Direct Classification of GC × GC-Analyzed Complex Mixtures Using Non-Negative Matrix Factorization-Based Feature Extraction

Zushi, Yasuyuki; Hashimoto, Shunji

doi:10.1021/acs.analchem.7b04313

Cited by 12 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aside from the question of whether the exclusion of matrices matches the purpose of non-target analysis, it may be possible to reduce the number of matrices by increasing the selectivity of SBSE while changing the adsorbent and/or adding solvent, or by adding solvent extraction and certain pre-treatments. Post-data processing, which we have developed (Zushi et al, 2017(Zushi et al, , 2018, is also a potential solution.…”

Section: Evaluation Of the Detectability Of Differencesmentioning

confidence: 99%

“…The use of GC × GC for environmental analysis is expected to be especially effective for simultaneous analysis of compounds with multiple isomers and analogs, such as hydroxylated polychlorinated biphenyls (HO-PCBs) (Hashimoto et al, 2010;Rezek et al, 2012) and chlorinated paraffins (Eljarrat and Barcelo, 2006;Muscalu et al, 2017), which pose environmental risks but are difficult to measure. We have been developing methods using GC × GC / ToFMS (Fushimi et al, 2012;Hashimoto et al, 2008Hashimoto et al, , 2011Ieda et al, 2019;Lješević et al, 2019;Ochiai et al, 2011) and software tools to analyze the data generated (Hashimoto et al, 2013;Zushi et al, 2013Zushi et al, , 2014Zushi et al, , 2015Zushi et al, , 2017Zushi and Hashimoto, 2018) for environmental investigations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Preliminary statistical investigation of anomaly detection in non-target environmental monitoring by comprehensive two-dimensional gas chromatography/time-of-flight mass spectrometry

Hashimoto

Ohtsuka

Onizuka

et al. 2021

EMCR

Self Cite

View full text Add to dashboard Cite

The notable challenges facing non-target environmental monitoring are the improvement of the reproducibility of extraction rates and the selection of internal standards for concentration correction. In the present study, a rapid and comprehensive analytical method, which we had developed in a previous study, greatly reduces the need for pretreatment. The method was applied to the actual measurement of river water. The water samples were divided into five sub-samples and analyzed by sorptive extraction using a magnetic stirrer coated with polydimethyl siloxane. Direct and whole sample extracts were determined by thermal desorption/comprehensive two-dimensional gas chromatography/ time-of-flight mass spectrometry. Approximately 2,000 of the components were detected, and 80 of these components were selected for statistical evaluation in order to investigate the stability of the method and the ability to detect differences among samples. The effectiveness of this technique was confirmed by statistical methods, including the Kruskal-Wallis test, which is used to examine nonparametric multigroup comparisons and with which once can detect differences by comparing raw data obtained as precise mass measurements without the need to identify the substance itself. In brief, we show that changes in signal intensity of any unknown substance can be detected. We note that variations in data (retention time, mass spectrum, and signal intensity) affect the ability to detect differences. The accuracy of each therefore had to be improved to enable sensitive and precise detection.

show abstract

Section: Evaluation Of the Detectability Of Differencesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Preliminary statistical investigation of anomaly detection in non-target environmental monitoring by comprehensive two-dimensional gas chromatography/time-of-flight mass spectrometry

Hashimoto

Ohtsuka

Onizuka

et al. 2021

EMCR

Self Cite

View full text Add to dashboard Cite

show abstract

“…A region of interest (ROI) refers to any region within the GC × GC–TOFMS contour image with contrasting features that could be used to classify the corresponding sample. Previously, non-negative matrix factorization was used for unsupervised direct GC × GC–TOFMS contour classification [ 27 ], but the method was unable to identify multiple ROIs within contour data and its classifier could not be customized. Furthermore, DL has not yet been used for automated multi-ROI identification, simulation, and untargeted profiling of GC × GC–TOFMS contour data.…”

Section: Introductionmentioning

confidence: 99%

CRISP: a deep learning architecture for GC × GC–TOFMS contour ROI identification, simulation and analysis in imaging metabolomics

