MSI-ATLAS: Mass spectrometry imaging and explainable machine learning uncover the brain's lipid landscapes

Abstract

Recent computational advances in mass spectrometry imaging (MSI) now enable unprecedented insight into organ-wide molecular composition and functional architecture. Here, we present the first high-resolution molecular-computational atlas of specific mouse brain lipids and metabolites, acquired using a NEDC matrix and negative-mode MSI, covering 123 anatomically defined regions and 191 polygonal annotations derived solely from MSI data, without auxiliary imaging. To over-come annotation ambiguity and MSI complexity, we introduced the Computational Brain Lipid Atlas (CBLA), a graph-based visual-explainability framework that generates Virtual Landscape Visualizations (VLVs) of specific lipid distributions across brain substructures. The CBLA integrates dimensionality reduction and ensembles of supervised models to (i) refine annotations, (ii) elucidate interregional relationships, (iii) interpret model behavior, and (iv) formulate biologically testable hypotheses. The CBLA revealed novel lipid distribution patterns, functional integrations, anatomical connections - the brains telephone cables, and region-specific disease signatures - index lipids, including disease networks in the basal ganglia. It further identified index lipids that trace extrapyramidal nuclei and their cortical-brainstem connections, highlighting network-level molecular organization. A new algorithm decomposes annotated regions into precise m/z features and resolves high-resolution m/z values from MSI data, producing a comprehensive high-resolution brain map. It can be applied to any MS measurements, including metabolites, lipids, and peptides. This resource underpins down-stream studies, as exemplified here by characterizing the molecular lipid composition of A{beta} plaques, their spatial arrangement, and their connections with surrounding tissue. For the first time, our data suggest that GM3 accumulation in cortical amyloid plaques may originate from hippocampal structures, consistent with longstanding evidence of disrupted hippocampocortical connectivity; a similar origin may also apply to plaque-associated A{beta} signals in the cortex. More broadly, several selected m/z signals showed putative anatomical origins in specific brain subregions. HighlightsO_LIMass spectrometry imaging (MSI) data were used to generate high-resolution, truthful visualizations for brain-region annotation without additional modalities. C_LIO_LIMSI data were further used to build a computational atlas of annotated brain regions. C_LIO_LIPathological structures reveal both their origins and effects on specific brain networks. C_LIO_LIAnatomical regions and functional networks exhibit distinct lipid/metabolite patterns. C_LIO_LIBrainstem nuclei and white matter exhibit distinct lipid/metabolite compositions, indicating their involvement in pathological networks. C_LIO_LIAtlas-based Virtual Landscape Visualizations (VLVs) enable comparison of region-specific differences across mouse models. C_LIO_LISeveral plaque-associated m/z signals, including GM3-related species, show putative hippocampocortical anatomical origins. C_LIO_LIExtrapyramidal nuclei and their cortical-brainstem connections are characterized by shared index lipids, enabling network-level molecular tracing. C_LI