release v2.2: README improved. Dataset and results are in zenodo

README.md

@@ -297,3 +297,4 @@ Everything
 
 
 
+

nextflow.config

@@ -3,7 +3,7 @@
 ##                                                                     ##
 ##     slivar_vcf_extraction.config                                    ##
 ##                                                                     ##
-##     Gael A. Millot                                                  ##
+##     gmillot A. Millot                                               ##
 ##     Bioinformatics and Biostatistics Hub                            ##
 ##     Computational Biology Department                                ##
 ##     Institut Pasteur Paris                                          ##
@@ -16,17 +16,17 @@
 
 // variables exported to the main.nf environment. See https://www.nextflow.io/docs/latest/config.html#scope-env
 env {
-    sample_path = "/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.gatk-vqsr.splitted.norm.vep.merged_first_10.vcf" // path of the sample file. Example : sample_path="/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.gatk-vqsr.splitted.norm.vep.merged_first_10000.vcf.gz" sample_path="/pasteur/zeus/projets/p02/ghfc_wgs_zeus/WGS/Dyslexia/vcf/Dyslexia.gatk-vqsr.splitted.norm.vep.merged.vcf.gz". The .tbi file seems not required when calling a .gz file
+    sample_path = "/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.gatk-vqsr.splitted.norm.vep.merged_first_10.vcf" // path of the sample file. Example : sample_path="/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.gatk-vqsr.splitted.norm.vep.merged_first_10000.vcf.gz" sample_path="/pasteur/zeus/projets/p02/ghfc_wgs_zeus/WGS/Dyslexia/vcf/Dyslexia.gatk-vqsr.splitted.norm.vep.merged.vcf.gz". The .tbi file seems not required when calling a .gz file
     //Warning: do not write the out_path now. See below. If written here, the one below is not considered"
-    fun_path = "/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/bin/slivar-functions.js" // .js file containing functions for the slivar --family-expr option. Example : fun_path="/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/bin/slivar-functions.js", fun_path="/pasteur/zeus/projets/p01/BioIT/gmillot/08002_bourgeron/bin/slivar-functions.js"
-    ped_path = "/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.pedigree.txt" // path of the pedigree file. Example : ped_path="/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.pedigree.txt", ped_path="/pasteur/zeus/projets/p01/BioIT/gmillot/08002_bourgeron/dataset/Dyslexia.pedigree.txt" // pedigree
+    fun_path = "/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/bin/slivar-functions.js" // .js file containing functions for the slivar --family-expr option. Example : fun_path="/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/bin/slivar-functions.js", fun_path="/pasteur/zeus/projets/p01/BioIT/gmillot/08002_bourgeron/bin/slivar-functions.js"
+    ped_path = "/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.pedigree.txt" // path of the pedigree file. Example : ped_path="/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/Dyslexia.pedigree.txt", ped_path="/pasteur/zeus/projets/p01/BioIT/gmillot/08002_bourgeron/dataset/Dyslexia.pedigree.txt" // pedigree
 
 // Reminder. The command of slivar used are:
     // slivar expr --js ${fun} -g ${annot1} -g ${annot2} --vcf ${vcf} --ped ${ped} --pass-only --family-expr "${pedigree_expr}" -o "res.vcf"
     // slivar tsv --ped ${ped} -s aff_only -i ${info} res.vcf > res.tsv
 
-    annot1_path = "/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/cadd-1.6-SNVs-phred10-GRCh37.zip" // path of the cadd annotation file. Example : annot1_path="/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/cadd-1.6-SNVs-phred10-GRCh37.zip", annot1_path="/pasteur/zeus/projets/p02/ghfc_wgs_zeus/references/GRCh37/slivar-gnotate/cadd-1.6-SNVs-phred10-GRCh37.zip" // cadd annotation
-    annot2_path = "/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/gnomad-2.1.1-genome-GRCh37.zip" // path of gnomad annotation file. Example : annot2_path="/mnt/c/Users/Gael/Documents/Git_projects/slivar_vcf_extraction/dataset/gnomad-2.1.1-genome-GRCh37.zip", annot2_path="/pasteur/zeus/projets/p02/ghfc_wgs_zeus/references/GRCh37/slivar-gnotate/gnomad-2.1.1-genome-GRCh37.zip" // gnomad annotation
+    annot1_path = "/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/cadd-1.6-SNVs-phred10-GRCh37.zip" // path of the cadd annotation file. Example : annot1_path="/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/cadd-1.6-SNVs-phred10-GRCh37.zip", annot1_path="/pasteur/zeus/projets/p02/ghfc_wgs_zeus/references/GRCh37/slivar-gnotate/cadd-1.6-SNVs-phred10-GRCh37.zip" // cadd annotation
+    annot2_path = "/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/gnomad-2.1.1-genome-GRCh37.zip" // path of gnomad annotation file. Example : annot2_path="/mnt/c/Users/gmillot/Documents/Git_projects/slivar_vcf_extraction/dataset/gnomad-2.1.1-genome-GRCh37.zip", annot2_path="/pasteur/zeus/projets/p02/ghfc_wgs_zeus/references/GRCh37/slivar-gnotate/gnomad-2.1.1-genome-GRCh37.zip" // gnomad annotation
     sample_expr = "--sample-expr 'all:true'" // expression to use for the --sample-expr option of slivar. Example: sample_expr = "--sample-expr 'high_quality:sample.GQ >= 10'". Before the colon is the name of the new field added in the INFO field of the VCF. Write " " if no selection wanted (only annotation). Write "--sample-expr 'all:true'" if no filter wanted but tsv wanted. Warning: all:sample.DP >= 0 is not equivalent to all:true. Of note, "--sample-expr 'all:sample.GQ == \".\"'" is correctly written in the .command.sh file in the work dir of nextflow, but does not seem to work in selecting the empty GQ
     pedigree_expr = " " // expression to use for the --family-expr or --trio or --group-expr option of slivar in order to filter the data according to pedigree info or VCF info (depends on the .js file defined by fun_path above). See https://github.com/brentp/slivar#commands for details. Example: "--family-expr 'aff_only:fam.every(find_het_aff_hom_ref_unaff)'". Write " " if no selection wanted (only annotation). Of note, for no filtering, pedigree_expr="all:fam.every(function(s){return s.affected || s.unaffected})" does not work, we have to use --sample-expr
     filter = "false" // if false, the output VCF is only labeled in the VCF INFO field according to the pedigree_expr parameter. If true, take only the labeled lines (variants) of the output VCF. Of note, true add the --pass-only argument to the slivar expr
@@ -44,7 +44,7 @@ env {
 
 //// must be also exported
 system_exec = 'local' // the system that runs the workflow. Either 'local' or 'slurm'
-out_path_ini = "$baseDir/results" // where the report file will be saved. Example report_path = '.' for where the main.nf run is executed or report_path = '/mnt/c/Users/Gael/Desktop'. Another example : out_path="/pasteur/zeus/projets/p01/BioIT/gmillot/08002_bourgeron/results". Warning: this does not work: out_path="/mnt/share/Users/gael/Desktop"
+out_path_ini = "$baseDir/results" // where the report file will be saved. Example report_path = '.' for where the main.nf run is executed or report_path = '/mnt/c/Users/gmillot/Desktop'. Another example : out_path="/pasteur/zeus/projets/p01/BioIT/gmillot/08002_bourgeron/results". Warning: this does not work: out_path="/mnt/share/Users/gael/Desktop"
 //// end must be also exported
 
 //// General variable