update test bam file downloading

.github/workflows/test_action.yml

@@ -16,7 +16,11 @@ jobs:
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v1
       - name: Download test dataset
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.9'
+          cache: 'pip'
         run: bash ${GITHUB_WORKSPACE}/test_data/download_data.sh
       - name: Run pipeline with test data
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,conda --souporcell False --generate_anndata False
+          nextflow run ${GITHUB_WORKSPACE} -profile test,conda --souporcell False --generate_anndata False

docs/source/genetic.md

@@ -40,10 +40,10 @@ Case 4: Run scSplit without data pre-processing:
 nextflow run ${hadge_project_dir}/main.nf -profile conda --mode genetic --scSplit_preprocess False //additional paramters as in case 1
 ```
 
-Case 5: Run the pipeline with different combinations of parameter. This is only available in the single sample mode. The values should be separated by semicolumn, and double quoted if specified in a config file.
+Case 5: Run the pipeline with different combinations of parameter. This is only available in the single sample mode. The values should be separated by semicolumn and double quoted.
 
 ```bash
-nextflow run ${hadge_project_dir}/main.nf -profile conda_singularity --mode genetic --alpha 0.1;0.3;0.5 //additional paramters as in case 1
+nextflow run ${hadge_project_dir}/main.nf -profile conda_singularity --mode genetic --alpha "0.1;0.3;0.5" //additional paramters as in case 1
 ```
 
 ## **Input data preparation**

docs/source/hashing.md

@@ -28,10 +28,10 @@ Case 2: Run Multiseq with raw counts :
 nextflow run ${hadge_project_dir}/main.nf -profile conda --outputdir ${output_dir} --mode hashing --rna_matrix_multiseq raw --hto_matrix_multiseq raw // additional parameters as in case 1
 ```
 
-Case 3: Run the pipeline with different combinations of parameter. This is only available in the single sample mode. The values should be separated by semicolumn, and double quoted if specified in a config file.
+Case 3: Run the pipeline with different combinations of parameter. This is only available in the single sample mode. The values should be separated by semicolumn and double quoted.
 
 ```bash
-nextflow run ${hadge_project_dir}/main.nf -profile conda --mode hashing --quantile_multi 0.5;0.7 //additional paramters as in case 1
+nextflow run ${hadge_project_dir}/main.nf -profile conda --mode hashing --quantile_multi "0.5;0.7" //additional paramters as in case 1
 ```
 
 ## **Input data preparation**

test_data/download_data.sh

@@ -6,9 +6,11 @@ wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=1xl9g
 wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=1jlhEO1Z7YGYVnxv1YO9arjDwGFeZbfkr' -O jurkat_293t_downsampled_n500_full_bam.bam.bai
 FILEID="13CV6CjP9VzmwG5MVHbJiVDMVdiIhGdJB"
 FILENAME="jurkat_293t_downsampled_n500_full_bam.bam"
-wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=$FILEID' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=$FILEID" -O $FILENAME && rm -rf /tmp/cookies.txt
+# wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=$FILEID' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=$FILEID" -O $FILENAME && rm -rf /tmp/cookies.txt
+pip install gdown
+gdown --id $FILEID -o $FILENAME
 wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=1MmwEiOsdzEfRdXS6oXXBwMJXUovKWcni' -O final_res.zip
-unzip final_res.zip 
+unzip final_res.zip
 rm final_res.zip
 mv final_res/jurkat_293t_demuxlet.best .
 rm -rf final_res
@@ -24,7 +26,12 @@ wget --no-check-certificate https://figshare.com/ndownloader/files/43102453 -O g
 wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=1lw4T6d7uXsm9dt39ZtEwpuB2VTY3wK1y' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=1lw4T6d7uXsm9dt39ZtEwpuB2VTY3wK1y" -O common_variants_hg19.vcf && rm -rf /tmp/cookies.txt
 wget https://master.dl.sourceforge.net/project/cellsnp/SNPlist/genome1K.phase3.SNP_AF5e2.chr1toX.hg19.vcf.gz
 # Processed by bcftools query -f '%CHROM:%POS\n' common_variants_hg19.vcf > common_variants_hg19_list.vcf
-wget https://s3-eu-west-1.amazonaws.com/pfigshare-u-files/41773431/common_variants_hg19_list.vcf?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIYCQYOYV5JSSROOA/20230731/eu-west-1/s3/aws4_request&X-Amz-Date=20230731T153655Z&X-Amz-Expires=10&X-Amz-SignedHeaders=host&X-Amz-Signature=283575c6ccb3104b8b95684e6d955abd28b47db71c18d1eeec99ae5dab65ff7b
+wget https://s3-eu-west-1.amazonaws.com/pfigshare-u-files/41773431/common_variants_hg19_list.vcf?X-Amz-Algorithm=AWS4-HMAC-SHA256 &
+X-Amz-Credential=AKIAIYCQYOYV5JSSROOA/20230731/eu-west-1/s3/aws4_request &
+X-Amz-Date=20230731T153655Z &
+X-Amz-Expires=10 &
+X-Amz-SignedHeaders=host &
+X-Amz-Signature=283575c6ccb3104b8b95684e6d955abd28b47db71c18d1eeec99ae5dab65ff7b
 
 # Download simualated data
 # Can also run Rscript simulation.R
@@ -34,9 +41,8 @@ wget --no-check-certificate https://figshare.com/ndownloader/files/41773428 -O b
 wget --no-check-certificate https://figshare.com/ndownloader/files/41773431 -O common_variants_hg19_list.vcf
 # simulated HTO and RNA counts
 wget --no-check-certificate https://figshare.com/ndownloader/files/41779407 -O hto.zip
-unzip hto.zip 
+unzip hto.zip
 wget --no-check-certificate https://figshare.com/ndownloader/files/41779260 -O rna.zip
 unzip rna.zip
 rm hto.zip
 rm rna.zip
-