describes parameters

README.md

@@ -11,13 +11,16 @@ The current pipeline integrate the following workflow:
 
 The following Item are necessary to run JASS pipeline
 
-1. --input_folder : A path toward a meta-data file describing GWAS (see example file in ./input_files/test1.csv)
+1. --meta_data : A path toward a meta-data file describing GWAS (see example file in ./input_files/test1.csv)
 2. --gwas_folder : A path toward a folder containing the summary statistics to analyze
-3. A folder containing a Reference Panel in the .bim, .bed, .fam format
-4. If you wish to compute joint analyses with the pipeline, a group file with the each phenotype group written on a separated line
+3. --ref_panel :A folder containing a Reference Panel in the .bim, .bed, .fam format
+4. --ld-folder : A path toward a folder containing LD matrices (that can be generated from the reference panel with the raiss package as described here : http://statistical-genetics.pages.pasteur.fr/raiss/#precomputation-of-ld-correlation)
+5. --group If you wish to compute joint analyses with the pipeline, a group file with the each phenotype group written on a separated line
+
 
 ## Optional parameters
-. A path toward a folder to write pipeline results (inittable, worktable...). by default results will be publish in the workflow directory.
+
+* --output_folder : A path toward a folder to write pipeline results (inittable, worktable...). by default results will be publish in the workflow directory.
 
 ## Usage of nextflow pipeline
 

jass_pipeline.nf

 
-params.compute_project=false
+params.compute_project=true
 params.compute_LDSC_matrix=true
-params.compute_imputation=false
+params.compute_imputation=true
 
-
-params.meta_data = "test_final.csv"
-
-params.input_folder = ${baseDir}+"/input_files/"
+params.meta_data = "${baseDir}"+"/input_files/test_final.csv"
 params.gwas_folder = "/pasteur/projets/policy01/PCMA/1._DATA/RAW.GWAS/"
+params.ref_panel = '/pasteur/projets/policy01/PCMA/1._DATA/ImpG_refpanel/'
 
-
-params.group = params.input_folder+"/group.txt"
+params.group = "${baseDir}/input_files/group.txt"
 group = file(params.group)
+params.region = "${baseDir}/input_files/fourier_ls-all.bed"
+params.output_folder = "$baseDir"
 
-params.region = params.input_folder+"fourier_ls-all.bed"
-params.output_folder = $baseDir
-
-GWAS_labels = params.input_folder + params.input_folder
+diagnostic_folder= params.output_folder + "/sample_size/"
+harmonized_GWAS_folder = params.output_folder + "harmonized_GWAS_by_chr/"
+harmonized_GWAS_1_file_folder = params.output_folder +"harmonized_GWAS_WG/"
 
 Region_channel = Channel.fromPath(params.region)
 Region_channel2 = Channel.fromPath(params.region)
 
-diagnostic_folder= params.output_folder + "/sample_size/"
-harmonized_GWAS_folder = params.output_folder + "harmonized_GWAS_by_chr/"
-harmonized_GWAS_1_file_folder = params.output_folder + "harmonized_GWAS_WG/"
-
 chr_channel = Channel.from(1..22)
 
-ref_chr_channel=Channel.fromPath("/pasteur/projets/policy01/PCMA/1._DATA/ImpG_refpanel/chr*.eur.1pct.bim")
-ref_chr_channel2=Channel.fromPath("/pasteur/projets/policy01/PCMA/1._DATA/ImpG_refpanel/chr*.eur.1pct.bim")
-ref_chr_channel3=Channel.fromPath("/pasteur/projets/policy01/PCMA/1._DATA/ImpG_refpanel/chr*.eur.1pct.*")
+ref_chr_channel=Channel.fromPath(params.ref_panel+"/chr*.eur.1pct.bim")
+ref_chr_channel2=Channel.fromPath(params.ref_panel+"/chr*.eur.1pct.bim")
+ref_chr_channel3=Channel.fromPath(params.ref_panel+"/chr*.eur.1pct.*")
 
 ld_channel=Channel.fromPath("/pasteur/projets/policy01/PCMA/WKD_Hanna/impute_for_jass/ld_block_new_plink/*.ld")
 
 /* Script channels*/
-extract_sample_size_script_channel = Channel.fromPath('${baseDir}/extract_sample_size.py')
-generate_trait_pairs_channel = Channel.fromPath('${baseDir}/generate_trait_pairs.py')
-parse_correlation_channel = Channel.fromPath('${baseDir}/parse_correlation_results.py')
+extract_sample_size_script_channel = Channel.fromPath("${baseDir}/extract_sample_size.py")
+generate_trait_pairs_channel = Channel.fromPath("${baseDir}/generate_trait_pairs.py")
+parse_correlation_channel = Channel.fromPath("${baseDir}/parse_correlation_results.py")
 
 
 
