A Transformer for scATAC-scRNA Translation
scATAC-seq gives a comprehensive picture of the chromatin accessibility profile of a cell, covering not only protein-coding regions but also non-coding regulatory regions which are in theory missed by scRNA-seq. However, scATAC-seq data is highdimensional and noisy, aspects which when compounded wit...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/147430 |
| _version_ | 1811091561885204480 |
|---|---|
| author | Jin, Roger |
| author2 | Kellis, Manolis |
| author_facet | Kellis, Manolis Jin, Roger |
| author_sort | Jin, Roger |
| collection | MIT |
| description | scATAC-seq gives a comprehensive picture of the chromatin accessibility profile of a cell, covering not only protein-coding regions but also non-coding regulatory regions which are in theory missed by scRNA-seq. However, scATAC-seq data is highdimensional and noisy, aspects which when compounded with data scarcity present challenges for modeling on even seemingly-simple downstream tasks such as cell-type prediction. As such, researchers may benefit from access to a large library of models to evaluate. While we do not demonstrate state of the art results in any capacity, we provide an implementation of a simple representation of sparse tabular data that allows it to be inputted into the popular transformer family of architectures, and use this representation to train a transformer that predicts scRNA-seq given scATAC-seq. Our code is made available here https://github.com/rogershijin/GANOLI. |
| first_indexed | 2024-09-23T15:04:20Z |
| format | Thesis |
| id | mit-1721.1/147430 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:04:20Z |
| publishDate | 2023 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1474302023-01-20T03:12:28Z A Transformer for scATAC-scRNA Translation Jin, Roger Kellis, Manolis Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science scATAC-seq gives a comprehensive picture of the chromatin accessibility profile of a cell, covering not only protein-coding regions but also non-coding regulatory regions which are in theory missed by scRNA-seq. However, scATAC-seq data is highdimensional and noisy, aspects which when compounded with data scarcity present challenges for modeling on even seemingly-simple downstream tasks such as cell-type prediction. As such, researchers may benefit from access to a large library of models to evaluate. While we do not demonstrate state of the art results in any capacity, we provide an implementation of a simple representation of sparse tabular data that allows it to be inputted into the popular transformer family of architectures, and use this representation to train a transformer that predicts scRNA-seq given scATAC-seq. Our code is made available here https://github.com/rogershijin/GANOLI. M.Eng. 2023-01-19T19:49:51Z 2023-01-19T19:49:51Z 2022-09 2022-09-16T20:23:33.197Z Thesis https://hdl.handle.net/1721.1/147430 In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Jin, Roger A Transformer for scATAC-scRNA Translation |
| title | A Transformer for scATAC-scRNA Translation |
| title_full | A Transformer for scATAC-scRNA Translation |
| title_fullStr | A Transformer for scATAC-scRNA Translation |
| title_full_unstemmed | A Transformer for scATAC-scRNA Translation |
| title_short | A Transformer for scATAC-scRNA Translation |
| title_sort | transformer for scatac scrna translation |
| url | https://hdl.handle.net/1721.1/147430 |
| work_keys_str_mv | AT jinroger atransformerforscatacscrnatranslation AT jinroger transformerforscatacscrnatranslation |