Machine learning for classifying narrow‐beam electron diffraction data

As an alternative approach to X‐ray crystallography and single‐particle cryo‐electron microscopy, single‐molecule electron diffraction has a better signal‐to‐noise ratio and the potential to increase the resolution of protein models. This technology requires collection of numerous diffraction patter...

Full description

Saved in:
Bibliographic Details
Published in:Acta crystallographica. Section A, Foundations and advances Foundations and advances, 2023-07, Vol.79 (4), p.360-368
Main Authors: Matinyan, Senik, Demir, Burak, Filipcik, Pavel, Abrahams, Jan Pieter, van Genderen, Eric
Format: Article
Language:English
Subjects:
Algorithms
Classification
Crystallography
Data collection
diffraction
Diffraction patterns
Electron beams
Electron diffraction
Electron microscopy
Electrons
Feature extraction
Learning algorithms
Machine learning
neural networks
Proteins
Research Papers
single‐molecule electron diffraction
TEM
transmission electron microscopy
Workflow
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As an alternative approach to X‐ray crystallography and single‐particle cryo‐electron microscopy, single‐molecule electron diffraction has a better signal‐to‐noise ratio and the potential to increase the resolution of protein models. This technology requires collection of numerous diffraction patterns, which can lead to congestion of data collection pipelines. However, only a minority of the diffraction data are useful for structure determination because the chances of hitting a protein of interest with a narrow electron beam may be small. This necessitates novel concepts for quick and accurate data selection. For this purpose, a set of machine learning algorithms for diffraction data classification has been implemented and tested. The proposed pre‐processing and analysis workflow efficiently distinguished between amorphous ice and carbon support, providing proof of the principle of machine learning based identification of positions of interest. While limited in its current context, this approach exploits inherent characteristics of narrow electron beam diffraction patterns and can be extended for protein data classification and feature extraction. Neural networks were trained for robust classification of narrow electron beam diffraction patterns and may significantly decrease the need for storage space.
ISSN:2053-2733
0108-7673
2053-2733
DOI:10.1107/S2053273323004680