bioRxiv (Cold Spring Harbor Laboratory) · 2023 · 11 citations · 13 references
Life SciencesBiochemistryBioinformaticsMachine LearningMass Spectrometric AnalysisMetabolomicsMass Spectrometry-based MetabolomicsMetabolite AnnotationMetabolite IdentificationMetabolite ProfilingMetabolomics Data AnalysisSpatial MetabolomicsComputational Metabolite AnnotationData-driven Metabolite AnnotationFalse Discovery RateFalse Discovery Rate EstimationMetabolite Feature AnnotationMetabolome AnnotationMetabolomics Data ProcessingPrecision
Abstract Imaging mass spectrometry is a powerful technology enabling spatial metabolomics, yet metabolites can be assigned only to a fraction of the data generated. METASPACE-ML is a machine learning-based approach addressing this challenge which incorporates new scores and computationally-efficient False Discovery Rate estimation. For training and evaluation, we use a comprehensive set of 1,710 datasets from 159 researchers from 47 labs encompassing both animal and plant-based datasets representing multiple spatial metabolomics contexts derived from the METASPACE knowledge base. Here we show that, METASPACE-ML outperforms its rule-based predecessor, exhibiting higher precision, increased throughput, and enhanced capability in identifying low-intensity and biologically-relevant metabolites.
13
From local explanations to global understanding with explainable AI for trees
Scott Lundberg, Gabriel Erion, Hugh Chen et al. · Nature Machine Intelligence · 2020 · 8.9K citations · Full text
MS-DIAL: data-independent MS/MS deconvolution for comprehensive metabolome analysis
Hiroshi Tsugawa, Tomáš Čajka, Tobias Kind et al. · Nature Methods · 2015 · 3.4K citations · Full text
Life Sciences, Biochemistry, Mass Spectrometric Analysis +13
Zuguang Gu · iMeta · 2022 · 1.8K citations · Full text