Browse
Submit Data
Databases
API
Help

Dataset Information

23 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Rapid Prediction of Electron-Ionization Mass Spectrometry Using Neural Networks.

ABSTRACT: When confronted with a substance of unknown identity, researchers often perform mass spectrometry on the sample and compare the observed spectrum to a library of previously collected spectra to identify the molecule. While popular, this approach will fail to identify molecules that are not in the existing library. In response, we propose to improve the library's coverage by augmenting it with synthetic spectra that are predicted from candidate molecules using machine learning. We contribute a lightweight neural network model that quickly predicts mass spectra for small molecules, averaging 5 ms per molecule with a recall-at-10 accuracy of 91.8%. Achieving high-accuracy predictions requires a novel neural network architecture that is designed to capture typical fragmentation patterns from electron ionization. We analyze the effects of our modeling innovations on library matching performance and compare our models to prior machine-learning-based work on spectrum prediction.

SUBMITTER: Wei JN

PROVIDER: S-EPMC6487538 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Rapid Prediction of Electron-Ionization Mass Spectrometry Using Neural Networks.

Wei Jennifer N JN Belanger David D Adams Ryan P RP Sculley D D

ACS central science 20190319 4

When confronted with a substance of unknown identity, researchers often perform mass spectrometry on the sample and compare the observed spectrum to a library of previously collected spectra to identify the molecule. While popular, this approach will fail to identify molecules that are not in the existing library. In response, we propose to improve the library's coverage by augmenting it with synthetic spectra that are predicted from candidate molecules using machine learning. We contribute a li ...[more]

PMID: 31041390

Similar Datasets

Rapid high mass resolution mass spectrometry using matrix-assisted ionization.

Project description:Matrix-assisted ionization (MAI) is demonstrated to be a robust and sensitive analytical method capable of analyzing proteins such as cholera toxin B-subunit and pertussis toxin mutant from conditions containing relatively high amounts of inorganic salts, buffers, and preservatives without the need for prior sample clean-up or concentration. By circumventing some of the sample preparation steps, MAI simplifies and accelerates the analytical workflow for biological samples in complex media. The benefits of multiply charged ions characteristic of electrospray ionization (ESI) and the robustness of matrix-assisted laser desorption/ionization (MALDI) can be obtained from a single method, making it well suited for analysis of proteins and other biomolecules at ultra-high resolution as demonstrated on an Orbitrap Fusion where protein subunits were resolved for which MALDI-time-of-flight failed. MAI results are compared with those obtained with ESI, MALDI, and laserspray ionization methods and fundamental commonalities discussed.

| S-EPMC4930895 | biostudies-literature

Retention time prediction using neural networks increases identifications in crosslinking mass spectrometry.

Project description:Crosslinking mass spectrometry has developed into a robust technique that is increasingly used to investigate the interactomes of organelles and cells. However, the incomplete and noisy information in the mass spectra of crosslinked peptides limits the numbers of protein-protein interactions that can be confidently identified. Here, we leverage chromatographic retention time information to aid the identification of crosslinked peptides from mass spectra. Our Siamese machine learning model xiRT achieves highly accurate retention time predictions of crosslinked peptides in a multi-dimensional separation of crosslinked E. coli lysate. Importantly, supplementing the search engine score with retention time features leads to a substantial increase in protein-protein interactions without affecting confidence. This approach is not limited to cell lysates and multi-dimensional separation but also improves considerably the analysis of crosslinked multiprotein complexes with a single chromatographic dimension. Retention times are a powerful complement to mass spectrometric information to increase the sensitivity of crosslinking mass spectrometry analyses.

| S-EPMC8163845 | biostudies-literature

Rapid Quantification of Low-Viscosity Acetyl-Triacylglycerols Using Electrospray Ionization Mass Spectrometry.

Project description:Acetyl-triacylglycerols (acetyl-TAG) possess an sn-3 acetate group, which confers useful chemical and physical properties to these unusual triacylglycerols (TAG). Current methods for quantification of acetyl-TAG are time consuming and do not provide any information on the molecular species profile. Electrospray ionization mass spectrometry (ESI-MS)-based methods can overcome these drawbacks. However, the ESI-MS signal intensity for TAG depends on the aliphatic chain length and unsaturation index of the molecule. Therefore response factors for different molecular species need to be determined before any quantification. The effects of the chain length and the number of double-bonds of the sn-1/2 acyl groups on the signal intensity for the neutral loss of short chain length sn-3 groups were quantified using a series of synthesized sn-3 specific structured TAG. The signal intensity for the neutral loss of the sn-3 acyl group was found to negatively correlated with the aliphatic chain length and unsaturation index of the sn-1/2 acyl groups. The signal intensity of the neutral loss of the sn-3 acyl group was also negatively correlated with the size of that chain. Further, the position of the group undergoing neutral loss was also important, with the signal from an sn-2 acyl group much lower than that from one located at sn-3. Response factors obtained from these analyses were used to develop a method for the absolute quantification of acetyl-TAG. The increased sensitivity of this ESI-MS-based approach allowed successful quantification of acetyl-TAG in various biological settings, including the products of in vitro enzyme activity assays.