@@ -97,21 +91,21 @@ process meta_data_GWAS{
     output:
         file "meta_data_chk*" into meta_data mode flatten
     """
-    d=`wc -l ${GWAS_labels}`
+    d=`wc -l ${params.meta_data}`
     e=`echo \$d | cut -d ' ' -f 1`
 
     for ((i = 2; i <= \$e; i++));
     do
-        head -n1 ${GWAS_labels} > "meta_data_chk\$i.csv"
-        head -n \$i ${GWAS_labels} | tail -n 1 >> "meta_data_chk\$i.csv"
+        head -n1 ${params.meta_data} > "meta_data_chk\$i.csv"
+        head -n \$i ${params.meta_data} | tail -n 1 >> "meta_data_chk\$i.csv"
     done
 """
 }
 
 process Clean_GWAS {
 
-    //publishDir "${output_folder}/harmonized_GWAS", pattern: "*.txt", mode: 'copy'
-    //publishDir "${output_folder}", pattern: "harmonized_GWAS_1_file/*.txt", mode: 'copy'
+    publishDir "${output_folder}/harmonized_GWAS_files/", pattern: "*.txt", mode: 'copy'
+    publishDir "${output_folder}", pattern: "*.txt", mode: 'copy'
 
     input:
         file ref_panel from ref_panel_wg_channel
@@ -139,7 +133,7 @@ process Clean_GWAS {
 
 
 process Impute_GWAS {
-    //publishDir "${output_folder}", pattern: "imputed_GWAS/*.txt", mode: 'copy'
+    publishDir "${output_folder}", pattern: "imputed_GWAS/*.txt", mode: 'copy'
     memory '8 GB'
     time '8h'
     input:
@@ -188,11 +182,10 @@ process Do_not_Impute_GWAS {
 }
 
 /*
-process related to LD-score calculation
+    process related to LD-score calculation
 */
-
 process Munge_LDSC_data {
-    //publishDir "${baseDir}", pattern: "ldsc_data/data_*.sumstats.gz", mode: 'copy'
+    publishDir "${output_folder}", pattern: "ldsc_data/data_*.sumstats.gz", mode: 'copy'
 
     input:
         file clean_gwas from cleaned_gwas
@@ -203,7 +196,7 @@ process Munge_LDSC_data {
     when:
         params.compute_LDSC_matrix
     """
-    Nsamp=\$(python2.7 ${extract_sample_size_script} ${clean_gwas} ${GWAS_labels})
+    Nsamp=\$(python2.7 ${extract_sample_size_script} ${clean_gwas} ${params.meta_data})
 
     if [ ! -d "ldsc_data" ]
     then
@@ -236,7 +229,7 @@ process Generate_trait_pair {
 
 process Correlation_LDSC_data {
 
-    //publishDir "${baseDir}/cor_data/", pattern: "*.log", mode: 'copy'
+    publishDir "${output_folder}/cor_data/", pattern: "*.log", mode: 'copy'
     input:
         file trait_pair from combi_channel
         file ldsc_data from ldsc_data_channel_bis.collect()
@@ -266,7 +259,7 @@ process Correlation_LDSC_data {
 
 
 process Correlation_matrices {
-    //publishDir "${baseDir}/Correlation_matrices/", pattern: "*.csv", mode: 'copy'
+    publishDir "${output_folder}/Correlation_matrices/", pattern: "*.csv", mode: 'copy'
 
     input:
         file parsing_script from parse_correlation_channel
@@ -300,7 +293,7 @@ process Create_inittable_LDSC {
     date_init=\$(date +"%m_%d_%Y-%H:%M")
 
     init_name="inittable_LDSC_\$date_init.hdf5"
-    jass create-inittable --input-data-path "\$e" --init-covariance-path ${Covariance_H0} --regions-map-path ${Regions} --description-file-path ${GWAS_labels} --init-table-path  \$init_name
+    jass create-inittable --input-data-path "\$e" --init-covariance-path ${Covariance_H0} --regions-map-path ${Regions} --description-file-path ${params.meta_data} --init-table-path  \$init_name
 
     """
 }
@@ -324,7 +317,7 @@ process Create_inittable {
     date_init=\$(date +"%m_%d_%Y-%H:%M")
 
     init_name="inittable_NO_LDSC_\$date_init.hdf5"
-    jass create-inittable --input-data-path "\$e" --regions-map-path ${Regions} --description-file-path ${GWAS_labels} --init-table-path inittable_no_LDSC.hdf5 --init-covariance-path ${baseDir}/Correlation_matrices/Covariance_matrix_H0.csv
+    jass create-inittable --input-data-path "\$e" --regions-map-path ${Regions} --description-file-path ${params.meta_data} --init-table-path inittable_no_LDSC.hdf5 --init-covariance-path ${baseDir}/Correlation_matrices/Covariance_matrix_H0.csv
 
     """
 }