Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Curated CYP450 Interaction Dataset: Covering the Majority of Phase I Drug Metabolism.

Scientific data·2025
Same author

Analyzing Generative AI and Machine Learning in Auto-Assessing Schizophrenia's Negative Symptoms.

Schizophrenia bulletin·2025
Same author

A robust and interpretable graph neural network-based protocol for predicting p-glycoprotein substrates.

Briefings in bioinformatics·2025
Same author

Advantages of two quantum programming platforms in quantum computing and quantum chemistry.

Journal of cheminformatics·2025
Same author

SPARK Taiwan: a decade of insights in adapting US translational medicine and commercialization methods.

Nature biotechnology·2025
Same author

Digital annealing optimization for natural product structure elucidation.

Briefings in bioinformatics·2024

Related Experiment Video

Updated: Jan 16, 2026

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow
09:04

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow

Published on: April 18, 2019

13.1K

DeePFAS: Deep-Learning-Enabled Rapid Annotation of PFAS: Enhancing Nontargeted Screening through Spectral Encoding

Heng Wang1, Tien-Chueh Kuo2, Yufeng Jane Tseng1,2,3,4

  • 1Department of Computer Science and Information Engineering, National Taiwan University, Taipei 10617, Taiwan.

Environmental Science & Technology
|September 30, 2025
PubMed
Summary

Detecting per- and polyfluoroalkyl substances (PFAS) is difficult. A new deep learning method, DeePFAS, rapidly annotates PFAS using MS2 spectra, streamlining environmental analysis.

Keywords:
PFAS (per- and polyfluoroalkyl substances)chemically latent spacedeep learningenvironmental analysismass spectrometry

More Related Videos

A Filter-based Surface Enhanced Raman Spectroscopic Assay for Rapid Detection of Chemical Contaminants
08:13

A Filter-based Surface Enhanced Raman Spectroscopic Assay for Rapid Detection of Chemical Contaminants

Published on: February 19, 2016

9.8K
PTR-ToF-MS Coupled with an Automated Sampling System and Tailored Data Analysis for Food Studies: Bioprocess Monitoring, Screening and Nose-space Analysis
08:43

PTR-ToF-MS Coupled with an Automated Sampling System and Tailored Data Analysis for Food Studies: Bioprocess Monitoring, Screening and Nose-space Analysis

Published on: May 11, 2017

12.9K

Related Experiment Videos

Last Updated: Jan 16, 2026

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow
09:04

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow

Published on: April 18, 2019

13.1K
A Filter-based Surface Enhanced Raman Spectroscopic Assay for Rapid Detection of Chemical Contaminants
08:13

A Filter-based Surface Enhanced Raman Spectroscopic Assay for Rapid Detection of Chemical Contaminants

Published on: February 19, 2016

9.8K
PTR-ToF-MS Coupled with an Automated Sampling System and Tailored Data Analysis for Food Studies: Bioprocess Monitoring, Screening and Nose-space Analysis
08:43

PTR-ToF-MS Coupled with an Automated Sampling System and Tailored Data Analysis for Food Studies: Bioprocess Monitoring, Screening and Nose-space Analysis

Published on: May 11, 2017

12.9K

Area of Science:

  • Environmental Chemistry
  • Analytical Chemistry
  • Artificial Intelligence

Background:

  • Per- and polyfluoroalkyl substances (PFAS) detection is challenging due to chemical diversity, complex matrices, and trace levels.
  • Existing methods like LC-HRMS face issues with contamination, labor, detection limits, and data processing.
  • A universal PFAS detection method is hindered by background contamination and the vast number of compounds.

Purpose of the Study:

  • To develop a rapid and efficient method for annotating PFAS in complex samples.
  • To overcome the limitations of current LC-HRMS techniques for PFAS analysis.
  • To leverage artificial intelligence for streamlining large-scale nontargeted PFAS screening.

Main Methods:

  • Developed DeePFAS, a deep-learning method for PFAS annotation.
  • Employed a spectral encoder with convolutional and transformer architectures.
  • Projected raw MS2 spectra into a latent space of chemical structural features.

Main Results:

  • DeePFAS enables efficient annotation of MS2 spectra by comparing latent representations with candidate molecules.
  • The method streamlines large-scale nontargeted PFAS screening.
  • Reduced analytical complexity in PFAS detection.

Conclusions:

  • DeePFAS demonstrates the potential of AI in environmental chemistry for PFAS analysis.
  • The deep learning approach offers a faster and more efficient alternative for PFAS identification.
  • This method can aid in overcoming current obstacles in PFAS detection and screening.