| S-EPMC5890426 | biostudies-literature

Rapid identification of emerging infectious agents using PCR and electrospray ionization mass spectrometry.

Project description:Newly emergent infectious diseases are a global public health problem. The population dense regions of Southeast Asia are the epicenter of many emerging diseases, as evidenced by the outbreak of Nipah, SARS, avian influenza (H5N1), Dengue, and enterovirus 71 in this region in the past decade. Rapid identification, epidemiologic surveillance, and mitigation of transmission are major challenges in ensuring public health safety. Here we describe a powerful new approach for infectious disease surveillance that is based on polymerase chain reaction (PCR) to amplify nucleic acid targets from large groupings of organisms, electrospray ionization mass spectrometry (ESI-MS) for accurate mass measurements of the PCR products, and base composition signature analysis to identify organisms in a sample. This approach is capable of automated analysis of more than 1,500 PCR reactions a day. It is applicable to the surveillance of bacterial, viral, fungal, or protozoal pathogens and will facilitate rapid characterization of known and emerging pathogens.

| S-EPMC7167958 | biostudies-literature

Identification of Bacillus anthracis by using matrix-assisted laser desorption ionization-time of flight mass spectrometry and artificial neural networks.

Project description:This report demonstrates the applicability of a combination of matrix-assisted laser desorption ionization-time of flight (MALDI-TOF) mass spectrometry (MS) and chemometrics for rapid and reliable identification of vegetative cells of the causative agent of anthrax, Bacillus anthracis. Bacillus cultures were prepared under standardized conditions and inactivated according to a recently developed MS-compatible inactivation protocol for highly pathogenic microorganisms. MALDI-TOF MS was then employed to collect spectra from the microbial samples and to build up a database of bacterial reference spectra. This database comprised mass peak profiles of 374 strains from Bacillus and related genera, among them 102 strains of B. anthracis and 121 strains of B. cereus. The information contained in the database was investigated by means of visual inspection of gel view representations, univariate t tests for biomarker identification, unsupervised hierarchical clustering, and artificial neural networks (ANNs). Analysis of gel views and independent t tests suggested B. anthracis- and B. cereus group-specific signals. For example, mass spectra of B. anthracis exhibited discriminating biomarkers at 4,606, 5,413, and 6,679 Da. A systematic search in proteomic databases allowed tentative assignment of some of the biomarkers to ribosomal protein or small acid-soluble proteins. Multivariate pattern analysis by unsupervised hierarchical cluster analysis further revealed a subproteome-based taxonomy of the genus Bacillus. Superior classification accuracy was achieved when supervised ANNs were employed. For the identification of B. anthracis, independent validation of optimized ANN models yielded a diagnostic sensitivity of 100% and a specificity of 100%.

| S-EPMC2786504 | biostudies-literature

Structural characterization of wax esters by electron ionization mass spectrometry.

Project description:The interpretation of the electron ionization mass spectra of straight-chain and methyl-branched saturated and unsaturated wax esters (WEs) is discussed in this study based on the spectra of 154 standards. The most important fragments indicative of the structure of the acid and alcohol chains are identified and summarized for WEs with various number of double bonds in the chains. Briefly, most WEs provide acylium ions allowing structural characterization of the acid part, whereas the alcohol part gives corresponding alkyl radical cations. The elemental composition of selected important fragments is established from a high-resolution accurate mass analysis. The ion abundances are discussed with respect to the length and unsaturation of the aliphatic chains. The interpretation of the spectra of branched or unsaturated WEs requires the recognition of small but important peaks that are difficult to discern among the other fragments. We demonstrate that such fragments are easily detected in differential mass spectra. This approach requires spectra of WE standards (e.g., straight-chain analogs in the case of branched WEs) recorded under the same experimental conditions. The WEs mass spectral database provided in the supplemental data can be used as a reference for the analysis of the GC/EI-MS data.

| S-EPMC3243477 | biostudies-literature

ARISTO: ontological classification of small molecules by electron ionization-mass spectrometry.

