Automated Cell Type Annotation with Reference Cluster Mapping
Galanti, V.; Shi, L.; Azizi, E.; Liu, Y.; Blumberg, A. J.
Show abstract
Single-cell RNA sequencing has transformed the field of cellular biology by providing unprecedented insights into cellular heterogeneity. However, characterizing scRNA-seq datasets remains a significant challenge. We introduce RefCM, a novel computational method that combines optimal transport and integer programming to enhance the annotation of scRNA clusters using established reference datasets. Our method produces highly accurate cross-technology, cross-tissue, and cross-species mappings while remaining tractable at atlas scale, outperforming existing methods across all these tasks. By providing precise annotations, RefCM can enable the discovery of new cell types, states, and relationships in single-cell transcriptomic data.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Metric learning enables synthesis of heterogeneous single-cell modalities 97%
- Enhancement of network architecture alignment in comparative single-cell studies 97%
- scDesign2: a transparent simulator that generates high-fidelity single-cell gene expression count data with gene correlations captured 97%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.