-
Notifications
You must be signed in to change notification settings - Fork 10
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
79,809 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,129 @@ | ||
############################## Config ######################################### | ||
container: "docker://satijalab/azimuth-references:human_adipose-1.0.0" | ||
|
||
############################## All ############################################ | ||
rule all: | ||
input: | ||
"reference/ref.Rds", | ||
"reference/idx.annoy" | ||
|
||
############################## Reference ###################################### | ||
rule download: | ||
params: | ||
aizarani_url = "https://ftp.ncbi.nlm.nih.gov/geo/series/GSE124nnn/GSE124395/suppl/GSE124395_Normalhumanlivercellatlasdata.txt.gz", | ||
macparland_url = "'https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE115469&format=file&file=GSE115469%5FData%2Ecsv%2Egz'", | ||
payen_url = "'https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE158723&format=file'", | ||
ramachandran_url = "'https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE136103&format=file'", | ||
zhang_url = "https://ftp.ncbi.nlm.nih.gov/geo/series/GSE138nnn/GSE138709/suppl/GSE138709_RAW.tar" | ||
output: | ||
"logs/download_data.log", | ||
"data/GSE124395_Normalhumanlivercellatlasdata.txt", | ||
"data/natcomm_GSE115469.csv.gz", | ||
"data/mockfile.txt" | ||
#"data/payen/*.gz", | ||
#"data/ramachandran/*.gz", | ||
#"data/zhang/*.gz" | ||
shell: | ||
""" | ||
wget {params.aizarani_url} -P data | ||
gunzip data/GSE124395_Normalhumanlivercellatlasdata.txt.gz | ||
wget -O data/natcomm_GSE115469.csv.gz \ | ||
{params.macparland_url} | ||
wget -O data/JHEP_GSE158723.tar \ | ||
'https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE158723&format=file' | ||
mkdir data/payen/ | ||
tar -xvf data/JHEP_GSE158723.tar -C data/payen/ | ||
FILES=$(ls data/payen/*.gz) | ||
for f in $FILES ; do | ||
basename=$(basename ${{f}}) | ||
num=${{basename:8:2}} | ||
substring=$(echo $f| cut --complement -d'_' -f 1,2) | ||
mv "$f" "$substring" | ||
mkdir -p data/payen/GSM"$num" | ||
mv "$substring" data/payen/GSM"$num"/ | ||
gunzip data/payen/GSM"$num"/"$substring" | ||
done | ||
wget -O data/GSE136103_RAW.tar {params.ramachandran_url} | ||
mkdir data/ramachandran/ | ||
tar -xvf data/GSE136103_RAW.tar -C data/ramachandran/ | ||
FILES=$(ls data/ramachandran/*healthy[0-9]*) | ||
for f in $FILES ; do | ||
basename=$(basename ${{f}}) | ||
num=${{basename:8:2}} | ||
substring=$(echo $f| cut --complement -d'_' -f 1,2,3) | ||
mv "$f" "$substring" | ||
mkdir -p data/ramachandran/GSM"$num" | ||
mv "$substring" data/ramachandran/GSM"$num"/ | ||
gunzip data/ramachandran/GSM"$num"/"$substring" | ||
done | ||
rm data/ramachandran/*.gz | ||
wget {params.zhang_url} -P data | ||
mkdir data/zhang/ | ||
tar -xvf data/GSE138709_RAW.tar -C data/zhang/ | ||
touch data/mockfile.txt | ||
echo "Liver reference data downloaded on: $(date)" > logs/download_data.log | ||
""" | ||
|
||
rule build_reference: | ||
input: | ||
script = "scripts/build_reference.R", | ||
aizarani = "data/GSE124395_Normalhumanlivercellatlasdata.txt", | ||
macparland = "data/natcomm_GSE115469.csv.gz", | ||
payen = "data/payen", | ||
ramachandran = "data/ramachandran", | ||
zhang = "data/zhang", | ||
annotations = "data/annotations.csv" | ||
output: | ||
ref = "reference/ref.Rds", | ||
idx = "reference/idx.annoy", | ||
obj = "full_reference.Rds" | ||
shell: | ||
""" | ||
Rscript {input.script} {input.aizarani} {input.macparland} {input.payen} {input.ramachandran} {input.zhang} {input.annotations} {output.ref} {output.idx} {output.obj} | ||
""" | ||
############################## Demo ###################################### | ||
rule download_demo: | ||
params: | ||
demo_url = "https://www.livercellatlas.org/data_files/toDownload/rawData_human.zip" | ||
output: | ||
"logs/download_data.log", | ||
"data/demo/rawData_human/countTable_human/barcodes.tsv.gz", | ||
"data/demo/rawData_human/countTable_human/features.tsv.gz", | ||
"data/demo/rawData_human/countTable_human/matrix.mtx.gz" | ||
shell: | ||
""" | ||
wget {params.demo_url} - P data/demo | ||
gunzip rawData_human | ||
echo "Demo data downloaded on: $(date)" > logs/download_data.log | ||
""" | ||
|
||
rule build_demo: | ||
input: | ||
script = "scripts/build_demo.R", | ||
demo = "data/demo/rawData_human/countTable_human/" | ||
output: | ||
obj = "reference/demo.Rds" | ||
shell: | ||
""" | ||
Rscript {input.script} {input.demo} {output.obj} | ||
""" | ||
|
||
############################## Explorer ######################################## | ||
rule export_zarr: | ||
input: | ||
ref = "reference/ref.Rds", | ||
fullref = "full_reference.Rds", | ||
script1 = "scripts/convert_to_h5ad.R", | ||
script2 = "scripts/convert_to_zarr.py" | ||
output: | ||
h5Seurat = "vitessce/vitessce_ref.h5Seurat", | ||
h5ad = "vitessce/vitessce_ref.h5ad", | ||
zarr = directory("vitessce/vitessce_ref.zarr") | ||
container: | ||
"docker://satijalab/azimuth-references:vitessce" | ||
shell: | ||
""" | ||
mkdir -p vitessce | ||
Rscript {input.script1} {input.ref} {input.fullref} {output.h5Seurat} | ||
python3 {input.script2} {output.h5ad} {output.zarr} | ||
""" |
Oops, something went wrong.