From 878d275c5f14736199fb926dcfacd4fc499d9f67 Mon Sep 17 00:00:00 2001
From: Robrecht Cannoodt <rcannood@gmail.com>
Date: Sun, 8 Sep 2024 11:30:26 +0200
Subject: [PATCH] use subset adata

---
 book/in_memory2.qmd                 | 15 +--------------
 book/in_memory_interoperability.qmd | 14 +-------------
 book/usecase/index.qmd              |  2 ++
 3 files changed, 4 insertions(+), 27 deletions(-)

diff --git a/book/in_memory2.qmd b/book/in_memory2.qmd
index c163b4b..104129d 100644
--- a/book/in_memory2.qmd
+++ b/book/in_memory2.qmd
@@ -16,7 +16,7 @@ Read in the anndata object
 ```{r read_in}
 library(anndata)
 
-adata_path <- "usecase/data/sc_counts_reannotated_with_counts.h5ad"
+adata_path <- "usecase/data/sc_counts_subset.h5ad"
 adata <- anndata::read_h5ad(adata_path)
 ```
 
@@ -28,19 +28,6 @@ adata <- anndata::read_h5ad(adata_path)
 
 # Usecase
 
-## 3. Subset data
-
-Subset to a single small molecule and control for computational efficiency:
-
-```{r select_sm_celltype}
-library(dplyr)
-
-sm_name2 <- "Belinostat"
-control_name <- "Dimethyl Sulfoxide"
-
-# subset obs
-adata <- adata[adata$obs$sm_name %in% c(control_name, sm_name), ]
-```
 
 ## 4. Compute pseudobulk
 
diff --git a/book/in_memory_interoperability.qmd b/book/in_memory_interoperability.qmd
index 827e91d..a687501 100644
--- a/book/in_memory_interoperability.qmd
+++ b/book/in_memory_interoperability.qmd
@@ -203,22 +203,10 @@ with (robjects.default_converter + pandas2ri.converter).context():
 ```{r read_in}
 library(anndata)
 
-adata_path <- "usecase/data/sc_counts_reannotated_with_counts.h5ad"
+adata_path <- "usecase/data/sc_counts_subset.h5ad"
 adata <- anndata::read_h5ad(adata_path)
 ```
 
-Subset to a single small molecule and control for computational efficiency:
-
-```{r select_sm_celltype}
-library(dplyr)
-
-sm_name <- "Belinostat"
-control_name <- "Dimethyl Sulfoxide"
-
-# subset obs
-adata <- adata[adata$obs$sm_name %in% c(control_name, sm_name), adata$var$highly_variable]
-```
-
 ## 4. Compute pseudobulk
 
 ```{r import_pandas}
diff --git a/book/usecase/index.qmd b/book/usecase/index.qmd
index 4dc4812..01603c0 100644
--- a/book/usecase/index.qmd
+++ b/book/usecase/index.qmd
@@ -67,6 +67,8 @@ adata = adata[
   adata.obs["sm_name"].isin([sm_name, control_name]) &
   adata.obs["cell_type"].isin([cell_type]),
 ].copy()
+
+adata.write_h5ad("data/sc_counts_subset.h5ad")
 ```
 
 We will also subset the genes to the top 2000 most variable genes.