Project description:Gas chromatography-mass spectrometry (GC-MS) acquisitions routinely yield hundreds to thousands of Electron Ionization (EI) mass spectra. The chemical identification of these spectra typically involves a search protocol that seeks an exact match to a reference spectrum. Reference spectra are found in comprehensive libraries of small molecule EI spectra curated by commercial and public entities. We developed ARISTO (Automatic Reduction of Ion Spectra To Ontology), a webtool, which provides information regarding the general chemical nature of the compound underlying an input EI mass spectrum. Importantly, ARISTO can provide such annotation without necessitating an exact match to a specific compound. ARISTO provides assignments to a subset of the ChEBI (Chemical Entities of Biological Interest) dictionary, an ontology, which aims to cover biologically relevant small molecules. Our system takes as input a mass spectrum represented as a series of mass and intensity pairs; the system returns a graphical representation of the supported ontology as well as a detailed table of suggested annotations along with their associated statistical evidence. ARISTO is accessible at this URL: http://www.ionspectra.org/aristo. The system is free, open to all and does not require registration of any sort.

| S-EPMC3125788 | biostudies-literature

Peak learning of mass spectrometry imaging data using artificial neural networks.

Project description:Mass spectrometry imaging (MSI) is an emerging technology that holds potential for improving, biomarker discovery, metabolomics research, pharmaceutical applications and clinical diagnosis. Despite many solutions being developed, the large data size and high dimensional nature of MSI, especially 3D datasets, still pose computational and memory complexities that hinder accurate identification of biologically relevant molecular patterns. Moreover, the subjectivity in the selection of parameters for conventional pre-processing approaches can lead to bias. Therefore, we assess if a probabilistic generative model based on a fully connected variational autoencoder can be used for unsupervised analysis and peak learning of MSI data to uncover hidden structures. The resulting msiPL method learns and visualizes the underlying non-linear spectral manifold, revealing biologically relevant clusters of tissue anatomy in a mouse kidney and tumor heterogeneity in human prostatectomy tissue, colorectal carcinoma, and glioblastoma mouse model, with identification of underlying m/z peaks. The method is applied for the analysis of MSI datasets ranging from 3.3 to 78.9 GB, without prior pre-processing and peak picking, and acquired using different mass spectrometers at different centers.

| S-EPMC8452737 | biostudies-literature

Rapid prediction of protein natural frequencies using graph neural networks.

Project description:Natural vibrational frequencies of proteins help to correlate functional shifts with sequence or geometric variations that lead to negligible changes in protein structures, such as point mutations related to disease lethality or medication effectiveness. Normal mode analysis is a well-known approach to accurately obtain protein natural frequencies. However, it is not feasible when high-resolution protein structures are not available or time consuming to obtain. Here we provide a machine learning model to directly predict protein frequencies from primary amino acid sequences and low-resolution structural features such as contact or distance maps. We utilize a graph neural network called principal neighborhood aggregation, trained with the structural graphs and normal mode frequencies of more than 34 000 proteins from the protein data bank. combining with existing contact/distance map prediction tools, this approach enables an end-to-end prediction of the frequency spectrum of a protein given its primary sequence.

| S-EPMC9189858 | biostudies-literature

"Magic" Ionization Mass Spectrometry.

Project description:The systematic study of the temperature and pressure dependence of matrix-assisted ionization (MAI) led us to the discovery of the seemingly impossible, initially explained by some reviewers as either sleight of hand or the misinterpretation by an overzealous young scientist of results reported many years before and having little utility. The “magic” that we were attempting to report was that with matrix assistance, molecules, at least as large as bovine serum albumin (66 kDa), are lifted into the gas phase as multiply charged ions simply by exposure of the matrix:analyte sample to the vacuum of a mass spectrometer. Applied heat, a laser, or voltages are not necessary to achieve charge states and ion abundances only previously observed with electrospray ionization (ESI). The fundamentals of how solid phase volatile or nonvolatile compounds are converted to gas-phase ions without added energy currently involves speculation providing a great opportunity to rethink mechanistic understanding of ionization processes used in mass spectrometry. Improved understanding of the mechanism(s) of these processes and their connection to ESI and matrix-assisted laser desorption/ionization may provide opportunities to further develop new ionization strategies for traditional and yet unforeseen applications of mass spectrometry. This Critical Insights article covers developments leading to the discovery of a seemingly magic ionization process that is simple to use, fast, sensitive, robust, and can be directly applied to surface characterization using portable or high performance mass spectrometers.

| S-EPMC4686549 | biostudies-other

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data