Merge pull request #85 from opain/dev

Dev
opain · Mar 3, 2024 · a779998 · a779998
2 parents 36706e9 + d321690
commit a779998
Show file tree

Hide file tree

Showing 21 changed files with 462 additions and 440 deletions.
diff --git a/Scripts/Ancestry_identifier/Ancestry_identifier.R b/Scripts/Ancestry_identifier/Ancestry_identifier.R
diff --git a/Scripts/format_target/format_target.R b/Scripts/format_target/format_target.R
@@ -151,11 +151,9 @@ targ_pvar<-targ_pvar[,c('CHR','BP','SNP','A2','A1'),with=F]
 
 # Label SNP with _dup if the RSID is duplicated, so these variants are removed.
 dup_snp<-duplicated(targ_pvar$SNP)
-log_add(log_file = log_file, message = paste0('Removing ', sum(dup_snp),' duplicate variants.'))
+log_add(log_file = log_file, message = paste0('Removing ', sum(dup_snp),' duplicate variants - May have IUPAC NA.'))
 targ_pvar$SNP[dup_snp]<-paste0(targ_pvar$SNP[dup_snp],'_dup')
 
-log_add(log_file = log_file, message = paste0(sum(!dup_snp)," of ", nrow(ref)," reference variants are in the target."))
-
 # Write out new bim file
 names(targ_pvar)<-c('#CHROM','POS','ID','REF','ALT')
 fwrite(targ_pvar, paste0(tmp_dir,'/subset.pvar'), col.names=T, row.names=F, quote=F, na='NA', sep=' ')
@@ -180,18 +178,22 @@ ref_psam<-fread(paste0(opt$ref,'.psam'))
 names(ref_psam)<-gsub('\\#', '', names(ref_psam))
 ref_psam <- ref_psam[, names(ref_psam) %in% c('FID', 'IID'), with = F]
 if(ncol(ref_psam) == 1){
-  ref_ID_update<-data.frame(ref_psam$`IID`, paste0(ref_psam$`#IID`,'_REF'))
+  ref_ID_update<-data.frame(ref_psam$`IID`, paste0(ref_psam$`IID`,'_REF'))
 } else {
   ref_ID_update<-data.frame(ref_psam$`FID`, ref_psam$`IID`, paste0(ref_psam$`FID`,'_REF'), paste0(ref_psam$`IID`,'_REF'))
 }
 fwrite(ref_ID_update, paste0(tmp_dir,'/ref_ID_update.txt'), sep=' ', col.names=F)
 system(paste0(opt$plink2,' --pfile ',opt$ref,' --make-pgen --update-ids ',tmp_dir,'/ref_ID_update.txt --out ',tmp_dir,'/REF --memory 5000 --threads 1'))
 
 # Merge target and reference plink files to insert missing SNPs
-system(paste0(opt$plink2,' --pfile ',tmp_dir,'/subset --pmerge ',tmp_dir,'/REF --make-pgen --memory 5000 --threads 1 --out ',tmp_dir,'/subset'))
+# plink2's pmerge only handles concatenation for the time being
+# In the meantime, convert the ref and target into plink1 binaries, merge, and then convert back to plink2 binaries
+system(paste0(opt$plink2,' --pfile ',tmp_dir,'/subset --make-bed --memory 5000 --threads 1 --out ',tmp_dir,'/subset'))
+system(paste0(opt$plink2,' --pfile ',tmp_dir,'/REF --make-bed --out ',tmp_dir,'/REF --memory 5000 --threads 1'))
+system(paste0(opt$plink,' --bfile ',tmp_dir,'/subset --bmerge ',tmp_dir,'/REF --make-bed --allow-no-sex --out ',tmp_dir,'/ref_targ'))
 
