A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation.

Zeng, Xiangrui; Leung, Miguel Ricardo; Zeev-Ben-Mordehai, Tzviya; Xu, Min

Zeng, Xiangrui; Leung, Miguel Ricardo; Zeev-Ben-Mordehai, Tzviya; Xu, Min.

Afiliação

Zeng X; Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh 15213, USA.
Leung MR; Division of Structural Biology, Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford OX3 7BN, UK; Cryo-electron Microscopy, Bijvoet Center for Biomolecular Research, Utrecht University, Utrecht, Netherlands.
Zeev-Ben-Mordehai T; Division of Structural Biology, Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford OX3 7BN, UK; Cryo-electron Microscopy, Bijvoet Center for Biomolecular Research, Utrecht University, Utrecht, Netherlands.
Xu M; Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh 15213, USA. Electronic address: mxu1@cs.cmu.edu.

J Struct Biol ; 202(2): 150-160, 2018 05.

Article em En | MEDLINE | ID: mdl-29289599

Assuntos

Microscopia Crioeletrônica/métodos; Processamento de Imagem Assistida por Computador/métodos; Substâncias Macromoleculares/química; Software; Algoritmos

Palavras-chave

Cellular electron cryo-tomography; Convolutional autoencoder; Convolutional neural network; Deep learning; Image semantic segmentation; Machine learning; Macromolecular complex; Particle picking; Pose normalization; Structural pattern mining; Subtomogram classification; Unsupervised learning; Visual proteomics; Weakly supervised learning

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Processamento de Imagem Assistida por Computador / Software / Microscopia Crioeletrônica / Substâncias Macromoleculares Idioma: En Revista: J Struct Biol Assunto da revista: BIOLOGIA MOLECULAR Ano de publicação: 2018 Tipo de documento: Article País de afiliação: Estados Unidos

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google