EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced Environmental PFAS Characterization Using a Virtual High-Resolution Mass Spectral Library Generated by Transfer Learning-Based Neural Network

Yi-Chi Chen iD, Hsin-Yi Wu iD, Man-Ni Zhuang iD, Chen-Ming Yi, Wei-Sheng Wu iD, Pao-Chi Liao iD

Environmental Science & Technology · 23.06.2026 · 60 (24) · 17341-17354

DOI: 10.1021/acs.est.6c05733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Science & Technology, online erschienen am 10.06.2026. Verfasst von Yi-Chi Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Environmental and Occupational Health, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

spectral prediction models for PFAS spectra prediction across multiple spectral similarity metrics. In library searching tasks, libraries generated by other spectral prediction models showed top-1 recall between 42.1% and 55.4%, while NPFAS-MS demonstrated 71.1%. Applying the virtual PFAS mass spectral library generated with NPFAS-MS using 10,553 PFAS structures from the U.S. EPA and NORMAN databases to groundwater and aqueous film-forming foam (AFFF) samples revealed more potential PFAS than other mass spectral databases. Specifically, 38 potential PFAS were annotated in AFFF products and 40 in groundwater samples. NPFAS-MS enabled characterization of emerging PFAS, including ultrashort-chain, unsaturated, and substituted derivatives in environmental matrices. This advancement enables comprehensive environmental monitoring of rapidly evolving PFAS contamination. NPFAS-MS and associated resources were deployed as a web-based tool at https://cosbi10.ee.ncku.edu.tw/NPFAS_MS/, enabling both structure-to-spectrum prediction and library searching against 31,659 predicted PFAS spectra.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerTransfer Machine LearningFluorocarbonsMass Spectrometry

Stichwörter der Autor:innen

PFASartificial neural networkhigh-resolution mass spectrometrymass spectral librarytransfer learning

Substanzen

Fluorocarbons

Autor:innen und Institutionen

  • Department of Environmental and Occupational Health, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan.
  • Instrumentation Center, National Taiwan University, Taipei 106, Taiwan.
  • Institute of Computer and Communication Engineering, National Cheng Kung University, Tainan 701, Taiwan.
  • Department of Electrical Engineering, National Cheng Kung University, Tainan 701, Taiwan.

ORCID-Profile: Yi-Chi Chen, Hsin-Yi Wu, Man-Ni Zhuang, Wei-Sheng Wu, Pao-Chi Liao

Förderung

  • National Science and Technology Council

Zitieren

APA

Chen, Y. C., Wu, H. Y., Zhuang, M. N., Yi, C. M., Wu, W. S., & Liao, P. C. (2026). Enhanced Environmental PFAS Characterization Using a Virtual High-Resolution Mass Spectral Library Generated by Transfer Learning-Based Neural Network. Environmental Science & Technology, 60(24), 17341-17354. https://doi.org/10.1021/acs.est.6c05733

Vancouver

Chen YC, Wu HY, Zhuang MN, Yi CM, Wu WS, Liao PC. Enhanced Environmental PFAS Characterization Using a Virtual High-Resolution Mass Spectral Library Generated by Transfer Learning-Based Neural Network. Environmental Science & Technology. 2026;60(24):17341-17354. doi:10.1021/acs.est.6c05733

BibTeX
@article{Chen2026,
  author = {Chen, Yi-Chi and Wu, Hsin-Yi and Zhuang, Man-Ni and Yi, Chen-Ming and Wu, Wei-Sheng and Liao, Pao-Chi},
  title = {Enhanced Environmental PFAS Characterization Using a Virtual High-Resolution Mass Spectral Library Generated by Transfer Learning-Based Neural Network},
  journal = {Environmental Science & Technology},
  year = {2026},
  volume = {60},
  number = {24},
  pages = {17341--17354},
  doi = {10.1021/acs.est.6c05733}
}
Kostenlos starten →