 # Extract only target individuals
-system(paste0(opt$plink2,' --pfile ',tmp_dir,'/subset --remove ',tmp_dir,'/REF.psam --make-pgen --memory 5000 --threads 1 --out ',opt$output))
+system(paste0(opt$plink2,' --bfile ',tmp_dir,'/ref_targ --remove ',tmp_dir,'/REF.psam --make-pgen --memory 5000 --threads 1 --out ',opt$output))
 
 end.time <- Sys.time()
 time.taken <- end.time - start.time

diff --git a/Scripts/pipeline_reports/indiv_report_creator.Rmd b/Scripts/pipeline_reports/indiv_report_creator.Rmd
@@ -124,11 +124,11 @@ for(chr in CHROMS){
 # Count the number of variants in the target sample data that match reference variants
 nvar_in_target <-
   sum(sapply(format_target_logs, function(x)
-    as.numeric(gsub(' .*', '', x[grepl('reference variants are in the target.$', x)]))))
+    as.numeric(gsub('.* ','', gsub(' reference variants.', '', x[grepl('^Target contains', x) & grepl('reference variants.$', x)])))))
 
 nvar_in_ref <-
   sum(sapply(format_target_logs, function(x)
-    as.numeric(gsub('.* ','', gsub(' reference variants are in the target.', '', x[grepl('reference variants are in the target.$', x)])))))
+    as.numeric(gsub('.* ','', gsub(' variants', '', x[grepl('^Reference data contains ', x)])))))
 
 if(imp_incl){
   

diff --git a/Scripts/pipeline_reports/samp_report_creator.Rmd b/Scripts/pipeline_reports/samp_report_creator.Rmd
@@ -105,11 +105,11 @@ for(chr in CHROMS){
 # Count the number of variants in the target sample data that match reference variants
 nvar_in_target <-
   sum(sapply(format_target_logs, function(x)
-    as.numeric(gsub(' .*', '', x[grepl('reference variants are in the target.$', x)]))))
+    as.numeric(gsub('.* ','', gsub(' reference variants.', '', x[grepl('^Target contains', x) & grepl('reference variants.$', x)])))))
 
 nvar_in_ref <-
   sum(sapply(format_target_logs, function(x)
-    as.numeric(gsub('.* ','', gsub(' reference variants are in the target.', '', x[grepl('reference variants are in the target.$', x)])))))
+    as.numeric(gsub('.* ','', gsub(' variants', '', x[grepl('^Reference data contains ', x)])))))
 
 cat0("- The target sample contains ", nrow(target_psam), " individuals.\n")
 cat0("- The target genotype data was provided in ", target_list$type[target_list$name == params$name], " format.\n")

diff --git a/Scripts/target_scoring/target_scoring.R b/Scripts/target_scoring/target_scoring.R
@@ -80,7 +80,16 @@ if(!is.na(opt$test)){
 #####
 
 log_add(log_file = log_file, message = 'Calculating polygenic scores in the target sample.')
-scores<-plink_score(pfile = opt$target_plink_chr, chr = CHROMS, plink2 = opt$plink2, score = opt$ref_score, keep = opt$target_keep, frq = opt$ref_freq_chr, threads = opt$n_cores)
+scores <-
+  plink_score(
+    pfile = opt$target_plink_chr,
+    chr = CHROMS,
+    plink2 = opt$plink2,
+    score = opt$ref_score,
+    keep = opt$target_keep,
+    frq = opt$ref_freq_chr,
+    threads = opt$n_cores
+  )
 
