Shallow Sparsely-Connected Autoencoders for Gene Set Projection
When analyzing biological data, it can be helpful to consider gene sets, or predefined groups of biologically related genes. Methods exist for identifying gene sets that are differential between conditions, but large public datasets from consortium projects and single-cell RNA-Sequencing have opened...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Pub Co Pte Lt
2020
|
| Online Access: | https://hdl.handle.net/1721.1/125231 |
| _version_ | 1826213624087052288 |
|---|---|
| author | Gold, Maxwell P. Lenail, Alexander Fraenkel, Ernest |
| author2 | Massachusetts Institute of Technology. Department of Biological Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Biological Engineering Gold, Maxwell P. Lenail, Alexander Fraenkel, Ernest |
| author_sort | Gold, Maxwell P. |
| collection | MIT |
| description | When analyzing biological data, it can be helpful to consider gene sets, or predefined groups of biologically related genes. Methods exist for identifying gene sets that are differential between conditions, but large public datasets from consortium projects and single-cell RNA-Sequencing have opened the door for gene set analysis using more sophisticated machine learning techniques, such as autoencoders and variational autoencoders. We present shallow sparsely-connected autoencoders (SSCAs) and variational autoencoders (SSCVAs) as tools for projecting gene-level data onto gene sets. We tested these approaches on single-cell RNA-Sequencing data from blood cells and on RNA-Sequencing data from breast cancer patients. Both SSCA and SSCVA can recover known biological features from these datasets and the SSCVA method often outperforms SSCA (and six existing gene set scoring algorithms) on classification and prediction tasks. |
| first_indexed | 2024-09-23T15:52:13Z |
| format | Article |
| id | mit-1721.1/125231 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:52:13Z |
| publishDate | 2020 |
| publisher | World Scientific Pub Co Pte Lt |
| record_format | dspace |
| spelling | mit-1721.1/1252312022-10-02T04:44:12Z Shallow Sparsely-Connected Autoencoders for Gene Set Projection Gold, Maxwell P. Lenail, Alexander Fraenkel, Ernest Massachusetts Institute of Technology. Department of Biological Engineering When analyzing biological data, it can be helpful to consider gene sets, or predefined groups of biologically related genes. Methods exist for identifying gene sets that are differential between conditions, but large public datasets from consortium projects and single-cell RNA-Sequencing have opened the door for gene set analysis using more sophisticated machine learning techniques, such as autoencoders and variational autoencoders. We present shallow sparsely-connected autoencoders (SSCAs) and variational autoencoders (SSCVAs) as tools for projecting gene-level data onto gene sets. We tested these approaches on single-cell RNA-Sequencing data from blood cells and on RNA-Sequencing data from breast cancer patients. Both SSCA and SSCVA can recover known biological features from these datasets and the SSCVA method often outperforms SSCA (and six existing gene set scoring algorithms) on classification and prediction tasks. National Institutes of Health (U.S.) (Grant R01NS089076) National Institutes of Health (U.S.) (Grant 1U01CA18498) 2020-05-14T12:02:34Z 2020-05-14T12:02:34Z 2019-03 2020-03-06T15:02:11Z Article http://purl.org/eprint/type/JournalArticle 9789813279810 https://hdl.handle.net/1721.1/125231 Gold, Maxwell P., Alexander LeNail, and Ernest Fraenkel. "Shallow Sparsely-Connected Autoencoders for Gene Set Projection." Paper presented at the Pacific Symposium on Biocomputing 2019 (Kohala Coast, Hawaii, USA, 3-7 January 2019) 24 (2019): 374-385 © 2019 The Author(s) en 10.1142/9789813279827_0034 Pacific Symposium on Biocomputing 2019 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf World Scientific Pub Co Pte Lt PMC |
| spellingShingle | Gold, Maxwell P. Lenail, Alexander Fraenkel, Ernest Shallow Sparsely-Connected Autoencoders for Gene Set Projection |
| title | Shallow Sparsely-Connected Autoencoders for Gene Set Projection |
| title_full | Shallow Sparsely-Connected Autoencoders for Gene Set Projection |
| title_fullStr | Shallow Sparsely-Connected Autoencoders for Gene Set Projection |
| title_full_unstemmed | Shallow Sparsely-Connected Autoencoders for Gene Set Projection |
| title_short | Shallow Sparsely-Connected Autoencoders for Gene Set Projection |
| title_sort | shallow sparsely connected autoencoders for gene set projection |
| url | https://hdl.handle.net/1721.1/125231 |
| work_keys_str_mv | AT goldmaxwellp shallowsparselyconnectedautoencodersforgenesetprojection AT lenailalexander shallowsparselyconnectedautoencodersforgenesetprojection AT fraenkelernest shallowsparselyconnectedautoencodersforgenesetprojection |