Replaced all references of #ID with sample_id

broadinstitute · Oct 2, 2024 · a7a0855 · a7a0855
1 parent 6743cd5
commit a7a0855
Show file tree

Hide file tree

Showing 6 changed files with 11 additions and 13 deletions.
diff --git a/src/WGD/bin/estimatePloidy.R b/src/WGD/bin/estimatePloidy.R
@@ -1042,7 +1042,7 @@ if(kmeans==T){
   #Write out list of cluster assignments per sample
   clusterAssignments.out <- data.frame("ID"=names(clust.PCs$batch), 
                                        "batch"=as.vector(as.integer(clust.PCs$batch)))
-  colnames(clusterAssignments.out)[1] <- "#ID"
+  colnames(clusterAssignments.out)[1] <- "sample_id"
   write.table(clusterAssignments.out, 
               paste(OUTDIR, "/sample_batch_assignments.txt", sep=""), 
               col.names=T, row.names=F, sep="\t", quote=F)
@@ -1052,7 +1052,7 @@ if(kmeans==T){
 
   #Write out list of PCs per sample
   samplePCs.out <- PCs$top
-  colnames(samplePCs.out)[1] <- "#ID"
+  colnames(samplePCs.out)[1] <- "sample_id"
   write.table(samplePCs.out, paste(OUTDIR, "/sample_PCs.txt", sep=""), 
               col.names=T, row.names=F, sep="\t", quote=F)
   if(gzip==T){
@@ -1138,7 +1138,7 @@ dev.off()
 
 #Write table of sexes
 sexes <- sexes[match(colnames(dat)[-c(1:3)], sexes$ID), ]
-colnames(sexes)[1] <- "#ID"
+colnames(sexes)[1] <- "sample_id"
 write.table(sexes, paste(OUTDIR, "/sample_sex_assignments.txt", sep=""), 
             col.names=T, row.names=F, sep="\t", quote=F)
 if(gzip==T){
@@ -1158,13 +1158,13 @@ females.CN[, -1] <- apply(females.CN[, -1], 2, round, digits=2)
 #Merge male/female p-values and rounded CNs
 merged.p <- rbind(males.p, females.p)
 merged.p <- merged.p[match(colnames(dat)[-c(1:3)], merged.p$ID), ]
-colnames(merged.p) <- c("#ID", paste("chr", c(1:22, "X", "Y"), "_pValue", sep=""))
+colnames(merged.p) <- c("sample_id", paste("chr", c(1:22, "X", "Y"), "_pValue", sep=""))
 merged.q <- rbind(males.q, females.q)
 merged.q <- merged.q[match(colnames(dat)[-c(1:3)], merged.q$ID), ]
-colnames(merged.q) <- c("#ID", paste("chr", c(1:22, "X", "Y"), "_qValue", sep=""))
+colnames(merged.q) <- c("sample_id", paste("chr", c(1:22, "X", "Y"), "_qValue", sep=""))
 merged.CN <- rbind(males.CN, females.CN)
 merged.CN <- merged.CN[match(colnames(dat)[-c(1:3)], merged.CN$ID), ]
-colnames(merged.CN) <- c("#ID", paste("chr", c(1:22, "X", "Y"), "_CopyNumber", sep=""))
+colnames(merged.CN) <- c("sample_id", paste("chr", c(1:22, "X", "Y"), "_CopyNumber", sep=""))
 
 #Write merged p-values
 write.table(merged.p, paste(OUTDIR, "/CNA_pValues.txt", sep=""), 

diff --git a/src/WGD/bin/medianCoverage.R b/src/WGD/bin/medianCoverage.R
@@ -122,6 +122,6 @@ if(opts$binwise==TRUE){
   write.table(res,args$args[2], sep="\t", col.names=T, row.names=F, quote=F)
 }else{
   res <- covPerSample(cov,mad=opts$mad)
-  names(res)[1] <- "#ID"
+  names(res)[1] <- "sample_id"
   write.table(res,args$args[2], sep="\t", col.names=T, row.names=F, quote=F)
 }
diff --git a/src/WGD/bin/scoreDosageBiases.R b/src/WGD/bin/scoreDosageBiases.R
@@ -360,7 +360,7 @@ WGD.bins <- merge(WGD.bins,cov[,1:3],by=1:3)
 scores <- scoreSamples(cov,WGD.bins)
 
 #Write scores to file
-colnames(scores)[1] <- "#ID"
+colnames(scores)[1] <- "sample_id"
 write.table(scores,
             paste(OUTDIR,"/WGD_scores.txt",sep=""),
             col.names=T,row.names=F,sep="\t",quote=F)

diff --git a/src/sv-pipeline/00_preprocessing/misc_scripts/RD_matrix_QC.sh b/src/sv-pipeline/00_preprocessing/misc_scripts/RD_matrix_QC.sh
@@ -60,7 +60,7 @@ if [ ${DISTANCE} -lt 1 ]; then
 fi
 
 #Write header for outfile
-echo -e "#ID\tchromosome\tnonzero_bins_in_tail" > ${OUTFILE}
+echo -e "sample_id\tchromosome\tnonzero_bins_in_tail" > ${OUTFILE}
 
 #Iterate over contigs & write results to outfile
 while read contig end; do

diff --git a/src/sv-pipeline/00_preprocessing/misc_scripts/nonRD_matrix_QC.sh b/src/sv-pipeline/00_preprocessing/misc_scripts/nonRD_matrix_QC.sh
@@ -60,7 +60,7 @@ if [ ${DISTANCE} -lt 1 ]; then
 fi
 
 #Write header for outfile
-echo -e "#ID\tchromosome\tlines_in_tail" > ${OUTFILE}
+echo -e "sample_id\tchromosome\tlines_in_tail" > ${OUTFILE}
 
 #Iterate over contigs & write results to outfile
 while read contig end; do

diff --git a/src/sv-pipeline/scripts/make_evidence_qc_table.py b/src/sv-pipeline/scripts/make_evidence_qc_table.py
@@ -9,8 +9,7 @@
 from pathlib import Path
 import numpy as np
 
-ID_COL = "#ID"
-NEW_ID_COL = "sample_id"
+ID_COL = "sample_id"
 EMPTY_OUTLIERS = "EMPTY_ROWS_DROP"
 
 
@@ -217,7 +216,6 @@ def merge_evidence_qc_table(
     output_df = reduce(lambda left, right: pd.merge(left, right, on=ID_COL, how="outer"), dfs)
     output_df = output_df[output_df[ID_COL] != EMPTY_OUTLIERS]
     output_df[outlier_cols] = output_df[outlier_cols].replace([None, np.nan], 0.0)
-    output_df.rename(columns={ID_COL: NEW_ID_COL}, inplace=True)
 
     # save the file
     output_df.to_csv(f"{output_prefix}.evidence_qc_table.tsv", sep="\t", header=True, index=False, na_rep=np.nan)