 ###
 # Scale the polygenic scores based on the reference

diff --git a/docs/Images/OpenSNP/genopred-v1-comp-yengo_eur.png b/docs/Images/OpenSNP/genopred-v1-comp-yengo_eur.png
diff --git a/docs/Images/OpenSNP/genopred-v1-comp_strict-yengo_eur.png b/docs/Images/OpenSNP/genopred-v1-comp_strict-yengo_eur.png
diff --git a/docs/Images/OpenSNP/genopred-v1-comp_strict_eur-yengo_eur.png b/docs/Images/OpenSNP/genopred-v1-comp_strict_eur-yengo_eur.png
diff --git a/docs/Images/OpenSNP/genopred-yengo_eas.png b/docs/Images/OpenSNP/genopred-yengo_eas.png
diff --git a/docs/Images/OpenSNP/genopred-yengo_eur-external.png b/docs/Images/OpenSNP/genopred-yengo_eur-external.png
diff --git a/docs/Images/OpenSNP/genopred-yengo_eur.png b/docs/Images/OpenSNP/genopred-yengo_eur.png
diff --git a/docs/Images/OpenSNP/time_cpu_bench_pgs_methods.csv b/docs/Images/OpenSNP/time_cpu_bench_pgs_methods.csv
@@ -1,8 +1,8 @@
 method,s,h:m:s,max_rss,max_vms,max_uss,max_pss,io_in,io_out,mean_load,cpu_time,file,rule,label
-dbslmm,670.2083,0:11:10,1150.19,518875.48,1127.88,1128.51,0,792.55,7.77,272.6,prep_pgs_dbslmm_i-yengo_eur.txt,prep_pgs_dbslmm_i,DBSLMM
-lassosum,234.1869,0:03:54,4270.06,521977.98,4255.07,4255.75,0,1635.82,43.3,102.93,prep_pgs_lassosum_i-yengo_eur.txt,prep_pgs_lassosum_i,lassosum
-ldpred2,1895.106,0:31:35,20009.57,537189.04,19997.63,19998.87,0,18987.26,23.69,495.81,prep_pgs_ldpred2_i-yengo_eur.txt,prep_pgs_ldpred2_i,LDpred2
-megaprs,3974.4036,1:06:14,12626.76,523095.61,12613.95,12615.65,0,21801.18,293.76,11922.15,prep_pgs_megaprs_i-yengo_eur.txt,prep_pgs_megaprs_i,MegaPRS
-prscs,13389.7369,3:43:09,11977.42,16895.49,7635.95,8028.87,158.48,438.68,938.84,127317.72,prep_pgs_prscs_i-yengo_eur.txt,prep_pgs_prscs_i,PRS-CS
-ptclump,38.5799,0:00:38,391.48,4519.65,378.23,378.57,0,213.75,25.98,12.91,prep_pgs_ptclump_i-yengo_eur.txt,prep_pgs_ptclump_i,pT+clump
-sbayesr,1850.8346,0:30:50,23888.48,45932.89,20929.11,21196.32,0,2811.34,828.8,15532.77,prep_pgs_sbayesr_i-yengo_eur.txt,prep_pgs_sbayesr_i,SBayesR
+dbslmm,584.3754,0:09:44,1250.93,518932.27,1228.86,1235.85,0,832.08,9.55,350.71,prep_pgs_dbslmm_i-yengo_eur.txt,prep_pgs_dbslmm_i,DBSLMM
+lassosum,222.346,0:03:42,4320.55,522076.59,4307.17,4307.96,0,1600.7,45.6,107.35,prep_pgs_lassosum_i-yengo_eur.txt,prep_pgs_lassosum_i,lassosum
+ldpred2,4677.1611,1:17:57,25796.93,537282.12,25580.52,25582.33,0,18703.18,36.04,1752.48,prep_pgs_ldpred2_i-yengo_eur.txt,prep_pgs_ldpred2_i,LDpred2
+megaprs,3931.2688,1:05:31,12622.96,523078.8,12610.11,12610.78,0,21771.48,293.97,11783.88,prep_pgs_megaprs_i-yengo_eur.txt,prep_pgs_megaprs_i,MegaPRS
+prscs,13365.5906,3:42:45,11930.78,16875.75,7588.81,7982.41,0,421.89,942.42,127479.74,prep_pgs_prscs_i-yengo_eur.txt,prep_pgs_prscs_i,PRS-CS
+ptclump,27.0675,0:00:27,399.71,4519.64,385.74,388.07,0,243.38,32.97,12.32,prep_pgs_ptclump_i-yengo_eur.txt,prep_pgs_ptclump_i,pT+clump
+sbayesr,2255.2539,0:37:35,23888.02,45932.63,20929.12,21196.56,0,2877.13,864.48,19629.33,prep_pgs_sbayesr_i-yengo_eur.txt,prep_pgs_sbayesr_i,SBayesR
diff --git a/docs/Images/OpenSNP/time_cpu_bench_pgs_methods.png b/docs/Images/OpenSNP/time_cpu_bench_pgs_methods.png
diff --git a/docs/opensnp_benchmark.Rmd b/docs/opensnp_benchmark.Rmd
@@ -134,7 +134,7 @@ library(data.table)
 
 # Create config file
 conf <- c(
-  'outdir: /users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test4',
+  'outdir: /users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test5',
   'config_file: misc/opensnp/config.yaml',
   'gwas_list: misc/opensnp/gwas_list.txt',
   'score_list: misc/opensnp/score_list.txt',
@@ -228,8 +228,8 @@ library(cowplot)
 # Read in configuration specific benchmark files
 bm_files_i <-
   paste0(
-    '/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test4/reference/benchmarks/',
-    list.files('/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test4/reference/benchmarks/')
+    '/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test5/reference/benchmarks/',
+    list.files('/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test5/reference/benchmarks/')
   )
 
