new file: cre.coverage.sh

	modified:   cre.gemini_load.sh
	modified:   cre.prepare_bcbio_run.sh
	modified:   cre.sh
	deleted:    xhmm.sh

cre.coverage.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#average coverage and % of bases covered at 10x
+#total 35,405,680, 22387 genes
+
+for f in *.coverage;do cat $f  | sed 1d | awk '{if ($9<10) print $0}'  | awk '{print $4}'  > $f.bad_genes.txt;done;
+for f in *.bad_genes.txt; do for gene in `cat $f`;do cat protein_coding_genes.exons.fixed.bed | grep $gene >> $f.exon_lengths;done;done;
+for f in *.exon_lengths;do echo $f;cat $f | awk '{sum+=$3-$2+1}END{print sum}';done;

cre.gemini_load.sh

@@ -1,4 +1,4 @@
-#/bin/bash
+#!/bin/bash
 
 #vep2gemini - loads vep annotated vcf file to gemini database 
 #based on  bcbio.log

cre.prepare_bcbio_run.sh

@@ -3,7 +3,7 @@
 # prepares family for bcbio run when input files are family_sample.bam or family_sample_1/2.fq.gz
 family=$1
 
-#$2=template type, no value - default WES, noalign - no alignment (for rerunning), fast - no realignment,recalibration, and only gatk
+#$2 = template type, no value - default WES, noalign - no alignment (for rerunning), fast - no realignment,recalibration, and only gatk
 template_type=$2
 echo $template_type
 

cre.sh

@@ -52,7 +52,7 @@ function f_cleanup
 
     if [ "$type" == "wes.fast" ]
     then
-	cp ${family}-gatk-haplotype.db ${family}-ensemble.db
+	ln -s ${family}-gatk-haplotype.db ${family}-ensemble.db
 	ln -s ${family}-gatk-haplotype-annotated-decomposed.vcf.gz ${family}-ensemble-annotated-decomposed.vcf.gz
 	ln -s ${family}-gatk-haplotype-annotated-decomposed.vcf.gz.tbi ${family}-ensemble-annotated-decomposed.vcf.gz.tbi
     else