usecase data was moved

.dockerignore

@@ -10,3 +10,4 @@
 *.html
 *.DS_Store
 /usecase_data/
+/usecase/data/

.gitignore

@@ -6,6 +6,7 @@
 /site_libs/
 *.html
 *.DS_Store
+/usecase/data/
 /usecase_data/
 
 # Created by https://www.toptal.com/developers/gitignore/api/python,r

README.md

@@ -118,11 +118,11 @@ pixi run pipeline
 
 ### Docker
 
-To run the pipeline with Docker, use the following command. The image is ~5GB and the pipeline can require a lot of working memory ~20GB, so make sure to increase the RAM allocated to Docker in your settings. Note that the usecase_data/ and scripts/ folders are mounted to the Docker container, so you can edit the scripts and access the data.
+To run the pipeline with Docker, use the following command. The image is ~5GB and the pipeline can require a lot of working memory ~20GB, so make sure to increase the RAM allocated to Docker in your settings. Note that the usecase/data/ and scripts/ folders are mounted to the Docker container, so you can edit the scripts and access the data.
 
 ```bash
 docker pull berombau/polygloty-docker:latest
-docker run -it -v $(pwd)/usecase_data:/app/usecase_data -v $(pwd)/scripts:/app/scripts berombau/polygloty-docker:latest pixi run pipeline
+docker run -it -v $(pwd)/usecase/data:/app/usecase/data -v $(pwd)/scripts:/app/scripts berombau/polygloty-docker:latest pixi run pipeline
 ```
 
 ### Extra: building the Docker image yourself
@@ -131,7 +131,7 @@ To edit and build the Docker image yourself, use can use the following command.:
 
 ```bash
 docker build -t polygloty-docker .
-docker run -it -v $(pwd)/usecase_data:/app/usecase_data -v $(pwd)/scripts:/app/scripts polygloty-docker pixi run pipeline
+docker run -it -v $(pwd)/usecase/data:/app/usecase/data -v $(pwd)/scripts:/app/scripts polygloty-docker pixi run pipeline
 ```
 
 To publish it to Docker Hub, use the following command:

book/in_memory2.qmd

@@ -16,7 +16,7 @@ Read in the anndata object
 ```{r read_in}
 library(anndata)
 
-adata_path <- "notebooks/usecase_data/sc_counts_reannotated_with_counts.h5ad"
+adata_path <- "notebooks/usecase/data/sc_counts_reannotated_with_counts.h5ad"
 adata <- anndata::read_h5ad(adata_path)
 ```
 
@@ -89,5 +89,5 @@ pb_adata = ad.AnnData(
 Store to disk:
 
 ```{python store_pseudobulk}
-pb_adata.write_h5ad("usecase_data/pseudobulk.h5ad")
+pb_adata.write_h5ad("usecase/data/pseudobulk.h5ad")
 ```

book/in_memory_interoperability.qmd

@@ -203,7 +203,7 @@ with (robjects.default_converter + pandas2ri.converter).context():
 ```{r read_in}
 library(anndata)
 
-adata_path <- "notebooks/usecase_data/sc_counts_reannotated_with_counts.h5ad"
+adata_path <- "notebooks/usecase/data/sc_counts_reannotated_with_counts.h5ad"
 adata <- anndata::read_h5ad(adata_path)
 ```
 
@@ -270,6 +270,6 @@ pb_adata <- anndata::AnnData(
 Store to disk:
 
 ```{r store_pseudobulk}
-write_h5ad(pb_adata, "notebooks/usecase_data/pseudobulk.h5ad")
+write_h5ad(pb_adata, "notebooks/usecase/data/pseudobulk.h5ad")
 
 ```

book/on_disk_interoperability.qmd

@@ -122,9 +122,9 @@ With the Pixi task runner, you can define these tasks in their respective enviro
 pixi run pipeline
 ```
 
-You can create a Docker image with all the `pixi` environments and run the pipeline in one containerized environment. The image is ~5GB and the pipeline can require a lot of working memory ~20GB, so make sure to increase the RAM allocated to Docker in your settings. Note that the `usecase_data/` and `scripts/` folders are mounted to the Docker container, so you can interactively edit the scripts and access the data.
+You can create a Docker image with all the `pixi` environments and run the pipeline in one containerized environment. The image is ~5GB and the pipeline can require a lot of working memory ~20GB, so make sure to increase the RAM allocated to Docker in your settings. Note that the `usecase/data/` and `scripts/` folders are mounted to the Docker container, so you can interactively edit the scripts and access the data.
 
 ```bash
 docker pull berombau/polygloty-docker:latest
-docker run -it -v $(pwd)/usecase_data:/app/usecase_data -v $(pwd)/scripts:/app/scripts berombau/polygloty-docker:latest pixi run pipeline
+docker run -it -v $(pwd)/usecase/data:/app/usecase/data -v $(pwd)/scripts:/app/scripts berombau/polygloty-docker:latest pixi run pipeline
 ```

scripts/1_load_data.sh

@@ -1,6 +1,6 @@
-if [[ ! -f usecase_data/sc_counts_reannotated_with_counts.h5ad ]]; then
+if [[ ! -f usecase/data/sc_counts_reannotated_with_counts.h5ad ]]; then
   aws s3 cp \
     --no-sign-request \
     s3://openproblems-bio/public/neurips-2023-competition/sc_counts_reannotated_with_counts.h5ad \
-    usecase_data/sc_counts_reannotated_with_counts.h5ad
+    usecase/data/sc_counts_reannotated_with_counts.h5ad
 fi

scripts/2_compute_pseudobulk.py

@@ -2,7 +2,7 @@
 import anndata as ad
 
 print("Load data")
-adata = ad.read_h5ad("usecase_data/sc_counts_reannotated_with_counts.h5ad")
+adata = ad.read_h5ad("usecase/data/sc_counts_reannotated_with_counts.h5ad")
 
 sm_name = "Belinostat"
 control_name = "Dimethyl Sulfoxide"
@@ -44,4 +44,4 @@
 )
 
 print("Store to disk")
-pb_adata.write_h5ad("usecase_data/pseudobulk.h5ad")
+pb_adata.write_h5ad("usecase/data/pseudobulk.h5ad")

scripts/3_analysis_de.R

@@ -3,7 +3,7 @@ library(anndata)
 library(dplyr, warn.conflicts = FALSE)
 
 print("Reading data...")
-pb_adata <- read_h5ad("usecase_data/pseudobulk.h5ad")
+pb_adata <- read_h5ad("usecase/data/pseudobulk.h5ad")
 
 # Select small molecule and control:
 sm_name <- "Belinostat"
@@ -34,4 +34,4 @@ res |>
   head(10)
 
 # Write to disk:
-write.csv(res, "usecase_data/de_contrasts.csv")
+write.csv(res, "usecase/data/de_contrasts.csv")