PSMS: A Deep Learning-Based Prediction System for Identifying New Psychoactive Substances Using Mass Spectrometry.

Journal: Analytical chemistry
PMID:

Abstract

The rapid proliferation of new psychoactive substances (NPS) poses significant challenges to conventional mass-spectrometry-based identification methods due to the absence of reference spectra for these emerging substances. This paper introduces PSMS, an AI-powered predictive system designed specifically to address the limitations of identifying the emergence of unidentified novel illicit drugs. PSMS builds a synthetic NPS database by enumerating feasible derivatives of known substances and uses deep learning to generate mass spectra and chemical fingerprints. When the mass spectrum of an analyte does not match any known reference, PSMS simultaneously examines the chemical fingerprint and mass spectrum against the putative NPS database using integrated metrics to deduce possible identities. Experimental results affirm the effectiveness of PSMS in identifying cathinone derivatives within real evidence specimens, signifying its potential for practical use in identifying emerging drugs of abuse for researchers and forensic experts.

Authors

  • Yi-Ching Lin
    Department of Laboratory Medicine, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan.
  • Wei-Chen Chien
    Department of Computer Science, National Yang Ming Chiao Tung University, HsinChu 300, Taiwan.
  • Yu-Xuan Wang
    Department of Computer Science, National Yang Ming Chiao Tung University, HsinChu 300, Taiwan.
  • Ying-Hau Wang
    Department of Computer Science, National Yang Ming Chiao Tung University, HsinChu 300, Taiwan.
  • Feng-Shuo Yang
    Department of Laboratory Medicine, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung 807, Taiwan.
  • Li-Ping Tseng
    Department of Laboratory Medicine, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan.
  • Jui-Hung Hung
    Department of Computer Science, National Yang Ming Chiao Tung University, HsinChu 300, Taiwan.