Image Processing and Machine Learning for Automated Identification of Chemo-/Biomarkers in Chromatography-Mass Spectrometry

Chaiyanut Jirayupat, Kazuki Nagashima, Takuro Hosomi, Tsunaki Takahashi, Wataru Tanaka, Benjarong Samransuksamer, Guozhu Zhang, Jiangyang Liu, Masaki Kanai, Takeshi Yanagida

Research output: Contribution to journalArticlepeer-review

Abstract

We present a method namedNPFimg, which automatically identifies multivariate chemo-/biomarker features of analytes in chromatography-mass spectrometry (MS) data by combining image processing and machine learning.NPFimgprocesses a two-dimensional MS map (m/zvs retention time) to discriminate analytes and identify and visualize the marker features. Our approach allows us to comprehensively characterize the signals in MS data without the conventional peak picking process, which suffers from false peak detections. The feasibility of marker identification is successfully demonstrated in case studies of aroma odor and human breath on gas chromatography-mass spectrometry (GC-MS) even at the parts per billion level. Comparison with the widely usedXCMSshows the excellent reliability ofNPFimg, in that it has lower error rates of signal acquisition and marker identification. In addition, we show the potential applicability ofNPFimgto the untargeted metabolomics of human breath. While this study shows the limited applications,NPFimgis potentially applicable to data processing in diverse metabolomics/chemometrics using GC-MS and liquid chromatography-MS.NPFimgis available as open source on GitHub (http://github.com/poomcj/NPFimg) under the MIT license.

Original languageEnglish
Pages (from-to)14708-14715
Number of pages8
JournalAnalytical Chemistry
Volume93
Issue number44
DOIs
Publication statusPublished - Nov 9 2021

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry

Fingerprint

Dive into the research topics of 'Image Processing and Machine Learning for Automated Identification of Chemo-/Biomarkers in Chromatography-Mass Spectrometry'. Together they form a unique fingerprint.

Cite this