Mathema

Duangkumpha

Wanichthanarak

et al. 2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

Two-dimensional gas chromatography–time-of-flight mass spectrometry (GC × GC–TOFMS) provides a large amount of molecular information from biological samples. However, the lack of a comprehensive compound library or customizable bioinformatics tool is currently a challenge in GC × GC–TOFMS data analysis. We present an open-source deep learning (DL) software called contour regions of interest (ROI) identification, simulation and untargeted metabolomics profiler (CRISP). CRISP integrates multiple customizable deep neural network architectures for assisting the semi-automated identification of ROIs, contour synthesis, resolution enhancement and classification of GC × GC–TOFMS-based contour images. The approach includes the novel aggregate feature representative contour (AFRC) construction and stacked ROIs. This generates an unbiased contour image dataset that enhances the contrasting characteristics between different test groups and can be suitable for small sample sizes. The utility of the generative models and the accuracy and efficacy of the platform were demonstrated using a dataset of GC × GC–TOFMS contour images from patients with late-stage diabetic nephropathy and healthy control groups. CRISP successfully constructed AFRC images and identified over five ROIs to create a deepstacked dataset. The high fidelity, 512 × 512-pixels generative model was trained as a generator with a Fréchet inception distance of <47.00. The trained classifier achieved an AUROC of >0.96 and a classification accuracy of >95.00% for datasets with and without column bleed. Overall, CRISP demonstrates good potential as a DL-based approach for the rapid analysis of 4-D GC × GC–TOFMS untargeted metabolite profiles by directly implementing contour images. CRISP is available at https://github.com/vivekmathema/GCxGC-CRISP.

show abstract

“…NMF has been used in the wider field of mass spectrometry, , image analysis, and acoustic analysis . Recently, NMF was applied for the deconvolution of spectra and for classification of chromatographic patterns in measurements recorded by state-of-the-art technology of GC × GC-HR-TOFMS. ,, Apart from MCR, model peak methods are implemented in the software AMDIS and ADAP-GC which were developed for analyzing GC–MS data. The model peak method first attempts to find a peak to be deconvoluted which fulfills peak criteria, such as peak height and sharpness for each ion chromatogram.…”

Section: Introductionmentioning

confidence: 99%

NMF-Based Spectral Deconvolution with a Web Platform GC Mixture Touch

Zushi

2021

ACS Omega

Self Cite

View full text Add to dashboard Cite

Complete separation of chemicals in a complex mixture is far from being achieved even with the current highperformance separation technology, such as gas chromatography− mass spectrometry (GC−MS). Several deconvolution techniques based on multivariate curve resolution (MCR), or model peak methods, which are represented by AMDIS, have been developed to address the above-mentioned issue. The model peak methods have been developed to provide easy-to-use tools, including AMDIS, but are limited for MCR with approximation methods. The objective of this study was to provide an easy-to-use deconvolution tool based on the MCR approach for GC−MS data. The spectral deconvolution tool based on non-negative matrix factorization (NMF), which calculates outputs using an approximation method, was implemented as a free web platform, namely, GC Mixture Touch, clarifying the effects of the parameters required for the deconvolution. The GC Mixture Touch was applied to the actual mixture sample of road dust spiked with chemical standards. The recommended parameter settings for smoothing of the chromatogram, the number of ranks, and the NMF algorithm for the deconvolution were clarified through the study. The performance with the suggested parameters was evaluated with respect to compound identification for the actual sample. All of the test compounds in the sample were correctly identified with the GC Mixture Touch, outperforming AMDIS with respect to the identification. The GC Mixture Touch is easy to use on the web even for users without programming skills. This is expected to enhance the application of the NMF-based deconvolution, and it should prove helpful in finding the compounds hidden in complex mixtures that are difficult to find using conventional approaches.

show abstract

Direct Classification of GC × GC-Analyzed Complex Mixtures Using Non-Negative Matrix Factorization-Based Feature Extraction

Cited by 12 publications

References 33 publications

Preliminary statistical investigation of anomaly detection in non-target environmental monitoring by comprehensive two-dimensional gas chromatography/time-of-flight mass spectrometry

Preliminary statistical investigation of anomaly detection in non-target environmental monitoring by comprehensive two-dimensional gas chromatography/time-of-flight mass spectrometry

CRISP: a deep learning architecture for GC × GC–TOFMS contour ROI identification, simulation and analysis in imaging metabolomics

NMF-Based Spectral Deconvolution with a Web Platform GC Mixture Touch

Contact Info

Product

Resources

About