J 2021

DeepAlign, a 3D Alignment Method based on Regionalized Deep Learning for Cryo-EM

JIMÉNEZ-MORENO, Amaya; David STŘELÁK; Jiří FILIPOVIČ; José María CARAZO; Carlos Óscar S. SORZANO et. al.

Basic information

Original name

DeepAlign, a 3D Alignment Method based on Regionalized Deep Learning for Cryo-EM

Authors

JIMÉNEZ-MORENO, Amaya (724 Spain); David STŘELÁK (203 Czech Republic, belonging to the institution); Jiří FILIPOVIČ (203 Czech Republic, guarantor, belonging to the institution); José María CARAZO and Carlos Óscar S. SORZANO

Edition

Journal of Structural Biology, San Diego,USA, Academic Press, 2021, 1047-8477

Other information

Language

English

Type of outcome

Article in a journal

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

is not subject to a state or trade secret

References:

Impact factor

Impact factor: 3.234

RIV identification code

RIV/00216224:14610/21:00121351

Organization unit

Institute of Computer Science

UT WoS

000756475200010

EID Scopus

2-s2.0-85102652992

Keywords in English

3D alignment; 3D reconstruction; Cryo-EM; Deep learning; Machine learning

Tags

Tags

International impact, Reviewed
Changed: 12/4/2022 16:50, Mgr. Alena Mokrá

Abstract

In the original language

Cryo Electron Microscopy (Cryo-EM) is currently one of the main tools to reveal the structural information of biological specimens at high resolution. Despite the great development of the techniques involved to solve the biological structures with Cryo-EM in the last years, the reconstructed 3D maps can present lower resolution due to errors committed while processing the information acquired by the microscope. One of the main problems comes from the 3D alignment step, which is an error-prone part of the reconstruction workflow due to the very low signal-to-noise ratio (SNR) common in Cryo-EM imaging. In fact, as we will show in this work, it is not unusual to find a disagreement in the alignment parameters in approximately 20–40% of the processed images, when outputs of different alignment algorithms are compared. In this work, we present a novel method to align sets of single particle images in the 3D space, called DeepAlign. Our proposal is based on deep learning networks that have been successfully used in plenty of problems in image classification. Specifically, we propose to design several deep neural networks on a regionalized basis to classify the particle images in sub-regions and, then, make a refinement of the 3D alignment parameters only inside that sub-region. We show that this method results in accurately aligned images, improving the Fourier shell correlation (FSC) resolution obtained with other state-of-the-art methods while decreasing computational time.

Links

MUNI/A/1411/2019, interní kód MU
Name: Aplikovaný výzkum: softwarové architektury kritických infrastruktur, bezpečnost počítačových systémů, zpracování přirozeného jazyka a jazykové inženýrství, vizualizaci velkých dat a rozšířená realita.
Investor: Masaryk University, Category A
MUNI/A/1549/2020, interní kód MU
Name: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity 21 (Acronym: SKOMU)
Investor: Masaryk University