Our study introduces conditional autoencoder for multiplexed pixel analysis (CAMPA), a deep-learning framework that uses highly multiplexed imaging to identify consistent subcellular landmarks across heterogeneous cell populations and experimental perturbations. Generating interpretable cellular phenotypes revealed links between subcellular organization and perturbations of RNA production, RNA processing and cell size.
References
Moffitt, J. R., Lundberg, E. & Heyn, H. The emerging landscape of spatial profiling technologies. Nat. Rev. Genet. 23, 741–759 (2022). This review article discusses spatial omics technologies.
Takei, Y. et al. Integrated spatial genomics reveals global architecture of single nuclei. Nature 590, 344–350 (2021). This paper presents an existing method for analyzing subcellular organization using multiplexed imaging.
Gut, G., Herrmann, M. D. & Pelkmans, L. Multiplexed protein maps link subcellular organization to cellular states. Science 361, (2018). This paper introduces the 4i imaging technique.
Lopez, R., Regier, J., Cole, M. B., Jordan, M. I. & Yosef, N. Deep generative modeling for single-cell transcriptomics. Nat. Methods 15, 1053–1058 (2018). This paper proposes the use of conditional variational autoencoders on single-cell transcriptomics data.
Lotfollahi, M. et al. Mapping single-cell data to reference atlases by transfer learning. Nat. Biotechnol. 40, 121–130 (2022). This paper introduces ‘architecture surgery’ for mapping new single-cell datasets to an existing reference atlas.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Spitzer, H., Berry, S., Donoghoe, M., Pelkmans, L. & Theis, F. J. Learning consistent subcellular landmarks to quantify changes in multiplexed protein maps. Nat. Methods https://doi.org/10.1038/s41592-023-01894-z (2023).
Rights and permissions
About this article
Cite this article
Deciphering subcellular organization with multiplexed imaging and deep learning. Nat Methods 20, 995–996 (2023). https://doi.org/10.1038/s41592-023-01895-y
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41592-023-01895-y
- Springer Nature America, Inc.