 # Read in benchmark files
@@ -315,7 +315,7 @@ source_all('../functions')
 pheno <- fread('/users/k1806347/oliverpainfel/Data/OpenSNP/processed/pheno/height.txt')
 
 # Define pgs_methods used
-pgs_methods <- c('external','ptclump', 'dbslmm', 'prscs', 'sbayesr', 'lassosum', 'ldpred2', 'megaprs')
+pgs_methods <- c('external',read_param(config = 'misc/opensnp/config.yaml', param = 'pgs_methods', return_obj = F))
 
 # Define pgs_methods applied to non-EUR GWAS
 pgs_methods_eur <- c('ptclump','lassosum','megaprs','prscs','dbslmm')
@@ -673,6 +673,7 @@ keep_list <- fread('/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test1/op
 
 # Read in pgs
 gwas_list <- fread('misc/opensnp/gwas_list.txt')
+gwas_list$name<-gsub('_','',gwas_list$name)
 pgs_methods <- c('pt_clump','dbslmm','prscs','sbayesr','lassosum','ldpred2','megaprs')
 pgs_methods_eur <- c('pt_clump','lassosum','megaprs')
 
@@ -731,6 +732,7 @@ write.csv(
   row.names = F
 )
 
+cor<-fread('/scratch/prj/oliverpainfel/Data/OpenSNP/assoc/genopred-v1-yengo-assoc.csv')
 # Restrict to best only
 cor_subset <- NULL
 for(pop_i in unique(cor$pop)){
@@ -907,6 +909,7 @@ write.csv(
   '/scratch/prj/oliverpainfel/Data/OpenSNP/assoc/genopred-v1-strict-yengo-assoc.csv',
   row.names = F
 )
+cor<-fread('/scratch/prj/oliverpainfel/Data/OpenSNP/assoc/genopred-v1-strict-yengo-assoc.csv')
 
 # Restrict to best only
 cor_subset <- NULL
@@ -1005,7 +1008,7 @@ dev.off()
 # Plot the same plot only using the EUR target population in OpenSNP
 ######
 
-tmp <- cor_both[cor_both$gwas == 'yengoeur' & cor_both$pop == 'EUR\n N = 653', ]
+tmp <- cor_both[cor_both$gwas == 'yengoeur' & grepl('EUR', cor_both$pop), ]
 y_lim <- c(min(tmp$r - tmp$se), max(tmp$r + tmp$se))
 
 v1_plot <-
@@ -1028,7 +1031,7 @@ v1_plot <-
     background_grid() +
     theme(axis.text.x = element_text(angle = 45, hjust = 1),
           plot.title = element_text(hjust = 0.5, size=12)) +
-    facet_grid(pop ~ Version) +
+    facet_grid(. ~ Version) +
     panel_border()
 
 v2_plot <-
@@ -1051,7 +1054,7 @@ v2_plot <-
     background_grid() +
     theme(axis.text.x = element_text(angle = 45, hjust = 1),
           plot.title = element_text(hjust = 0.5, size=12)) +
-    facet_grid(pop ~ Version) +
+    facet_grid(. ~ Version) +
     panel_border()
 
 png('/users/k1806347/oliverpainfel/Software/MyGit/GenoPred/docs/Images/OpenSNP/genopred-v1-comp_strict_eur-yengo_eur.png',
@@ -1078,12 +1081,16 @@ dev.off()
 </div>
 </div>
 
+</br>
+
 <div class="centered-container">
 <div class="rounded-image-container">
 ![Using same ancestry classification threshold](Images/OpenSNP/genopred-v1-comp_strict-yengo_eur.png)
 </div>
 </div>
 
+</br>
+
 <div class="centered-container">
 <div class="rounded-image-container" style="width: 60%;">
 ![Showing results in European OpenSNP data only](Images/OpenSNP/genopred-v1-comp_strict_eur-yengo_eur.png)

diff --git a/docs/opensnp_benchmark.html b/docs/opensnp_benchmark.html
@@ -13,7 +13,7 @@
 
