Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Toward Machine Learning-Driven Mass Spectrometric Identification of Trichothecenes in the Absence of Standard Reference Materials

Journal Article · · Analytical Chemistry

While a significant body of work exists on the detection of commonly known trichothecene toxins, biological, environmental, and other transformational processes can generate many under-characterized and unknown modified trichothecenes. Lacking both analytical reference standards and associated mass spectral databases, identification of these modified compounds reflects both a challenge and a critical gap from forensic and public health perspectives. Here we report here the application of machine learning (ML) techniques toward identification of discriminative fragment ions from mass spectrometric data that can be exploited to detect evidence of type A and B trichothecenes. The goal of this work is to establish a new method for the identification of unknown, though structurally similar trichothecenes, by leveraging objective ML techniques. Discriminative fragments derived from a series of gradient-boosted machine learners are then used to develop ML-driven precursor ion scan (PIS) methods on a triple quadrupole mass spectrometer (QQQ) for screening of “unknown unknown” trichothecenes. Specifically, we apply the PIS method to a laboratory-synthesized trichothecene, a first step in demonstrating the power of alternative, machine learning-driven mass spectrometric methods.

Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC52-07NA27344
OSTI ID:
2230002
Report Number(s):
LLNL--JRNL-858297; 1081772
Journal Information:
Analytical Chemistry, Journal Name: Analytical Chemistry Journal Issue: 35 Vol. 95; ISSN 0003-2700
Publisher:
American Chemical Society (ACS)Copyright Statement
Country of Publication:
United States
Language:
English

References (22)

Mycotoxins journal January 2002
Modern Applied Statistics with S book August 2002
Metabolism of three trichothecene ycotoxins, T-2 toxin, diacetoxyscirpenol and deoxynivalenol, by bovne rumen microorganisms journal January 1987
Modified mycotoxins: An updated review on their formation, detection, occurrence, and toxic effects journal January 2018
Multiplexing data independent untargeted workflows for mycotoxins screening on a quadrupole-Orbitrap high resolution mass spectrometry platform journal April 2019
Determination of deoxynivalenol (DON) and its derivatives: Current status of analytical methods journal November 2013
Molecular biodiversity of mycotoxigenic fungi that threaten food safety journal October 2013
Fragmentation study of five trichothecenes using electrospray hybrid ion trap/time-of-flight mass spectrometry with accurate mass measurements journal January 2012
Detection of new emerging type-A trichothecenes by untargeted mass spectrometry journal February 2018
Statistical analysis of the chemical attribution signatures of 3-methylfentanyl and its methods of production journal August 2018
Part 3: Solid phase extraction of Russian VX and its chemical attribution signatures in food matrices and their detection by GC-MS and LC-MS journal August 2018
MS2Analyzer: A Software for Small Molecule Substructure Annotations from Accurate Tandem Mass Spectra journal October 2014
Chemical Attribution of Fentanyl Using Multivariate Statistical Analysis of Orthogonal Mass Spectral Data journal March 2016
All Ion Fragmentation Analysis Enhances the Untargeted Profiling of Glucosinolates in Brassica Microgreens by Liquid Chromatography and High-Resolution Mass Spectrometry journal October 2022
Reproducible molecular networking of untargeted mass spectrometry data using GNPS journal May 2020
Topic modeling for untargeted substructure exploration in metabolomics journal November 2016
Study of the natural occurrence of T-2 and HT-2 toxins and their glucosyl derivatives from field barley to malt by high-resolution Orbitrap mass spectrometry journal June 2015
Recent advances and prospects of computational methods for metabolite identification: a review with emphasis on machine learning approaches journal August 2018
Variable selection and validation in multivariate modelling journal August 2018
Feature Selection with the Boruta Package journal January 2010
Molecular Networking: A Useful Tool for the Identification of New Psychoactive Substances in Seizures by LC–HRMS journal November 2020
Trichothecenes: From Simple to Complex Mycotoxins journal July 2011