diff --git a/replication/gwascat/README.md b/replication/gwascat/README.md index f072ca7c..37fb45af 100644 --- a/replication/gwascat/README.md +++ b/replication/gwascat/README.md @@ -16,8 +16,8 @@ script using gwas catalog to compared gwas summary statistics to compared gwas s * `head_A1` ["ALLELE1"] * `head_A0` ["ALLELE0"] * gwas catalog : algorithm download version of gwas catalog from ucsc, separate by comma - * `pheno` : un phenotype - * `file_pheno` : file containing list of phenotype extracted from gwas catalog + * `pheno_gc` : phenotype from gwas catalog + * `file_pheno_gc` : file containing list of phenotype extracted from gwas catalog * `list_chro` : list chro to analyse, separate by x-y (x to y) and comma [1-22] * `clump_r2` : min pvalue used for clump and ld * `size_win_kb` : size in kb to analyse used in clump, ld and windows analyse @@ -28,11 +28,11 @@ script using gwas catalog to compared gwas summary statistics to compared gwas s ### list of phenotypes available to obtain list of phenotype without run algorinm """ -nextflow run h3abionet/h3agwas/replication/gwascat/main.nf --justpheno 1 --output_dir gwascatpheno/ --output gwascatpheno -resume -profile slurm +nextflow run h3abionet/h3agwas/replication/gwascat/main.nf --justpheno_gc 1 --output_dir gwascatpheno/ --output gwascatpheno -resume -profile slurm """ ### GWAS catalog : -extract from gwas catalog postiion and chromosome relative to `file_pheno` or `pheno` and `list_chro`. computed heritabilite, beta and se for input +extract from gwas catalog postiion and chromosome relative to `file_pheno_gc` or `pheno_gc` and `list_chro`. computed heritabilite, beta and se for input OR transformed using log2 and defined if column contains information higher than 1 @@ -101,24 +101,21 @@ z values defined as beta / se ### process - * process dl\_gwascat\_hg19 : optional if gwascat is not give as parameter - * process formatgwascat\_pheno : format gwas catalog, if just\_pheno - * process formatgwascat : format gwast catalog - * process extractgwas\_fromgwascat : extract position from gwas present in positoins of gwas catalog +* process dl\_gwascat\_hg19 : optional if gwascat is not give as parameter +* process formatgwascat\_pheno : format gwas catalog, if just\_pheno +* process formatgwascat : format gwast catalog +* process extractgwas\_fromgwascat : extract position from gwas present in positoins of gwas catalog * file description * sub\_plk : sub plink, extracted positions from 1) gwas 2)gwas catalog -process update_rs{ -process clump_aroundgwascat{ -process computedstat_pos{ -process computedstat_windneutre{ -process computedstat_win{ -process computed_ld{ -process computed_ld_stat{ -process computed_clump_stat{ -process build_ldwind{ -process computed_ld2_stat{ -process computed_ldext_stat{ - process computed_ldwind_stat{ -process computed_ldwindext_stat{ +* process update\_rs : process to format plink file with specifi rs +* process clump\_aroundgwascat : clump around each gwas cat +* process computedstat\_pos : exraction of position from gwas catalog on summary statistics +* process computedstat\_windneutre : +* process computedstat\_win : computed statistcs by windows +* process computed\_ld :extraction of positions from gwas catalog and summary statistics in LD +* process computed\_ld\_stat : computed statistics from ` computed\_ld` +* process computed\_clump\_stat : computed statistics using clump function from plink +* process build\_ldwind +* process computed\_ldwind\_stat diff --git a/replication/gwascat/main.nf b/replication/gwascat/main.nf index 7d32d822..bdc33433 100755 --- a/replication/gwascat/main.nf +++ b/replication/gwascat/main.nf @@ -151,7 +151,7 @@ params.gwascat_format="USCS" params.gwas_cat_ftp="http://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/gwasCatalog.txt.gz" -params.file_pheno="" +params.file_pheno_gc="" params.list_chro="1-22" @@ -239,17 +239,17 @@ System.exit(-1) } listchro=getlistchro(params.list_chro) -if(params.file_pheno!=''){ -file_pheno_ch=file(params.file_pheno, checkIfExists:true) +if(params.file_pheno_gc!=''){ +file_pheno_gc_ch=file(params.file_pheno_gc, checkIfExists:true) }else{ -file_pheno_ch=file('nofile') +file_pheno_gc_ch=file('nofile') } process formatgwascat{ label 'R' publishDir "${params.output_dir}/gwascat", mode:'copy' input : file(gwascat) from gwascat_init_ch - file(filepheno) from file_pheno_ch + file(filepheno) from file_pheno_gc_ch output : file("${out}_range.bed") into gwascat_rangebed file("${out}.pos") into (gwascat_pos_subplk, gwascat_pos_ld2, gwascat_pos, gwascat_poswindneutre) @@ -259,7 +259,7 @@ process formatgwascat{ script : chroparam= (params.list_chro=='') ? "" : " --chro ${listchro.join(',')}" phenoparam= (params.pheno_gc=='') ? "" : " --pheno \"${params.pheno_gc}\" " - phenoparam= (params.file_pheno=='') ? " $phenoparam " : " --file_pheno $filepheno " + phenoparam= (params.file_pheno_gc=='') ? " $phenoparam " : " --file_pheno_gc $filepheno " out=params.output+'_gwascat' """ format_gwascat.r --file $gwascat $chroparam $phenoparam --out $out --wind ${params.size_win_kb} --chro_head ${params.head_chro_gwascat} --bp_head ${params.head_bp_gwascat} --pheno_head ${params.head_pheno_gwascat} --beta_head ${params.head_beta_gwascat} --ci_head ${params.head_ci_gwascat} --p_head ${params.head_pval_gwascat} --n_head ${params.head_n_gwascat} --freq_head ${params.head_af_gwascat} --rs_head ${params.head_rs_gwascat} --riskall_head ${params.head_riskall_gwascat} --format $format