From 4c555cc4870308f8977a65f147a6303cd3d1c7e8 Mon Sep 17 00:00:00 2001
From: hjulienn <hanna.julienne@pasteur.fr>
Date: Wed, 11 Oct 2023 10:00:49 +0200
Subject: [PATCH] tutorial works with DSL2
---
README.md | 21 +++------------------
input_files/group.txt | 3 ++-
jass_pipeline.nf | 28 +++++++++++++---------------
3 files changed, 18 insertions(+), 34 deletions(-)
diff --git a/README.md b/README.md
index cc30a98..eda3624 100644
--- a/README.md
+++ b/README.md
@@ -25,26 +25,11 @@ Clone the current repository locally:
```
git clone https://gitlab.pasteur.fr/statistical-genetics/jass_suite_pipeline.git
```
-<!--
-download the test data through the interface, using wget or git lfs
-and place it in the ./test_data/hg38_EAS folder.
+[!NOTE]
+The pipeline has been upgraded to nextflow DSL2 syntax recently. If you wish to use the previous version in DSL1, you find it in ./old_versions and run it with previous version of nextflow ("NXF_VER=22.10.5 nextflow run jass_pipeline.nf ....")
-Option with wget
-```
-cd ${PATH_TO_PIPELINE_FOLDER}/test_data/hg38_EAS/
-wget https://gitlab.pasteur.fr/statistical-genetics/jass_suite_pipeline/-/raw/pipeline_ancestry/test_data/hg38_EAS/RBC_EAS_chr22.tsv?inline=false && mv RBC_EAS_chr22.tsv\?inline\=false RBC_EAS_chr22.tsv
-wget https://gitlab.pasteur.fr/statistical-genetics/jass_suite_pipeline/-/raw/pipeline_ancestry/test_data/hg38_EAS/PLT_EAS_chr22.tsv?inline=false && mv PLT_EAS_chr22.tsv\?inline\=false PLT_EAS_chr22.tsv
-wget https://gitlab.pasteur.fr/statistical-genetics/jass_suite_pipeline/-/raw/pipeline_ancestry/test_data/hg38_EAS/WBC_EAS_chr22.tsv?inline=false && mv WBC_EAS_chr22.tsv\?inline\=false WBC_EAS_chr22.tsv
-```
-Option with git-lfs (require installing git lfs)
-```
- git lfs pull --include PLT_EAS_chr22.tsv
- git lfs pull --include RBC_EAS_chr22.tsv
- git lfs pull --include WBC_EAS_chr22.tsv
-```
--->
Test data are located in the ${PATH_TO_PIPELINE_FOLDER}/test_data/hg38_EAS/ folder
These are extracts of summary statistics from a trans ancestry GWAS on blood traits ([Chen et al](https://www.sciencedirect.com/science/article/pii/S0092867420308229?via%3Dihub)): WBC, White blood cell count; RBC, Red blood cell count; PLT, platelet count.
@@ -53,7 +38,7 @@ They correspond to the chromosome 21 and 22 for the East asian ancestry.
Once done you can launch the pipeline as:
```
- NXF_VER=22.10.5 nextflow run jass_pipeline.nf --ref_panel_WG {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}Ref_Panel/1000G_EAS_0_01_chr22_21.csv --gwas_folder {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/test_data/hg38_EAS/ --meta-data {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/input_files/Data_test_EAS.csv --region {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/input_files/All_Regions_ALL_ensemble_1000G_hg38_EAS.bed --group {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/input_files/group.txt -with-report jass_report.html -c nextflow_local.config
+ nextflow run jass_pipeline.nf --ref_panel_WG {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}Ref_Panel/1000G_EAS_0_01_chr22_21.csv --gwas_folder {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/test_data/hg38_EAS/ --meta-data {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/input_files/Data_test_EAS.csv --region {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/input_files/All_Regions_ALL_ensemble_1000G_hg38_EAS.bed --group {ABSOLUTE_PATH_TO_PIPELINE_FOLDER}/input_files/group.txt -with-report jass_report.html -c nextflow_local.config
```
See the description of required parameters in the next section.
