PS2MS: A Deep Learning-Based Prediction System for Identifying New Psychoactive Substances Using Mass Spectrometry
Year: 2024
Type: article
Abstract: High Resolution Image Download MS PowerPoint Slide 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 PS 2 MS, an AI-powered predictive system designed specifically to address the limitations of identifying the emergence of unidentified novel illicit drugs. PS 2 MS 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, PS 2 MS 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 PS 2 MS 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.
Source: Analytical Chemistry
Authors: Yi-Ching Lin, Wei-Chen Chien, Yu-Xuan Wang, Ying-Hau Wang, Feng-Shuo Yang, Li-Ping Tseng, Jui-Hung Hung
Language: English
Subfield: Toxicology
Domain: Life Sciences
Open Access status: hybrid
Estimated APC paid: $4,500
Awards: G1186371594, G1341408376, G1541832837, Innovating the Next Generation Sequencing Cloud Analysis Platform---Using the Cloud-Based On-Demand Self-Service and the Compute Unified Device Architecture GPU Computing Technology, G352983100, G3645236443, G4444771526, G6130654231, Developing a Computationally Composed Mass Spectra Prediction System for New Psychoactive Substances Detection: a Novel Study of Synthetic Cathinone Detection, G6883705590
OpenAlex ID: W4392864267