An official website of the United States government
Tandem mass spectrometry (MS/MS) is crucial for small-molecule analysis; however, traditional computational methods are limited by incomplete reference libraries and complex data processing. Machine learning (ML) is transforming small-molecule mass spectrometry in three key directions: (a) predicting MS/MS spectra and related physicochemical properties to expand reference libraries, (b) improving spectral matching through automated pattern extraction, and (c) predicting molecular structures of compounds directly from their MS/MS spectra. We review ML approaches for molecular representations [descriptors, simplified molecular-input line-entry (SMILE) strings, and graphs] and MS/MS spectra representations (using binned vectors and peak lists) along with recent advances in spectra prediction, retention time, collision cross sections, and spectral matching. Finally, we discuss ML-integrated workflows for chemical formula identification. By addressing the limitations of current methods for compound identification, these ML approaches can greatly enhance the understanding of biological processes and the development of diagnostic and therapeutic tools.
more »
« less
3DMolMS: prediction of tandem mass spectra from 3D molecular conformations
Abstract Motivation Tandem mass spectrometry is an essential technology for characterizing chemical compounds at high sensitivity and throughput, and is commonly adopted in many fields. However, computational methods for automated compound identification from their MS/MS spectra are still limited, especially for novel compounds that have not been previously characterized. In recent years, in silico methods were proposed to predict the MS/MS spectra of compounds, which can then be used to expand the reference spectral libraries for compound identification. However, these methods did not consider the compounds’ 3D conformations, and thus neglected critical structural information. Results We present the 3D Molecular Network for Mass Spectra Prediction (3DMolMS), a deep neural network model to predict the MS/MS spectra of compounds from their 3D conformations. We evaluated the model on the experimental spectra collected in several spectral libraries. The results showed that 3DMolMS predicted the spectra with the average cosine similarity of 0.691 and 0.478 with the experimental MS/MS spectra acquired in positive and negative ion modes, respectively. Furthermore, 3DMolMS model can be generalized to the prediction of MS/MS spectra acquired by different labs on different instruments through minor fine-tuning on a small set of spectra. Finally, we demonstrate that the molecular representation learned by 3DMolMS from MS/MS spectra prediction can be adapted to enhance the prediction of chemical properties such as the elution time in the liquid chromatography and the collisional cross section measured by ion mobility spectrometry, both of which are often used to improve compound identification. Availability and implementation The codes of 3DMolMS are available at https://github.com/JosieHong/3DMolMS and the web service is at https://spectrumprediction.gnps2.org.
more »
« less
- PAR ID:
- 10431109
- Editor(s):
- Elofsson, Arne
- Date Published:
- Journal Name:
- Bioinformatics
- Volume:
- 39
- Issue:
- 6
- ISSN:
- 1367-4811
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Background: Spectral library searching is currently the most common approach for compound annotation in untargeted metabolomics. Spectral libraries applicable to liquid chromatography mass spectrometry have grown in size over the past decade to include hundreds of thousands to millions of mass spectra and tens of thousands of compounds, forming an essential knowledge base for the interpretation of metabolomics experiments. Aim of Review: We describe existing spectral library resources, highlight different strategies for compiling spectral libraries, and discuss quality considerations that should be taken into account when interpreting spectral library searching results. Finally, we describe how spectral libraries are empowering the next generation of machine learning tools in computational metabolomics, and discuss several opportunities for using increasingly accessible large spectral libraries. Key Scientific Concepts of Review: This review focuses on the current state of spectral libraries for untargeted LC-MS/MS based metabolomics. We show how the number of entries in publicly accessible spectral libraries has increased more than 60-fold in the past eight years to aid molecular interpretation and we discuss how the role of spectral libraries in untargeted metabolomics will evolve in the near future.more » « less
-
