Multi-domain translation between single-cell imaging and sequencing data using autoencoders
© 2021, The Author(s). The development of single-cell methods for capturing different data modalities including imaging and sequencing has revolutionized our ability to identify heterogeneous cell states. Different data modalities provide different perspectives on a population of cells, and their in...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2021
|
| Online Access: | https://hdl.handle.net/1721.1/133658 |
| _version_ | 1811096690269093888 |
|---|---|
| author | Yang, Karren Dai Belyaeva, Anastasiya Venkatachalapathy, Saradha Damodaran, Karthik Katcoff, Abigail Radhakrishnan, Adityanarayanan Shivashankar, GV Uhler, Caroline |
| author2 | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems |
| author_facet | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Yang, Karren Dai Belyaeva, Anastasiya Venkatachalapathy, Saradha Damodaran, Karthik Katcoff, Abigail Radhakrishnan, Adityanarayanan Shivashankar, GV Uhler, Caroline |
| author_sort | Yang, Karren Dai |
| collection | MIT |
| description | © 2021, The Author(s). The development of single-cell methods for capturing different data modalities including imaging and sequencing has revolutionized our ability to identify heterogeneous cell states. Different data modalities provide different perspectives on a population of cells, and their integration is critical for studying cellular heterogeneity and its function. While various methods have been proposed to integrate different sequencing data modalities, coupling imaging and sequencing has been an open challenge. We here present an approach for integrating vastly different modalities by learning a probabilistic coupling between the different data modalities using autoencoders to map to a shared latent space. We validate this approach by integrating single-cell RNA-seq and chromatin images to identify distinct subpopulations of human naive CD4+ T-cells that are poised for activation. Collectively, our approach provides a framework to integrate and translate between data modalities that cannot yet be measured within the same cell for diverse applications in biomedical discovery. |
| first_indexed | 2024-09-23T16:47:30Z |
| format | Article |
| id | mit-1721.1/133658 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:47:30Z |
| publishDate | 2021 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1336582023-03-15T20:51:10Z Multi-domain translation between single-cell imaging and sequencing data using autoencoders Yang, Karren Dai Belyaeva, Anastasiya Venkatachalapathy, Saradha Damodaran, Karthik Katcoff, Abigail Radhakrishnan, Adityanarayanan Shivashankar, GV Uhler, Caroline Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Massachusetts Institute of Technology. Institute for Data, Systems, and Society Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science © 2021, The Author(s). The development of single-cell methods for capturing different data modalities including imaging and sequencing has revolutionized our ability to identify heterogeneous cell states. Different data modalities provide different perspectives on a population of cells, and their integration is critical for studying cellular heterogeneity and its function. While various methods have been proposed to integrate different sequencing data modalities, coupling imaging and sequencing has been an open challenge. We here present an approach for integrating vastly different modalities by learning a probabilistic coupling between the different data modalities using autoencoders to map to a shared latent space. We validate this approach by integrating single-cell RNA-seq and chromatin images to identify distinct subpopulations of human naive CD4+ T-cells that are poised for activation. Collectively, our approach provides a framework to integrate and translate between data modalities that cannot yet be measured within the same cell for diverse applications in biomedical discovery. 2021-10-27T19:54:02Z 2021-10-27T19:54:02Z 2021 2021-01-29T19:39:52Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/133658 en 10.1038/s41467-020-20249-2 Nature Communications Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Nature |
| spellingShingle | Yang, Karren Dai Belyaeva, Anastasiya Venkatachalapathy, Saradha Damodaran, Karthik Katcoff, Abigail Radhakrishnan, Adityanarayanan Shivashankar, GV Uhler, Caroline Multi-domain translation between single-cell imaging and sequencing data using autoencoders |
| title | Multi-domain translation between single-cell imaging and sequencing data using autoencoders |
| title_full | Multi-domain translation between single-cell imaging and sequencing data using autoencoders |
| title_fullStr | Multi-domain translation between single-cell imaging and sequencing data using autoencoders |
| title_full_unstemmed | Multi-domain translation between single-cell imaging and sequencing data using autoencoders |
| title_short | Multi-domain translation between single-cell imaging and sequencing data using autoencoders |
| title_sort | multi domain translation between single cell imaging and sequencing data using autoencoders |
| url | https://hdl.handle.net/1721.1/133658 |
| work_keys_str_mv | AT yangkarrendai multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders AT belyaevaanastasiya multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders AT venkatachalapathysaradha multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders AT damodarankarthik multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders AT katcoffabigail multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders AT radhakrishnanadityanarayanan multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders AT shivashankargv multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders AT uhlercaroline multidomaintranslationbetweensinglecellimagingandsequencingdatausingautoencoders |