Introduction

Cell annotation aims to accurately classify cells and determine their biological identity (such as cell type, state, or subtype) by analyzing single-cell gene expression profiles. This helps interpret the biological significance of the data, reveal the cellular composition and functional heterogeneity of tissues or samples, and provides a classification basis for various downstream analyses, including cellular neighborhood analysis, CNV Analysis, cell communication analysis，trajectory analysis，cell-type spatial relationship analysis，differential gene analysis and transcription factor analysis.

Algorithm recommendation

• If you want to obtain results quickly, it is recommended to first try using Tangram or RCTD. For human samples without single-cell references, you can also try SCimilarity first. If you need more accurate annotation results and have GPU resources, it is recommended to use cell2location. For detailed algorithm evaluation information, please refer to this website.

Algorithm	Performance	Memory	Time	GPU Acceleration
cell2location	⭐⭐⭐⭐⭐	⭐⭐	⭐	Extremely slow without GPU
RCTD	⭐⭐⭐⭐ (excluding unannotated cells)	⭐⭐⭐	⭐⭐⭐
Tangram	⭐⭐⭐	⭐⭐⭐⭐	⭐⭐⭐⭐	Fast on CPU, GPU acceleration available
SPOTlight	⭐⭐	⭐	⭐⭐
SCimilarity	⭐	⭐⭐⭐⭐⭐	⭐⭐⭐⭐⭐	Very fast on CPU. GPU acceleration available, but not significantly effective

Module overview

Reference

• Biancalani, T., Scalia, G., Buffoni, L., Avasthi, R., Lu, Z., Sanger, A., ... & Regev, A. (2021). Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram. Nature methods, 18(11), 1352-1362.

• Cable, D. M., Murray, E., Zou, L. S., Goeva, A., Macosko, E. Z., Chen, F., & Irizarry, R. A. (2022). Robust decomposition of cell type mixtures in spatial transcriptomics. Nature biotechnology, 40(4), 517-526.

• Elosua-Bayes, M., Nieto, P., Mereu, E., Gut, I., & Heyn, H. (2021). SPOTlight: seeded NMF regression to deconvolute spatial transcriptomics spots with single-cell transcriptomes. Nucleic acids research, 49(9), e50-e50.

• Heimberg, G., Kuo, T., DePianto, D. J., Salem, O., Heigl, T., Diamant, N., ... & Regev, A. (2025). A cell atlas foundation model for scalable search of similar human cells. Nature, 638(8052), 1085-1094.

• Kleshchevnikov, V., Shmatko, A., Dann, E., Aivazidis, A., King, H. W., Li, T., ... & Bayraktar, O. A. (2022). Cell2location maps fine-grained cell types in spatial transcriptomics. Nature biotechnology, 40(5), 661-671.