Alignment of spatial genomics data using deep Gaussian processes. Jones, A., Townes, F. W., Li, D., & Engelhardt, B. E. Nature Methods, 20(9):1379–1387, September, 2023. Number: 9 Publisher: Nature Publishing Group
Alignment of spatial genomics data using deep Gaussian processes [link]Paper  doi  abstract   bibtex   
Spatially resolved genomic technologies have allowed us to study the physical organization of cells and tissues, and promise an understanding of local interactions between cells. However, it remains difficult to precisely align spatial observations across slices, samples, scales, individuals and technologies. Here, we propose a probabilistic model that aligns spatially-resolved samples onto a known or unknown common coordinate system (CCS) with respect to phenotypic readouts (for example, gene expression). Our method, Gaussian Process Spatial Alignment (GPSA), consists of a two-layer Gaussian process: the first layer maps observed samples’ spatial locations onto a CCS, and the second layer maps from the CCS to the observed readouts. Our approach enables complex downstream spatially aware analyses that are impossible or inaccurate with unaligned data, including an analysis of variance, creation of a dense three-dimensional (3D) atlas from sparse two-dimensional (2D) slices or association tests across data modalities.
@article{jones_alignment_2023,
	title = {Alignment of spatial genomics data using deep {Gaussian} processes},
	volume = {20},
	copyright = {2023 The Author(s)},
	issn = {1548-7105},
	url = {https://www.nature.com/articles/s41592-023-01972-2},
	doi = {10.1038/s41592-023-01972-2},
	abstract = {Spatially resolved genomic technologies have allowed us to study the physical organization of cells and tissues, and promise an understanding of local interactions between cells. However, it remains difficult to precisely align spatial observations across slices, samples, scales, individuals and technologies. Here, we propose a probabilistic model that aligns spatially-resolved samples onto a known or unknown common coordinate system (CCS) with respect to phenotypic readouts (for example, gene expression). Our method, Gaussian Process Spatial Alignment (GPSA), consists of a two-layer Gaussian process: the first layer maps observed samples’ spatial locations onto a CCS, and the second layer maps from the CCS to the observed readouts. Our approach enables complex downstream spatially aware analyses that are impossible or inaccurate with unaligned data, including an analysis of variance, creation of a dense three-dimensional (3D) atlas from sparse two-dimensional (2D) slices or association tests across data modalities.},
	language = {en},
	number = {9},
	urldate = {2023-11-07},
	journal = {Nature Methods},
	author = {Jones, Andrew and Townes, F. William and Li, Didong and Engelhardt, Barbara E.},
	month = sep,
	year = {2023},
	note = {Number: 9
Publisher: Nature Publishing Group},
	keywords = {Image processing, Machine learning, Software, Statistical methods, Transcriptomics},
	pages = {1379--1387},
}

Downloads: 0