EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

3D-MSNet: a point cloud-based deep learning model for untargeted feature detection and quantification in profile LC-HRMS data

Ruimin Wang iD, Miaoshan Lu iD, Shaowei An iD, Jinyin Wang iD, Changbin Yu iD

Bioinformatics · 2023

DOI: 10.1093/bioinformatics/btad195 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2023. Verfasst von Ruimin Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Fudan University, Shanghai 200433, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province, Shandong First Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Liquid chromatography coupled with high-resolution mass spectrometry is widely used in composition profiling in untargeted metabolomics research. While retaining complete sample information, mass spectrometry (MS) data naturally have the characteristics of high dimensionality, high complexity, and huge data volume. In mainstream quantification methods, none of the existing methods can perform direct 3D analysis on lossless profile MS signals. All software simplify calculations by dimensionality reduction or lossy grid transformation, ignoring the full 3D signal distribution of MS data and resulting in inaccurate feature detection and quantification. Results On the basis that the neural network is effective for high-dimensional data analysis and can discover implicit features from large amounts of complex data, in this work, we propose 3D-MSNet, a novel deep learning-based model for untargeted feature extraction. 3D-MSNet performs direct feature detection on 3D MS point clouds as an instance segmentation task. After training on a self-annotated 3D feature dataset, we compared our model with nine popular software (MS-DIAL, MZmine 2, XCMS Online, MarkerView, Compound Discoverer, MaxQuant, Dinosaur, DeepIso, PointIso) on two metabolomics and one proteomics public benchmark datasets. Our 3D-MSNet model outperformed other software with significant improvement in feature detection and quantification accuracy on all evaluation datasets. Furthermore, 3D-MSNet has high feature extraction robustness and can be widely applied to profile MS data acquired with various high-resolution mass spectrometers with various resolutions. Availability and implementation 3D-MSNet is an open-source model and is freely available at https://github.com/CSi-Studio/3D-MSNet under a permissive license. Benchmark datasets, training dataset, evaluation methods, and results are available at https://doi.org/10.5281/zenodo.6582912.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCloud ComputingMass SpectrometrySoftwareChromatography, LiquidMetabolomics

Autor:innen und Institutionen

  • Fudan University, Shanghai 200433, China.
  • School of Engineering, Westlake University, Hangzhou, Zhejiang Province 310030, China.
  • Shandong First Medical University & Shandong Academy of Medical Sciences, Jinan, Shandong Province 250021, China.
  • Zhejiang University, Hangzhou, Zhejiang Province 310058, China.
  • School of Life Sciences, Westlake University, Hangzhou, Zhejiang Province 310030, China.

ORCID-Profile: Ruimin Wang, Miaoshan Lu, Shaowei An, Jinyin Wang, Changbin Yu

Förderung

  • Natural Science Foundation of Shandong Province
  • Shandong First Medical University

Zitieren

APA

Wang, R., Lu, M., An, S., Wang, J., & Yu, C. (2023). 3D-MSNet: a point cloud-based deep learning model for untargeted feature detection and quantification in profile LC-HRMS data. Bioinformatics. https://doi.org/10.1093/bioinformatics/btad195

Vancouver

Wang R, Lu M, An S, Wang J, Yu C. 3D-MSNet: a point cloud-based deep learning model for untargeted feature detection and quantification in profile LC-HRMS data. Bioinformatics. 2023. doi:10.1093/bioinformatics/btad195

BibTeX
@article{Wang2023,
  author = {Wang, Ruimin and Lu, Miaoshan and An, Shaowei and Wang, Jinyin and Yu, Changbin},
  title = {3D-MSNet: a point cloud-based deep learning model for untargeted feature detection and quantification in profile LC-HRMS data},
  journal = {Bioinformatics},
  year = {2023},
  doi = {10.1093/bioinformatics/btad195}
}
Kostenlos starten →