new file: cram2bam.sh

	new file:   cram2fq.sh
	modified:   cre.bcbio.upgrade.sh
	new file:   cre.validation.sh
	new file:   cron_rsync_uploads.sh
	new file:   omim.inheritance.parse_orion.py
	modified:   omim.inheritance.py

cram2bam.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+#PBS -l walltime=10:00:00,nodes=1:ppn=1
+#PBS -joe .
+#PBS -d .
+#PBS -l vmem=20g,mem=20g
+
+module load java
+
+cramtools bam -I $cram -O $bam -b -R $ref

cram2fq.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+#PBS -l walltime=10:00:00,nodes=1:ppn=1
+#PBS -joe .
+#PBS -d .
+#PBS -l vmem=20g,mem=20g
+
+# reference should be decompressed and indexed: using one from bcbio
+# usually crams come with hg19 reference (chr), not GRCh37
+
+
+module load java
+
+cramtools fastq -Xmx10g -F $sample --skip-md5-check \
+		-z \
+		-I $cram \
+		-R /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/hg19/seq/hg19.fa

cre.bcbio.upgrade.sh

@@ -6,10 +6,10 @@
 #upgrade code to stable version
 #bcbio_nextgen.py upgrade -u stable
 #upgrade code to development
-#bcbio_nextgen.py upgrade -u development
+bcbio_nextgen.py upgrade -u development
 
 #upgrade tools
-bcbio_nextgen.py upgrade -u skip --tools
+#bcbio_nextgen.py upgrade -u skip --tools
 
 #check tools
 #bcbio_conda list | grep vep

cre.validation.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+export PATH=/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/anaconda/bin:$PATH &&  export RTG_JAVA_OPTS='-Xms750m' && export RTG_MEM=10000m && rtg vcfeval --threads 1  \
+    -b /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/validation/giab-NA12878/truth_small_variants.vcf.gz \
+    --bed-regions /hpf/largeprojects/ccmbio/naumenko/validation/lynette/work/validate/NA12878-1/ensemble/NA12878-1-sort-callable_sample-NA12878-1-ensemble-wrm.bed \
+    -c $1 \
+    -t /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/rtg/GRCh37.sdf -o rtg --vcf-score-field='GQ'
+
+for f in {tp,fp,fn};
+do
+    echo snp $f `bcftools view --types snps rtg/$f.vcf.gz | grep -vc "^#"` >> $1.stat
+    echo indels $f `bcftools view --exclude-types snps rtg/$f.vcf.gz | grep -vc "^#"` >> $1.stat
+done

cron_rsync_uploads.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+# push files from the uploader to hpf
+# ssh cron1
+
+echo "$(date)"
+
+magic_path=/hpf/tools/centos6/python/2.7.11
+
+export PATH=$magic_path/bin:$PATH
+export LD_LIBRARY_PATH=$magic_path/lib/:$LD_LIBRARY_PATH
+export PYTHONPATH=$magic_path:$PYTHONPATH
+export LD_LIBRARY_PATH=$magic_path/usr/lib64/atlas:$LD_LIBRARY_PATH
+
+python /hpf/largeprojects/ccm_dccforge/dccforge/cron/cron_rsync_uploads.py

omim.inheritance.parse_orion.py

@@ -0,0 +1,51 @@
+#!/usr/bin/python
+
+# extracts information about omim inheritance modes from https://www.cs.toronto.edu/~buske/cheo/
+
+import re
+from os.path import expanduser
+
+home = expanduser('~')
+
+inheritance = {}
+inheritance['Autosomal recessive']='AR'
+inheritance['Autosomal dominant'] = 'AD'
+inheritance['X-linked recessive'] = 'XLR'
+inheritance['X-linked dominant'] = 'XLD'
+inheritance['Isolated cases'] = 'IC'
+inheritance['Mitochondrial'] = 'Mi'
+inheritance['X-linked'] = 'XL'
+inheritance['Y-linked'] = 'YL'
+inheritance['Digenic recessive'] = 'DR'
+inheritance['Digenic dominant'] = 'DD'
+inheritance['Multifactorial'] = 'Mu'
+inheritance['Somatic mosaicism'] = 'Smo'
+inheritance['Somatic mutation'] = 'Smu'
+
+genes = {}
+
+f1 = open(home+'/cre/ensembl_w_description.txt','r')
+for line in f1:
+    ar = line.split('\t')
+    genes[ar[0]] = ar[1]
+f1.close()
+
+f = open('genemap2.txt','r')
+
+print 'Ensembl_gene_id Gene_name2 Omim_inheritance'
+
+for line in f:
+    #print line,
+    match = re.search(r'ENSG[0-9]{11}',line)
+    if match:
+	modes = []
+	#print 'found', match.group()
+	for key in inheritance.keys():
+	    match1 = re.search(key,line)
+	    if match1:
+		#print 'found inheritance', match1.group()
+		modes.append(inheritance[key])
+	if len(modes)>0:
+	    print match.group(), genes.get(match.group()), ','.join(modes)
+
+f.close()

omim.inheritance.py

@@ -30,12 +30,15 @@
     genes[ar[0]] = ar[1]
 f1.close()
 
-f = open('genemap2.txt','r')
+#save non empty lines 
+#gene	inheritance
+f = open('omim_by_orion.txt','r')
 
 print 'Ensembl_gene_id Gene_name2 Omim_inheritance'
 
 for line in f:
-    #print line,
+    ar = line.split('\t')
+
     match = re.search(r'ENSG[0-9]{11}',line)
     if match:
 	modes = []