Journal article
Integrative spatial analysis of cell morphologies and transcriptional states with MUSE
Nature biotechnology, Vol.40(8), pp.1200-1209
08/01/2022
DOI: 10.1038/s41587-022-01251-z
PMID: 35347329
Abstract
Deep learning analysis of microscopy and spatial transcriptomics data characterizes cell types and states.
Spatial transcriptomics enables the simultaneous measurement of morphological features and transcriptional profiles of the same cells or regions in tissues. Here we present multi-modal structured embedding (MUSE), an approach to characterize cells and tissue regions by integrating morphological and spatially resolved transcriptional data. We demonstrate that MUSE can discover tissue subpopulations missed by either modality as well as compensate for modality-specific noise. We apply MUSE to diverse datasets containing spatial transcriptomics (seqFISH+, STARmap or Visium) and imaging (hematoxylin and eosin or fluorescence microscopy) modalities. MUSE identified biologically meaningful tissue subpopulations and stereotyped spatial patterning in healthy brain cortex and intestinal tissues. In diseased tissues, MUSE revealed gene biomarkers for proximity to tumor region and heterogeneity of amyloid precursor protein processing across Alzheimer brain regions. MUSE enables the integration of multi-modal data to provide insights into the states, functions and organization of cells in complex biological tissues.
Details
- Title: Subtitle
- Integrative spatial analysis of cell morphologies and transcriptional states with MUSE
- Creators
- Feng Bao - University of California, San FranciscoYue Deng - Beihang UniversitySen Wan - Tsinghua UniversitySusan Q. Shen - University of California, San FranciscoBo Wang - Beihang UniversityQionghai Dai - Tsinghua UniversitySteven J. Altschuler - University of California, San FranciscoLani F. Wu - University of California, San Francisco
- Resource Type
- Journal article
- Publication Details
- Nature biotechnology, Vol.40(8), pp.1200-1209
- DOI
- 10.1038/s41587-022-01251-z
- PMID
- 35347329
- NLM abbreviation
- Nat Biotechnol
- ISSN
- 1087-0156
- eISSN
- 1546-1696
- Publisher
- NATURE PORTFOLIO
- Number of pages
- 25
- Grant note
- 62088102; 61971020; 62031001 / NSFC; National Natural Science Foundation of China (NSFC) ProjectALS UCSF Program for Breakthrough Biomedical Research 2020AA0105500; 2020AAA0105502 / MOST CZI NDNC Challenge Network; Chan Zuckerberg Initiative (CZI)
- Language
- English
- Date published
- 08/01/2022
- Academic Unit
- Psychiatry; Iowa Neuroscience Institute
- Record Identifier
- 9984618650802771
Metrics
11 Record Views