 <title>OpenSNP Benchmark</title>
 
-<script src="site_libs/header-attrs-2.23/header-attrs.js"></script>
+<script src="site_libs/header-attrs-2.25/header-attrs.js"></script>
 <script src="site_libs/jquery-3.6.0/jquery-3.6.0.min.js"></script>
 <meta name="viewport" content="width=device-width, initial-scale=1" />
 <link href="site_libs/bootstrap-3.3.5/css/cosmo.min.css" rel="stylesheet" />
@@ -35,8 +35,8 @@
 <script src="site_libs/navigation-1.1/tabsets.js"></script>
 <link href="site_libs/highlightjs-9.12.0/default.css" rel="stylesheet" />
 <script src="site_libs/highlightjs-9.12.0/highlight.js"></script>
-<link href="site_libs/font-awesome-6.4.0/css/all.min.css" rel="stylesheet" />
-<link href="site_libs/font-awesome-6.4.0/css/v4-shims.min.css" rel="stylesheet" />
+<link href="site_libs/font-awesome-6.4.2/css/all.min.css" rel="stylesheet" />
+<link href="site_libs/font-awesome-6.4.2/css/v4-shims.min.css" rel="stylesheet" />
 <link rel="stylesheet" href="styles/night-mode.css" id="nightModeStylesheet">
 
 <script>
@@ -531,7 +531,7 @@ <h3>Create gwas_list, target_list and config</h3>
 
 # Create config file
 conf &lt;- c(
-  &#39;outdir: /users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test4&#39;,
+  &#39;outdir: /users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test5&#39;,
   &#39;config_file: misc/opensnp/config.yaml&#39;,
   &#39;gwas_list: misc/opensnp/gwas_list.txt&#39;,
   &#39;score_list: misc/opensnp/score_list.txt&#39;,
@@ -603,7 +603,8 @@ <h2>Run GenoPred</h2>
 <summary>
 Show code
 </summary>
-<pre class="bash"><code>snakemake --profile slurm --use-conda --configfile=misc/opensnp/config.yaml output_all -n </code></pre>
+<pre class="bash"><code>snakemake --profile slurm --use-conda --configfile=misc/opensnp/config.yaml output_all -n 
+snakemake --profile slurm --use-conda --configfile=misc/opensnp/config.yaml outlier_detection -n </code></pre>
 </details>
 <hr />
 </div>
@@ -620,8 +621,8 @@ <h2>Check time and memory requirements</h2>
 # Read in configuration specific benchmark files
 bm_files_i &lt;-
   paste0(
-    &#39;/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test4/reference/benchmarks/&#39;,
-    list.files(&#39;/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test4/reference/benchmarks/&#39;)
+    &#39;/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test5/reference/benchmarks/&#39;,
+    list.files(&#39;/users/k1806347/oliverpainfel/Data/OpenSNP/GenoPred/test5/reference/benchmarks/&#39;)
   )
 
 # Read in benchmark files
@@ -706,7 +707,7 @@ <h2>Evaluate PGS</h2>
 pheno &lt;- fread(&#39;/users/k1806347/oliverpainfel/Data/OpenSNP/processed/pheno/height.txt&#39;)
 
 # Define pgs_methods used
-pgs_methods &lt;- c(&#39;external&#39;,&#39;ptclump&#39;, &#39;dbslmm&#39;, &#39;prscs&#39;, &#39;sbayesr&#39;, &#39;lassosum&#39;, &#39;ldpred2&#39;, &#39;megaprs&#39;)
+pgs_methods &lt;- c(&#39;external&#39;,read_param(config = &#39;misc/opensnp/config.yaml&#39;, param = &#39;pgs_methods&#39;, return_obj = F))
 
 # Define pgs_methods applied to non-EUR GWAS
 pgs_methods_eur &lt;- c(&#39;ptclump&#39;,&#39;lassosum&#39;,&#39;megaprs&#39;,&#39;prscs&#39;,&#39;dbslmm&#39;)
@@ -1061,6 +1062,7 @@ <h2>Evaluate PGS</h2>
 
 # Read in pgs
 gwas_list &lt;- fread(&#39;misc/opensnp/gwas_list.txt&#39;)
+gwas_list$name&lt;-gsub(&#39;_&#39;,&#39;&#39;,gwas_list$name)
 pgs_methods &lt;- c(&#39;pt_clump&#39;,&#39;dbslmm&#39;,&#39;prscs&#39;,&#39;sbayesr&#39;,&#39;lassosum&#39;,&#39;ldpred2&#39;,&#39;megaprs&#39;)
 pgs_methods_eur &lt;- c(&#39;pt_clump&#39;,&#39;lassosum&#39;,&#39;megaprs&#39;)
 
