elife"},{"key":"pcbi.1008227.ref024","article-title":"Adam: A Method for Stochastic Optimization","author":"D Kingma","year":"2014","journal-title":"Computer Science"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1008227","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T20:09:35Z","timestamp":1606162175000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008227"}},"subtitle":[],"editor":[{"given":"Turkan","family":"Haliloglu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,11,11]]},"references-count":24,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2020,11,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1008227","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1008227","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,11]]}}}