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

Qualitative Analysis01:10

Qualitative Analysis

1.3K
Qualitative analysis is the process of identifying elements, ions, or compounds in an unknown sample. It is the first and most fundamental type of analysis based on the hierarchy of analytical goals. This hierarchy is significant as it provides a structured approach to scientific research, with qualitative analysis serving as the initial step, providing essential information before moving on to quantitative or other forms of analysis.
There are two main approaches to qualitative analysis:...
1.3K
Mass Spectrum: Interpretation01:24

Mass Spectrum: Interpretation

2.7K
An unknown compound can be established by identifying the molecular ion peak in the mass spectrum. The molecular ion peak is often weak or absent due to the predominance of fragmentation in high-energy electron beams. In such cases, a soft-energy electron beam can be used to scan the spectrum to enhance the intensity of the molecular ion peak. Additionally, chemical ionization, field ionization, and desorption ionization spectra are used to obtain a relatively intense molecular ion peak.To...
2.7K
Mass Spectrometry: Complex Analysis01:21

Mass Spectrometry: Complex Analysis

1.6K
Mass spectrometry is an important technique for the identification of pure compounds. However, it has some limitations for the analysis of complex mixtures, often due to excessive fragmentation making the spectrum too complicated to decipher. Mass spectrometry can be combined with suitable separation methods in sequence, forming hyphenated methods, which are useful in the analysis of complex mixtures.
GC–MS is a powerful hyphenated method commonly used in forensics and environmental...
1.6K
Chemical Ionization (CI) Mass Spectrometry01:21

Chemical Ionization (CI) Mass Spectrometry

1.4K
The molecular ion peak of a molecule in the mass spectrum provides vital information for molecular identification. However, conventional electron impact ionization can lead to the rapid dissociation of some molecular ions before they reach the detector. A milder ionization method is required to increase the lifetime of such ionized analyte molecules. Chemical ionization (CI) is a gas-phase protonation reaction useful for mass-analyzing analyte molecules that are easily protonated to yield the...
1.4K

You might also read

Related Articles

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

Sort by
Same author

Efficient on-site detection of nitazenes in hair: Integrating MCX pipette-tip solid-phase extraction with miniaturized mass spectrometry.

Talanta·2026
Same author

Integrated micro-solid-phase extraction with miniature mass spectrometry for on-site detection of illicit drugs in human hair.

Journal of chromatography. A·2026
Same author

META-Tox: Multiview Ensemble with Topological Aggregation for Robust <i>In Vivo</i> Toxicity Prediction.

The journal of physical chemistry letters·2026
Same author

A Deep Learning Model for Efficient Nontargeted Screening of New Psychoactive Substances with Benchtop Nuclear Magnetic Resonance Devices.

Analytical chemistry·2025
Same author

Regulating cell stress responses by nitric oxide to enhance calcium overload-mediated tumor therapy.

Biomaterials·2025
Same author

A Novel Nontargeted Screening Strategy for New Psychoactive Substances: A Case Study of Synthetic Cannabinoids Based on Electron-Activated Dissociation High-Resolution Mass Spectrometry and Intelligent Elucidation.

Analytical chemistry·2025

Related Experiment Video

Updated: Jan 13, 2026

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry
11:14

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Published on: October 2, 2016

12.1K

Explainable Analysis for New Psychoactive Substance Identification with Chemical Insights.

Pengfei Liu1, Cuimei Liu2, Liang Li3

  • 1School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong 510006, China.

Journal of Chemical Information and Modeling
|October 28, 2025
PubMed
Summary

A new deep learning model, NPS-EDR, can identify novel psychoactive substances (NPS) by analyzing molecular structures. This explainable AI approach offers enhanced accuracy and transparency for public health and forensic applications.

More Related Videos

Color Spot Test As a Presumptive Tool for the Rapid Detection of Synthetic Cathinones
06:06

Color Spot Test As a Presumptive Tool for the Rapid Detection of Synthetic Cathinones

Published on: February 5, 2018

26.1K
High-throughput and Comprehensive Drug Surveillance Using Multisegment Injection-Capillary Electrophoresis-Mass Spectrometry
10:17

High-throughput and Comprehensive Drug Surveillance Using Multisegment Injection-Capillary Electrophoresis-Mass Spectrometry

Published on: April 23, 2019

10.2K

Related Experiment Videos

Last Updated: Jan 13, 2026

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry
11:14

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Published on: October 2, 2016

12.1K
Color Spot Test As a Presumptive Tool for the Rapid Detection of Synthetic Cathinones
06:06

Color Spot Test As a Presumptive Tool for the Rapid Detection of Synthetic Cathinones

Published on: February 5, 2018

26.1K
High-throughput and Comprehensive Drug Surveillance Using Multisegment Injection-Capillary Electrophoresis-Mass Spectrometry
10:17

High-throughput and Comprehensive Drug Surveillance Using Multisegment Injection-Capillary Electrophoresis-Mass Spectrometry

Published on: April 23, 2019

10.2K

Area of Science:

  • Chemistry
  • Computer Science
  • Pharmacology
  • Public Health

Background:

  • New psychoactive substances (NPS) present a growing global health risk due to their rapid evolution and structural diversity.
  • Conventional detection methods struggle to identify novel NPS variants effectively.
  • Deep learning offers a promising avenue for proactive identification of emerging substances.

Purpose of the Study:

  • To introduce NPS-EDR, an Explainable Deep Reasoning model for the identification of new psychoactive substances.
  • To develop a model that provides interpretable structural and functional analyses of potential NPS molecules.
  • To enhance accuracy, precision, and transparency in NPS identification compared to existing methods.

Main Methods:

  • Development of NPS-EDR, a two-stage prediction-explanation deep learning framework.
  • Utilizing cooperative training of mode-specific experts and reinforcement learning for consistent predictions and explanations.
  • Training on a chain-of-thought dataset of over 2,900 NPS and drug molecules, integrating chemical prior knowledge.
  • Leveraging biochemical insights for structural-functional interpretation.

Main Results:

  • NPS-EDR achieves superior accuracy, precision, and transparency in identifying potential NPS molecules.
  • The model demonstrates enhanced analytical capabilities and builds confidence through its explanation framework.
  • NPS-EDR outperforms mainstream large language models and biomolecular-specific chemical language models in NPS identification.
  • The model provides interpretable structural and functional analyses, going beyond simple detection.

Conclusions:

  • NPS-EDR offers a novel and effective approach to address the challenge of emerging new psychoactive substances.
  • The model's transparent reasoning capabilities can significantly benefit public health strategies, pharmacological research, and forensic science.
  • Explainable deep learning provides a powerful tool for proactive identification and analysis in the field of drug discovery and control.