Segmentation aware probabilistic phenotyping of single-cell spatial protein expression data
Abstract Spatial protein expression technologies can map cellular content and organization by simultaneously quantifying the expression of >40 proteins at subcellular resolution within intact tissue sections and cell lines. However, necessary image segmentation to single cells is challenging and...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55214-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559279742484480 |
|---|---|
| author | Yuju Lee Edward L. Y. Chen Darren C. H. Chan Anuroopa Dinesh Somaieh Afiuni-Zadeh Conor Klamann Alina Selega Miralem Mrkonjic Hartland W. Jackson Kieran R. Campbell |
| author_facet | Yuju Lee Edward L. Y. Chen Darren C. H. Chan Anuroopa Dinesh Somaieh Afiuni-Zadeh Conor Klamann Alina Selega Miralem Mrkonjic Hartland W. Jackson Kieran R. Campbell |
| author_sort | Yuju Lee |
| collection | DOAJ |
| description | Abstract Spatial protein expression technologies can map cellular content and organization by simultaneously quantifying the expression of >40 proteins at subcellular resolution within intact tissue sections and cell lines. However, necessary image segmentation to single cells is challenging and error prone, easily confounding the interpretation of cellular phenotypes and cell clusters. To address these limitations, we present STARLING, a probabilistic machine learning model designed to quantify cell populations from spatial protein expression data while accounting for segmentation errors. To evaluate performance, we develop a comprehensive benchmarking workflow by generating highly multiplexed imaging data of cell line pellet standards with controlled cell content and marker expression and additionally established a score to quantify the biological plausibility of discovered cellular phenotypes on patient-derived tissue sections. Moreover, we generate spatial expression data of the human tonsil—a densely packed tissue prone to segmentation errors—and demonstrate cellular states captured by STARLING identify known cell types not visible with other methods and enable quantification of intra- and inter- individual heterogeneity. |
| format | Article |
| id | doaj-art-51cd0cf1bb234926afde30fc379deeff |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-51cd0cf1bb234926afde30fc379deeff2025-01-05T12:38:17ZengNature PortfolioNature Communications2041-17232025-01-0116111410.1038/s41467-024-55214-wSegmentation aware probabilistic phenotyping of single-cell spatial protein expression dataYuju Lee0Edward L. Y. Chen1Darren C. H. Chan2Anuroopa Dinesh3Somaieh Afiuni-Zadeh4Conor Klamann5Alina Selega6Miralem Mrkonjic7Hartland W. Jackson8Kieran R. Campbell9Lunenfeld-Tanenbaum Research Institute, Sinai Health SystemLunenfeld-Tanenbaum Research Institute, Sinai Health SystemLunenfeld-Tanenbaum Research Institute, Sinai Health SystemLunenfeld-Tanenbaum Research Institute, Sinai Health SystemLunenfeld-Tanenbaum Research Institute, Sinai Health SystemData Sciences Institute, University of TorontoLunenfeld-Tanenbaum Research Institute, Sinai Health SystemDepartment of Laboratory Medicine & Pathobiology, University of TorontoLunenfeld-Tanenbaum Research Institute, Sinai Health SystemLunenfeld-Tanenbaum Research Institute, Sinai Health SystemAbstract Spatial protein expression technologies can map cellular content and organization by simultaneously quantifying the expression of >40 proteins at subcellular resolution within intact tissue sections and cell lines. However, necessary image segmentation to single cells is challenging and error prone, easily confounding the interpretation of cellular phenotypes and cell clusters. To address these limitations, we present STARLING, a probabilistic machine learning model designed to quantify cell populations from spatial protein expression data while accounting for segmentation errors. To evaluate performance, we develop a comprehensive benchmarking workflow by generating highly multiplexed imaging data of cell line pellet standards with controlled cell content and marker expression and additionally established a score to quantify the biological plausibility of discovered cellular phenotypes on patient-derived tissue sections. Moreover, we generate spatial expression data of the human tonsil—a densely packed tissue prone to segmentation errors—and demonstrate cellular states captured by STARLING identify known cell types not visible with other methods and enable quantification of intra- and inter- individual heterogeneity.https://doi.org/10.1038/s41467-024-55214-w |
| spellingShingle | Yuju Lee Edward L. Y. Chen Darren C. H. Chan Anuroopa Dinesh Somaieh Afiuni-Zadeh Conor Klamann Alina Selega Miralem Mrkonjic Hartland W. Jackson Kieran R. Campbell Segmentation aware probabilistic phenotyping of single-cell spatial protein expression data Nature Communications |
| title | Segmentation aware probabilistic phenotyping of single-cell spatial protein expression data |
| title_full | Segmentation aware probabilistic phenotyping of single-cell spatial protein expression data |
| title_fullStr | Segmentation aware probabilistic phenotyping of single-cell spatial protein expression data |
| title_full_unstemmed | Segmentation aware probabilistic phenotyping of single-cell spatial protein expression data |
| title_short | Segmentation aware probabilistic phenotyping of single-cell spatial protein expression data |
| title_sort | segmentation aware probabilistic phenotyping of single cell spatial protein expression data |
| url | https://doi.org/10.1038/s41467-024-55214-w |
| work_keys_str_mv | AT yujulee segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT edwardlychen segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT darrenchchan segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT anuroopadinesh segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT somaiehafiunizadeh segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT conorklamann segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT alinaselega segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT miralemmrkonjic segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT hartlandwjackson segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata AT kieranrcampbell segmentationawareprobabilisticphenotypingofsinglecellspatialproteinexpressiondata |