Capitalizing on the differences of prediction between multiple scRNA-seq clustering methods.
<p dir="ltr">Single-cell RNA-sequencing measures individual cell transcriptomes in a tissue. In the past decade, that technology has motivated the development of hundreds of clustering methods. These methods attempt to group cells into populations by leveraging the similarity of thei...
Saved in:
| Main Author: | |
|---|---|
| Published: |
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | <p dir="ltr">Single-cell RNA-sequencing measures individual cell transcriptomes in a tissue. In the past decade, that technology has motivated the development of hundreds of clustering methods. These methods attempt to group cells into populations by leveraging the similarity of their transcriptomes. Because each method relies on specific hypotheses, their predictions can vary drastically. To address that issue, ensemble algorithms detect cell populations by integrating multiple clustering methods, and minimizing the differences of their predictions. While that approach is sensible, it has yet to address some conceptual challenges in single-cell data science; namely, ensemble algorithms have yet to generate clustering results with uncertainty values and multiple resolutions. In this work, we present an original approach to ensemble clustering that addresses these challenges; by describing the differences between clustering results, instead of minimizing them. We present our algorithm scEVE, and we evaluate it on 15 experimental and up to 600 synthetic datasets. Our results reveal that scEVE performs decently, and is the first scRNA-seq ensemble algorithm to address both challenges. They also highlight how biological downstream analyses benefit from addressing these challenges. Overall, we expect that our work will provide an alternative direction for developing single-cell ensemble clustering algorithms.</p> |
|---|