@@ -1119,6 +1121,7 @@ <h2>Evaluate PGS</h2>
   row.names = F
 )
 
+cor&lt;-fread(&#39;/scratch/prj/oliverpainfel/Data/OpenSNP/assoc/genopred-v1-yengo-assoc.csv&#39;)
 # Restrict to best only
 cor_subset &lt;- NULL
 for(pop_i in unique(cor$pop)){
@@ -1295,6 +1298,7 @@ <h2>Evaluate PGS</h2>
   &#39;/scratch/prj/oliverpainfel/Data/OpenSNP/assoc/genopred-v1-strict-yengo-assoc.csv&#39;,
   row.names = F
 )
+cor&lt;-fread(&#39;/scratch/prj/oliverpainfel/Data/OpenSNP/assoc/genopred-v1-strict-yengo-assoc.csv&#39;)
 
 # Restrict to best only
 cor_subset &lt;- NULL
@@ -1393,7 +1397,7 @@ <h2>Evaluate PGS</h2>
 # Plot the same plot only using the EUR target population in OpenSNP
 ######
 
-tmp &lt;- cor_both[cor_both$gwas == &#39;yengoeur&#39; &amp; cor_both$pop == &#39;EUR\n N = 653&#39;, ]
+tmp &lt;- cor_both[cor_both$gwas == &#39;yengoeur&#39; &amp; grepl(&#39;EUR&#39;, cor_both$pop), ]
 y_lim &lt;- c(min(tmp$r - tmp$se), max(tmp$r + tmp$se))
 
 v1_plot &lt;-
@@ -1416,7 +1420,7 @@ <h2>Evaluate PGS</h2>
     background_grid() +
     theme(axis.text.x = element_text(angle = 45, hjust = 1),
           plot.title = element_text(hjust = 0.5, size=12)) +
-    facet_grid(pop ~ Version) +
+    facet_grid(. ~ Version) +
     panel_border()
 
 v2_plot &lt;-
@@ -1439,7 +1443,7 @@ <h2>Evaluate PGS</h2>
     background_grid() +
     theme(axis.text.x = element_text(angle = 45, hjust = 1),
           plot.title = element_text(hjust = 0.5, size=12)) +
-    facet_grid(pop ~ Version) +
+    facet_grid(. ~ Version) +
     panel_border()
 
 png(&#39;/users/k1806347/oliverpainfel/Software/MyGit/GenoPred/docs/Images/OpenSNP/genopred-v1-comp_strict_eur-yengo_eur.png&#39;,
@@ -1465,6 +1469,7 @@ <h2>Evaluate PGS</h2>
 </div>
 </div>
 </div>
+<p></br></p>
 <div class="centered-container">
 <div class="rounded-image-container">
 <div class="figure">
@@ -1474,6 +1479,7 @@ <h2>Evaluate PGS</h2>
 </div>
 </div>
 </div>
+<p></br></p>
 <div class="centered-container">
 <div class="rounded-image-container" style="width: 60%;">
 <div class="figure">

diff --git a/docs/pipeline_readme.Rmd b/docs/pipeline_readme.Rmd
@@ -974,7 +974,7 @@ Outputs specific to the configuration used are stored in the `outdir` specified
   │       ├── [target_name]-report.html (sample-level report)
   │       └── individual (individual-level reports)
   │    
-  └── reference (nextflow pipeline execution data)
+  └── reference
       ├── gwas_sumstat (processed gwas sumstats)
       │   └── [gwas name] (pgs for each gwas or score file)
       ├── pgs_score_files (score files for polygenic scoring)

diff --git a/docs/pipeline_readme.html b/docs/pipeline_readme.html
@@ -1643,7 +1643,7 @@ <h2>Output structure</h2>
   │       ├── [target_name]-report.html (sample-level report)
   │       └── individual (individual-level reports)
   │    
-  └── reference (nextflow pipeline execution data)
+  └── reference
       ├── gwas_sumstat (processed gwas sumstats)
       │   └── [gwas name] (pgs for each gwas or score file)
       ├── pgs_score_files (score files for polygenic scoring)