The annotation of small molecules is one of the most challenging and important steps in untargeted mass spectrometry analysis, as most of our biological interpretations rely on structural annotations. Molecular networking has emerged as a structured way to organize and mine data from untargeted tandem mass spectrometry (MS/MS) experiments and has been widely applied to propagate annotations. However, propagation is done through manual inspection of MS/MS spectra connected in the spectral networks and is only possible when a reference library spectrum is available. One of the alternative approaches used to annotate an unknown fragmentation mass spectrum is through the use of in silico predictions. One of the challenges of in silico annotation is the uncertainty around the correct structure among the predicted candidate lists. Here we show how molecular networking can be used to improve the accuracy of in silico predictions through propagation of structural annotations, even when there is no match to a MS/MS spectrum in spectral libraries. This is accomplished through creating a network consensus of re-ranked structural candidates using the molecular network topology and structural similarity to improve in silico annotations. The Network Annotation Propagation (NAP) tool is accessible through the GNPS web-platform https://gnps.ucsd.edu/ProteoSAFe/static/gnps-theoretical.jsp.more » « less
-
Abstract MotivationTandem mass spectrometry (MS/MS) is a crucial technology for large-scale proteomic analysis. The protein database search or the spectral library search are commonly used for peptide identification from MS/MS spectra, which, however, may face challenges due to experimental variations between replicated spectra and similar fragmentation patterns among distinct peptides. To address this challenge, we present SpecEncoder, a deep metric learning approach to address these challenges by transforming MS/MS spectra into robust and sensitive embedding vectors in a latent space. The SpecEncoder model can also embed predicted MS/MS spectra of peptides, enabling a hybrid search approach that combines spectral library and protein database searches for peptide identification. ResultsWe evaluated SpecEncoder on three large human proteomics datasets, and the results showed a consistent improvement in peptide identification. For spectral library search, SpecEncoder identifies 1%–2% more unique peptides (and PSMs) than SpectraST. For protein database search, it identifies 6%–15% more unique peptides than MSGF+ enhanced by Percolator, Furthermore, SpecEncoder identified 6%–12% additional unique peptides when utilizing a combined library of experimental and predicted spectra. SpecEncoder can also identify more peptides when compared to deep-learning enhanced methods (MSFragger boosted by MSBooster). These results demonstrate SpecEncoder’s potential to enhance peptide identification for proteomic data analyses. Availability and ImplementationThe source code and scripts for SpecEncoder and peptide identification are available on GitHub at https://github.com/lkytal/SpecEncoder. Contact: hatang@iu.edu.more » « less
-
Purpose This paper aims to study the mass loss of three-dimensional (3D) printed materials at high temperatures. A preconcentration and analysis technique, static headspace gas chromatography-mass spectrometry (SHS-GC-MS), is demonstrated for the analysis of volatile compounds liberated from fused deposition modeling (FDM) and stereolithography (SLA) 3D printed models under elevated temperatures. Design/methodology/approach A total of seven commercial 3D printing materials were tested using the SHS-GC-MS approach. The printed model mass and mass loss were examined as a function of FDM printing parameters including printcore temperature, model size and printing speed, and the use of SLA postprocessing procedures. A high temperature resin was used to demonstrate that thermal degradation products can be identified when the model is incubated under high temperatures. Findings At higher printing temperatures and larger model sizes, the initial printed model mass increased and showed more significant mass loss after thermal incubation for FDM models. For models produced by SLA, the implementation of a postprocessing procedure reduced the mass loss at elevated temperatures. All FDM models showed severe structural deformation when exposed to high temperatures, while SLA models remained structurally intact. Mass spectra and chromatographic retention times acquired from the high temperature resin facilitated identification of eight compounds (monomers, crosslinkers and several photoinitiators) liberated from the resin. Originality/value The study exploits the high sensitivity of SHS-GC-MS to identify thermal degradation products emitted from 3D printed models under elevated temperatures. The results will aid in choosing appropriate filament/resin materials and printing mechanisms for applications that require elevated temperatures.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1093/bioinformatics/btad354
