From 17d4b20231f8b3657c840b859f3608b8ab6b64fb Mon Sep 17 00:00:00 2001 From: Xichen Wu Date: Thu, 9 Nov 2023 20:12:07 +0100 Subject: [PATCH] use subset reference genome as test data --- .github/workflows/test_action.yml | 9 +++------ test.config | 6 +++--- test_data/download_data.sh | 12 +++++++----- 3 files changed, 13 insertions(+), 14 deletions(-) diff --git a/.github/workflows/test_action.yml b/.github/workflows/test_action.yml index ecb3949..2838fab 100644 --- a/.github/workflows/test_action.yml +++ b/.github/workflows/test_action.yml @@ -1,8 +1,7 @@ name: hadge test workflow -on: - push +on: push jobs: - test: + test: name: Run pipeline with test data runs-on: ubuntu-latest steps: @@ -15,9 +14,7 @@ jobs: with: singularity-version: 3.8.3 - name: Download test dataset - run: bash ${GITHUB_WORKSPACE}/test_data/download_data.sh + run: bash ${GITHUB_WORKSPACE}/test_data/download_data.sh - name: Run pipeline with test data run: | nextflow run ${GITHUB_WORKSPACE} -profile test,conda_singularity - - \ No newline at end of file diff --git a/test.config b/test.config index a3bdbe1..2c14437 100644 --- a/test.config +++ b/test.config @@ -10,8 +10,8 @@ params { bam = "$projectDir/test_data/jurkat_293t_downsampled_n500_full_bam.bam" bai = "$projectDir/test_data/jurkat_293t_downsampled_n500_full_bam.bam.bai" barcodes = "$projectDir/test_data/barcodes.tsv" - fasta = "$projectDir/test_data/refdata-cellranger-hg19-3.0.0/fasta/genome.fa" - fasta_index = "$projectDir/test_data/refdata-cellranger-hg19-3.0.0/fasta/genome.fa.fai" + fasta = "$projectDir/test_data/refdata-cellranger-hg19-3.0.0/fasta/genome_chr1.fa" + fasta_index = "$projectDir/test_data/refdata-cellranger-hg19-3.0.0/fasta/genome_chr1.fa.fai" nsample = 2 common_variants_scSplit = "$projectDir/test_data/common_variants_hg19_list.vcf" common_variants_souporcell = "$projectDir/test_data/common_variants_hg19.vcf" @@ -19,7 +19,7 @@ params { common_variants_cellsnp = "$projectDir/test_data/genome1K.phase3.SNP_AF5e2.chr1toX.hg19.vcf.gz" vcf_donor = "$projectDir/test_data/jurkat_293t_exons_only.vcf.withAF.vcf" // Call freebayes on chr 1 and chr 2 only to speed up run time - region = "1;2" + region = "1" // donor genotype file provided by popscle doesnt work on souporcell use_known_genotype = "False" ignore = "True" diff --git a/test_data/download_data.sh b/test_data/download_data.sh index 608d601..ea3aa9b 100644 --- a/test_data/download_data.sh +++ b/test_data/download_data.sh @@ -12,10 +12,14 @@ unzip final_res.zip rm final_res.zip mv final_res/jurkat_293t_demuxlet.best . rm -rf final_res +# To run souporcell, unzip VCF file +gzip -dk jurkat_293t_exons_only.vcf.withAF.vcf.gz + +# Download subset reference genome +wget --no-check-certificate https://figshare.com/ndownloader/files/43102459 -O genome_chr1.fa +wget --no-check-certificate https://figshare.com/ndownloader/files/43102453 -O genome_chr1.fa.fai +# source: http://cf.10xgenomics.com/supp/cell-exp/refdata-cellranger-hg19-3.0.0.tar.gz -# Download reference genome -wget http://cf.10xgenomics.com/supp/cell-exp/refdata-cellranger-hg19-3.0.0.tar.gz -tar -xzvf refdata-cellranger-hg19-3.0.0.tar.gz # Download common variants 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 @@ -36,5 +40,3 @@ unzip rna.zip rm hto.zip rm rna.zip -# To run souporcell, unzip VCF file -gzip -dk test_data/jurkat_293t_exons_only.vcf.withAF.vcf.gz \ No newline at end of file