Published March 17, 2024
| Version v1
Dataset
Open
An interpretable and adaptive autoencoder for efficient tissue deconvolution
Creators
-
De la Fuente, Jesus
(Researcher)1, 2
-
Legarra, Naroa
(Researcher)1, 3
- Diaz-Mazkiaran, Aintzane (Researcher)1, 3
-
Serrano, Guillermo
(Researcher)4
- Marin-Goñi, Irene (Researcher)3, 1, 5
- Benito Sendin, Markel
- Garcia Osta, Ana (Researcher)3, 1
- Kalari, Krishna R. (Researcher)5
-
Fernandez-Granda, Carlos
(Researcher)6, 7
-
Ochoa, Idoia
(Researcher)8, 2, 1, 9
-
Hernaez, Mikel
(Researcher)3, 8, 1
-
1.
Universidad de Navarra
- 2. TECNUN
- 3. CIMA
-
4.
King Abdullah University of Science and Technology
- 5. Mayo Clinic Rochester
-
6.
New York University
- 7. NYU CDS
- 8. DATAI
-
9.
University of Illinois Urbana-Champaign
Description
An interpretable and adaptive autoencoder for efficient tissue deconvolution.
The github repository is: (https://github.com/ML4BM-Lab/Sweetwater/tree/main)
Here we provide the 4 datasets used along the Sweetwater paper. In order to reproduce the results and run Sweetwater with every dataset:
- Call load_X.py, being X the dataset/subdataset used. e.g. for the PBMC GS, load_pbmc_gs_data.py
- This will return 4 elements: scRNA-seq, bulkRNA-seq, common_genes, bulkrna_props
- scRNA-seq: scRNA-seq reference expression matrix.
- bulkRNA-seq: bulkRNA-seq matrix to be deconvolved.
- common_genes: genes that both matrix have in common, hence defining the input size of the model.
- bulkrna_props: proportions of the bulkrna-seq matrix to be deconvolved.
- run python3 src/main.py with the path to both the scRNA-seq and bulkRNA-seq path. (see github readme)
- Get the deconvolved proportions. Afterwards, you can evaluate the performance using bulkrna_props.
Other
Raw files can be downloaded from GEO...
Files
README.md
Files
(591.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:30e71d9f295bbb047deb2fd4ebf4e3f2
|
221.7 MB | Preview Download |
|
md5:19759e20b0a9ff77d41790166763abfa
|
65.9 MB | Preview Download |
|
md5:44f528d84844f70f9975a801ffa1651f
|
161.9 MB | Preview Download |
|
md5:f027e87a3bd9f3bf3a8d64b8b71cbd03
|
141.6 MB | Preview Download |
|
md5:192e5f215f18d13dbdfada4f2c66e0ff
|
549 Bytes | Preview Download |
Additional details
Software
- Repository URL
- https://github.com/ML4BM-Lab/Sweetwater/tree/main
- Programming language
- Python