modified: bcbio.prepare_families.sh

	new file:   fixit.sh
	new file:   vcf.split_multi.sh

bcbio.prepare_families.sh

@@ -2,7 +2,8 @@
 
 # prepares a run of multiples families to run variant calling, one family may have several samples
 # $1 - a file table.txt in the format
-# sample_id	family_id	absolute_path_to_bam_file
+# sample_id	family_id	absolute_path_to_bam_file, i.e.
+# 531_IN0067	531	/hpf/largeprojects/ccm_dccforge/dccdipg/dccc4r/c4r_wes/bam_files/531_IN0067.bam
 # creates one project per family
 # 
 # run with 

fixit.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+#$1 = family_id
+
+cat samples.txt | awk -v fam=$1 '{print fam"_"$1}' > samples.txt.fixed
+rm samples.txt
+mv samples.txt.fixed samples.txt
+
+for f in *ready.bam.bai;do mv $f `echo $f | sed s/"-ready"//`;done;
+for f in *ready.bam;do mv $f `echo $f | sed s/"-ready"//`;done;
+for f in *.bam;do mv $f `echo ${1}_${f}`;done;
+for f in *.bam.bai;do mv $f `echo ${1}_${f}`;done;
+
+
+for f in *.vcf.gz;do bcftools reheader -s samples.txt $f  > $f.reheader;done;
+rm *.vcf.gz
+for f in *.reheader;do mv $f `echo $f | sed s/.reheader//`;done;
+for f in *.vcf.gz; do tabix $f;done;
+
+vcf.split_multi.sh $1.vcf.gz
+
+# run gemini db gemini.vep2gemini.sh ${family}-ensemble-annotated-decomposed.vcf.gz
+# rerun cre.sh

vcf.split_multi.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+# $1 = family.vcf.gz
+
+for sample in `cat samples.txt`; 
+do 
+    bcftools view -c1 -Ov -s $sample -o $sample.vcf $1;
+done;