You can specify parameter in the jass_pipeline.nf header if prefered.
diff --git a/input_files/group.txt b/input_files/group.txt
index f20cd7a..558817a 100644
--- a/input_files/group.txt
+++ b/input_files/group.txt
@@ -1 +1,2 @@
-GRP1;z_SHRINE_FVC z_SHRINE_PEF z_SHRINE_FEV1 z_SHRINE_RATIO
+GRP1;z_BCT_WBC z_BCT_PLT z_BCT_RBC
+GRP2;z_BCT_PLT z_BCT_RBC
\ No newline at end of file
diff --git a/jass_pipeline.nf b/jass_pipeline.nf
index 9841c2f..6c56ddd 100644
--- a/jass_pipeline.nf
+++ b/jass_pipeline.nf
@@ -8,24 +8,23 @@ nextflow.enable.dsl=2
/* Parameter to set if optional pipeline steps are performed */
params.compute_project=true // Compute JASS runs
-params.compute_LDSC_matrix=true // Infer the genetic covariance and residual covariance using the LDscore regression (Bulik-Sullivan, et al, 2015). The residual covariance is necessary to perform multi-trait GWAS (see julienne, et al 2021) If set to false, the residual covariance will be infered from Zscores
-params.compute_imputation=true
+params.compute_LDSC_matrix=false // Infer the genetic covariance and residual covariance using the LDscore regression (Bulik-Sullivan, et al, 2015). The residual covariance is necessary to perform multi-trait GWAS (see julienne, et al 2021) If set to false, the residual covariance will be infered from Zscores
+params.compute_imputation=false
/* Path of input data */
-params.meta_data = "${projectDir}"+"/input_files/Meta_data_preliminary_analysis.csv" // file describing gwas summary statistic format
-params.gwas_folder = "${projectDir}" + "/RAW_SUMSTAT/"
-
-// //"/pasteur/zeus/projets/p02/GGS_JASS/1._DATA/Summary_stat_hg38/EAS/"
+params.meta_data = "${projectDir}"+"/input_files/Data_test_EAS.csv"
+ // "${projectDir}"+"/input_files/Meta_data_preliminary_analysis.csv" file describing gwas summary statistic format
+params.gwas_folder = "${projectDir}"+'/test_data/hg38_EAS/'
params.region = Channel.fromPath("${projectDir}"+"/input_files/All_Regions_ALL_ensemble_1000G_hg38_EUR.bed")
-params.ref_panel_WG = "${projectDir}"+"/Ref_Panel/1000G_EUR_0_01.csv"
-//"${projectDir}/Ref_Panel/1000G_SAS_0_01_chr22.csv"
+params.ref_panel_WG = "${projectDir}"+"/Ref_Panel/1000G_EAS_0_01_chr22_21.csv"
+
-params.ancestry="EUR"
+params.ancestry="EAS"
params.prefix="ALL_ensemble_1000G_hg38_EUR_chr"
-params.prefix_Impute_GWAS="ALL_ensemble_1000G_hg38_EUR_"
+params.prefix_Impute_GWAS="ALL_ensemble_1000G_hg38_EAS_"
params.suffix=""
-params.LD_SCORE_folder='/pasteur/zeus/projets/p02/GGS_WKD/DATA_1000G/Panels/Matrix_LDSCORE/EUR/'
+params.LD_SCORE_folder='/pasteur/zeus/projets/p02/GGS_WKD/DATA_1000G/Panels/Matrix_LDSCORE/EAS/'
/* Folder to store result output */
params.output_folder = "${projectDir}"
@@ -43,14 +42,13 @@ params.r2threshold = 0.6
params.eigenthreshold = 0.05
params.minimumld = 5
params.ld_type = "plink"
-params.ld_folder = Channel.fromPath("/pasteur/zeus/projets/p02/GGS_WKD/DATA_1000G/Panels/Matrix_LD_RAISS/EUR/*.ld").collect()
+params.ld_folder = Channel.fromPath("/pasteur/zeus/projets/p02/GGS_WKD/DATA_1000G/Panels/Matrix_LD_RAISS/EAS/*.ld").collect()
params.ref_panel = '/pasteur/zeus/projets/p02/GGS_JASS/jass_analysis_pipeline/Ref_panel_by_chr/'
chr_channel = Channel.from(1..22)
params.ref_chr_path= Channel.fromPath("/pasteur/zeus/projets/p02/GGS_WKD/DATA_1000G/Panels/EUR/ALL_ensemble_1000G_hg38_EUR_chr*.bim").collect()
-params.perform_sanity_checks=true
-params.perform_accuracy_checks=true
-
+params.perform_sanity_checks=false
+params.perform_accuracy_checks=false
/* Project group */
params.group = "${projectDir}/input_files/group.txt"
--
GitLab