modified: README.md

	modified:   cre.annotate_str.sh
	new file:   cre.roh.sh
	modified:   cre.sh
	modified:   cre.vep.sh

README.md

@@ -71,7 +71,7 @@ or use qsub, if you have a large cohort:
 qsub ~/cre/bcbio.prepare_families.sh	-v project_list=table.txt
 ```
 
-The script will prepare a folder for each project(family) using [bcbio.templates.exome.yaml](../master/bcbio.templates.exome.yaml) template.
+The script will prepare a folder for each project(family) using [bcbio.templates.wes.yaml](../master/bcbio.templates.wes.yaml) template.
 Using this template is important, because later the report will be produced from 4 callers.
 
 The details of the template:

cre.annotate_str.sh

@@ -14,6 +14,6 @@ tabix $bname.sorted.vcf.gz
 #there may be no gene
 vcfanno -base-path ~/cre/ ~/cre/cre.annotate_str.toml $bname.sorted.vcf.gz > $bname.annotated.vcf
 rm $bname.insertions.txt
-echo -e "CHR\tPOS\tREF\tALT\tGENE\tGENOTYPE\tINSERTION_LENGTH_BP" > $bname.insertions.txt
-cat $bname.annotated.vcf | grep -v "^#" | sed s/"gene="/"\t"/g | grep "0/1:" | awk '{print $1"\t"$2"\t"$4"\t"$5"\t"$9"\t"$NF}' | sed s/":.*"// | \
-    awk '{if (length($3)<length($4)) print $0"\t"length($4)-length($3);}' | sort -k7,7 -rn >> $bname.insertions.txt
+echo -e "CHR\tPOS\tREF\tALT\tGENE\tINSERTION_LENGTH_BP" > $bname.insertions.txt
+cat $bname.annotated.vcf | grep -v "^#" | sed s/"gene="/"\t"/g | awk '{print $1"\t"$2"\t"$4"\t"$5"\t"$9}' | awk '{if (length($3)<length($4)) print $0"\t"length($4)-length($3);}' | sort -k6,6 -rn | \
+    sed s/"GT.*STITCH"/NA/g >> $bname.insertions.txt

cre.roh.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+#PBS -l walltime=10:00:00,nodes=1:ppn=1
+#PBS -joe .
+#PBS -d .
+#PBS -l vmem=20g,mem=20g
+
+#ROH analysis with 
+#https://sourceforge.net/projects/h3m2/files/
+
+export H3M2PATH=/hpf/largeprojects/ccmbio/naumenko/tools/H3M2Tool
+
+$H3M2PATH/H3M2BamParsing.sh $H3M2PATH . $bam . LOH_analysis `basename $bam .bam` /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa $H3M2PATH/SNP1000GP.HGb37_Exome.bed
+
+$H3M2PATH/H3M2Analyze.sh $H3M2PATH . LOH_analysis `basename $bam .bam` $H3M2PATH/SNP1000GP.HGb37_Exome.bed 100000 0.1 0.1 5
+
+#DNorm -> parameter of the H3M2 (it can be 1000, 10000 and 100000. We suggest to use 100000)
+#P1 -> parameter of the H3M2 (set to 0.1)
+#P2 -> parameter of the H3M2 (set to 0.1)
+#Factor -> parameter of the H3M2 (set to 5)
+

cre.sh

@@ -59,10 +59,10 @@ function f_cleanup
     fi
 
     # we don't need gemini databases for particular calling algorythms
-    rm ${family}-freebayes.db
-    rm ${family}-gatk-haplotype.db
-    rm ${family}-samtools.db
-    rm ${family}-platypus.db
+    #rm ${family}-freebayes.db
+    #rm ${family}-gatk-haplotype.db
+    #rm ${family}-samtools.db
+    #rm ${family}-platypus.db
 
     cd ..
 }

cre.vep.sh

@@ -7,7 +7,7 @@
 #PBS -l walltime=10:00:00,nodes=1:ppn=1
 #PBS -joe .
 #PBS -d .
-#PBS -l vmem=20g,mem=20g
+#PBS -l vmem=30g,mem=30g
 
 if [ -z $vcf ];
 then