new file: HISTORY.md

	modified:   bcbio.array.pbs
	modified:   bcbio.pbs
	modified:   bcbio.templates.exome.yaml
	modified:   cre.sh
	modified:   gemini.vep.refseq.sh

HISTORY.md

@@ -0,0 +1 @@
+- 2017-07-04: bcbio uses vep-merged, a merged cache of refseq and vep, no need to annotate with refseq anymore

bcbio.array.pbs

@@ -13,6 +13,8 @@
 
 echo "START: " `date`;
 
+hostname
+
 module load java/1.8.0_91
 project=`cat projects.txt | head -n $PBS_ARRAYID | tail -n1`
 

bcbio.pbs

@@ -10,6 +10,7 @@
 #PBS -l vmem=50g,mem=50g
 
 echo "START: " `date`;
+hostname
 
 module load java/1.8.0_91
 

bcbio.templates.exome.yaml

@@ -8,6 +8,7 @@ details:
       use_filtered: false
     realign: true
     recalibrate: true
+    mark_duplicates: true
     save_diskspace: true
     tools_on:
     - svplots

cre.sh

@@ -14,14 +14,15 @@
 #PBS -d .
 #PBS -l vmem=20g,mem=20g
 
+
 function f_cleanup
 {
 
     # better to look for project-summary than hardcode the year
     # keep bam files for new samples
     cd $family
     result_dir=`find final -name project-summary.yaml | sed s/"\/project-summary.yaml"//`
-    if [ -d $result_dirt ];
+    if [ -d $result_dir ];
     then
 	mv $result_dir/* .
 	mv final/*/*.bam .

gemini.vep.refseq.sh

@@ -20,8 +20,8 @@ fi
 
 bname=`echo $vcf | sed s/.vcf.gz//`
 
-unset PERL5LIB && export PATH=/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/anaconda/bin:$PATH && /home/naumenko/work/tools/bcbio/anaconda/bin/variant_effect_predictor.pl --vcf -o stdout \
-    -i $vcf --species homo_sapiens_refseq --no_stats --cache --offline --dir /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/vep --symbol --numbers --biotype --total_length \
+unset PERL5LIB && export PATH=/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/anaconda/bin:$PATH && /home/naumenko/work/tools/bcbio/anaconda/bin/vep --vcf -o stdout \
+    -i $vcf --species homo_sapiens_merged --no_stats --cache --offline --dir /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/vep --symbol --numbers --biotype --total_length \
     --canonical --gene_phenotype --ccds --fields Consequence,Codons,Amino_acids,Gene,SYMBOL,Feature,EXON,PolyPhen,SIFT,Protein_position,BIOTYPE,CANONICAL,CCDS,HGVSc,HGVSp \
     --plugin LoF,human_ancestor_fa:/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/human_ancestor.fa.gz --sift b --polyphen b --hgvs --shift_hgvs 1 \
     --fasta /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa \