English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Machine-learning-enhanced time-of-flight mass spectrometry analysis

Wei, Y., Varanasi, R. S., Schwarz, T., Gomell, L., Zhao, H., Larson, D. J., et al. (2021). Machine-learning-enhanced time-of-flight mass spectrometry analysis. Patterns, 2(2): 100192. doi:10.1016/j.patter.2020.100192.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
Machine-learning-enhanced time-of-flight mass spectrometry analysis _ Elsevier Enhanced Reader.pdf (Supplementary material), 7MB
Name:
Machine-learning-enhanced time-of-flight mass spectrometry analysis _ Elsevier Enhanced Reader.pdf
Description:
Open Access
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
2021
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Wei, Ye1, Author              
Varanasi, Rama Srinivas2, Author              
Schwarz, Torsten3, Author              
Gomell, Leonie3, Author              
Zhao, Huan2, Author              
Larson, David J.4, Author              
Sun, Binhan5, Author              
Liu, Geng6, Author              
Chen, Hao6, Author              
Raabe, Dierk1, Author              
Gault, Baptiste3, 7, Author              
Affiliations:
1Microstructure Physics and Alloy Design, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_1863381              
2Alloy Design and Thermomechanical Processing, Microstructure Physics and Alloy Design, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_1863383              
3Atom Probe Tomography, Microstructure Physics and Alloy Design, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_1863384              
4CAMECA Instruments Inc., 5500 Nobel Drive, Madison, WI, USA, ou_persistent22              
5Mechanism-based Alloy Design, Microstructure Physics and Alloy Design, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_1863383              
6Key Laboratory for Advanced Materials of Ministry of Education, School of Materials Science and Engineering, Tsinghua University, Beijing 100084, China, ou_persistent22              
7Imperial College, Royal School of Mines, Department of Materials, London, SW7 2AZ, UK, ou_persistent22              

Content

show
hide
Free keywords: Chemical analysis; Computer aided instruction; Data handling; Inductively coupled plasma; Isotopes; Learning algorithms; Mass spectrometers; Mass spectrometry; Turing machines, Compositional analysis; High-throughput data; Identification process; Isotopic abundances; Machine learning applications; Mass-to-charge ratio; Time of flight mass spectrometry; Time-of-flight mass spectra, Machine learning
 Abstract: Mass spectrometry is a widespread approach used to work out what the constituents of a material are. Atoms and molecules are removed from the material and collected, and subsequently, a critical step is to infer their correct identities based on patterns formed in their mass-to-charge ratios and relative isotopic abundances. However, this identification step still mainly relies on individual users' expertise, making its standardization challenging, and hindering efficient data processing. Here, we introduce an approach that leverages modern machine learning technique to identify peak patterns in time-of-flight mass spectra within microseconds, outperforming human users without loss of accuracy. Our approach is cross-validated on mass spectra generated from different time-of-flight mass spectrometry (ToF-MS) techniques, offering the ToF-MS community an open-source, intelligent mass spectra analysis. Time-of-flight mass spectrometry (ToF-MS) is a mainstream analytical technique widely used in biology, chemistry, and materials science. ToF-MS provides quantitative compositional analysis with high sensitivity across a wide dynamic range of mass-to-charge ratios. A critical step in ToF-MS is to infer the identity of the detected ions. Here, we introduce a machine-learning-enhanced algorithm to provide a user-independent approach to performing this identification using patterns from the natural isotopic abundances of individual atomic and molecular ions, without human labeling or prior knowledge of composition. Results from several materials and techniques are compared with those obtained by field experts. Our open-source, easy-to-implement, reliable analytic method accelerates this identification process. A wide range of ToF-MS-based applications can benefit from our approach, e.g., hunting for patterns of biomarkers or for contamination on solid surfaces in high-throughput data. A machine-learning application for the accelerated data processing and interpretation of time-of-flight mass spectrometry is presented. The machine learns patterns in a human-label-free manner, making the process easy to implement and the result highly reproducible. © 2020 The Authors

Details

show
hide
Language(s): eng - English
 Dates: 2021-02-12
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1016/j.patter.2020.100192
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Patterns
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Amsterdam : Elsevier
Pages: - Volume / Issue: 2 (2) Sequence Number: 100192 Start / End Page: - Identifier: ISSN: 2666-3899
CoNE: https://pure.mpg.de/cone/journals/resource/2666-3899