Desktop iDMS: A stand-alone application of intelligent differential mobility spectrometry (iDMS), a neural network that predicts optimal separation and compensation voltages for field asymmetric differential ion mobility spectrometry
Preprint
Abstract
Summary: Mass spectrometry resolution of glycosphingolipids requires advanced separation methods. The virtually identical structures of glycolipid epimers cannot be discriminated by routine multiple reaction monitoring-high-performance liquid chromatography-electrospray ionization-tandem mass spectrometry (MRM-LC-ESI-MS/MS). Separation can be achieved using field asymmetric (differential) ion mobility mass spectrometry (FAIMS/DMS). A major bottleneck to MRM-LC-ESI-DMS-MS/MS method development lies in manually optimizing the compound-dependent parameters of separation voltage (SV) and compensation voltage (CoV). To address this challenge, we developed intelligent Differential Mobility Spectrometry (iDMS). iDMS is a supervised deep neural network that evaluates and predicts the optimal ion mobility SV and CoV parameters for any user-requested monoglycosphingolipid from a training set of measured signal intensities composed of 12 lipids (6 stereoisomer pairs). We initially introduced iDMS as a series of python scripts. Here, we share desktop applications of both iDMS and its pre-processing input data assembly modules (DMS Data Extraction Toolkit). Both software assemblies enable users to rapidly deploy a validated machine learning alternative to manual DMS optimization. The applications are user-friendly, operate without need for any technical operating environment, make training dataset assembly quick and simple, and return measured, normalized, and predicted ionograms at every user-interrogated SV, evaluation of separability at each SV and CoV combination, and prediction of optimal resolution parameters to accelerate users’ MRM-LC-ESI-DMS-MS/MS deployment. Availability and implementation: Desktop iDMS and DMS Data Extraction Toolkit are native desktop applications for macOS (Apple Silicon), freely available for download at https://www.neurolipidomics.com/platforms.html under the GNU v3.0 license. The source code is available from GitHub and Zenodo at https://github.com/Neurolipidomics/iDMS , https://zenodo.org/records/22214408 , https://github.com/Neurolipidomics/DMSDataExtractionToolkit , and https://ze-nodo.org/records/22777403 . Benchmarking metrics are available at https://www.biorxiv.org/content/10.64898/2026.08.26.747394v1 . Contact: ldomic@uottawa.ca Supplementary Information: Supplementary material is available at Bioinformatics online.Keywords
Funding Information
- Silverstein Foundation for Parkinson’s with GBA
This publication has 8 references indexed in Scilit:
- Intelligent differential ion mobility spectrometry (iDMS): A deep neural network that predicts optimal space-resolved ion mobility parameters for isomeric monoglycosphingolipidsbioRxiv, 2026
- Parkinson’s disease variant detection and disclosure: PD GENEration, a North American studyBrain, 2024
- Assessment of Glucocerebrosidase Enzyme Activity in Parkinson Disease Using Multiple ApproachesMovement Disorders, 2022
- Evaluation of Strategies for Measuring Lysosomal Glucocerebrosidase ActivityMovement Disorders, 2021
- Glucocerebrosidases catalyze a transgalactosylation reaction that yields a newly-identified brain sterol metabolite, galactosylated cholesterolJournal of Biological Chemistry, 2020
- DMS as an orthogonal separation to LC/ESI/MS/MS for quantifying isomeric cerebrosides in plasma and cerebrospinal fluidJournal of Lipid Research, 2019
- Insights into Krabbe disease from structures of galactocerebrosidaseProceedings of the National Academy of Sciences, 2011
- Gaucher disease: mutation and polymorphism spectrum in the glucocerebrosidase gene (GBA)Human Mutation, 2008