Probabilistic cell-type assignment of single-cell RNA-seq for tumor microenvironment profiling

By Allen W. Zhang, C. O’Flanagan, E. Chavez, J. Lim, N. Ceglia, Andrew W. McPherson, M. Wiens, Pascale Walters, Tim Chan, Brittany Hewitson and 12 more. Nature Methods, 2019

317 citations recorded by the source corpus.

Single-cell RNA sequencing has enabled the decomposition of complex tissues into functionally distinct cell types. Often, investigators wish to assign cells to cell types through unsupervised clustering followed by manual annotation or via ‘mapping’ to existing data. However, manual interpretation scales poorly to large datasets, mapping approaches require purified or pre-annotated data and both are prone to batch effects. To overcome these issues, we present CellAssign, a probabilistic model that leverages prior knowledge of cell-type marker genes to annotate single-cell RNA sequencing data into predefined or de novo cell types. CellAssign automates the process of assigning cells in a highly scalable manner across large datasets while controlling for batch and sample effects. We demonstrate the advantages of CellAssign through extensive simulations and analysis of tumor microenvironment composition in high-grade serous ovarian cancer and follicular lymphoma. CellAssign uses a probabilistic model to assign single cells to a given cell type defined by known marker genes, enabling automated annotation of cell types present in a tumor microenvironment.

Subfields: Cancer Research, Molecular Biology, Oncology

View Paper: https://www.semanticscholar.org/paper/48a840fa3840745a7562814f0e0dfe3700f484de

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cancer Research

1. Aleksandr Ianevski
2. Anil K. Giri
3. Tero Aittokallio

In Molecular Biology

1. Aleksandr Ianevski
2. Anil K. Giri
3. Tero Aittokallio
4. Jacques Colinge
5. Sameer Quazi

In Oncology

1. Tero Aittokallio

Citations in the corpus

• Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data (2022, methodology): “…study, by segregating them into immature B-cell and plasma (B) cell types (lower UMAP plot of panel ( d ). that was recently shown to outperform several popular tools such as Garnett 31 and CellAssign 32 ), (ii) fastest running time (SCINA 33 ), and (iii) full-automated process (scCATCH 34 ).”
• scDeepSort: a pre-trained cell-type annotation method for single-cell transcriptomics using deep learning with a weighted graph neural network (2021, methodology): “Although CellAssign, scmap, scID and SCINA performed worse than other methods across 265 489 cells, it’s worth to point out that they exhibited significant performance on some individual test datasets.”
• SingleCellSignalR: inference of intercellular networks from single-cell transcriptomics (2019, methodology): “users to apply advanced data normalization, clustering, and cell type calling tools (12, 34), and to submit preprocessed count matrices to SingleCellSignalR to perform LR interaction inference and visualization.”