Changes between Initial Version and Version 1 of VCFAggregateScriptManual

Timestamp:

2014-09-16T17:41:13+02:00 (11 years ago)

Author:

jvelde

Comment:

--

VCFAggregateScriptManual

@@ +1 @@
+Placeholder
+
+http://sourceforge.net/projects/samtools/files/tabix/
+http://vcftools.sourceforge.net/
+
+https://github.com/molgenis/ngs-utils/blob/master/scripts/vcf-fill-gtc.pl
+
+Super important:
+#  -ss       : remove sample details!
+
+
+
+
+#
+# Add bgzip and tabix to your environment.
+#
+export PATH=/Volumes/Users/Software/vcftools_0.1.10/bin/:/Volumes/Users/Software/tabix-0.2.6/:${PATH}
+
+#
+# Prepare sample VCFs for one batch; e.g. CAR_Batch1_106Samples
+#
+cd /Volumes/CardioKitVCFs/OriginalVCFs/CAR_Batch1_106Samples
+# Fix missing '>' at the end of contig meta-data lines.
+perl -pi -e 's/(contig=<ID=[^>\n]+)$/$1>/' CAR_*/*.vcf
+# Sort, filter on 'PASS', bgzip and index with tabix (vcftools will not work on uncompressed, unindexed VCF files.)
+for item in $(ls CAR_*/*.vcf); \
+do echo "Processing $item..."; \
+vcf-sort $item | vcf-annotate -H > $item\.sorted\.filtered; \
+bgzip $item\.sorted\.filtered; \
+tabix -p vcf $item\.sorted\.filtered\.gz; \
+done
+
+#
+# Merge sample VCFs into one batch VCF.
+#
+vcf-merge CAR_*/*.vcf.sorted.filtered.gz | bgzip -c > merged.vcf.gz
+
+#
+# Create a summary VCF per batch:
+#  -ss       : remove sample details!
+#  -fv PASS  : keep only high quality variant calls that pass all filters applied in NextGene.
+#              Just to be sure: variants should already have been filtered on PASS only in a previous step,
+#              so this should be redundant here...
+#  -si       : remove all INFO subfields except for INFO:AN and INFO:AC.
+#              INFO:AN and INFO:AC were automatically updated by vcf-merge,
+#              but the others were not and may contain erroneous annotation
+#              that cause vcf-validator to complain the created VCF is not valid.
+#
+~pneerincx/EclipseWorkspace/ngs_scripts/vcf-fill-gtc.pl -vcfi merged.vcf.gz -vcfo stripped.vcf -ss -fv PASS -si -ll INFO > stripped.vcf.log
+mv stripped.vcf      ../CAR_Batch1_106Samples.vcf
+mv stripped.vcf.log  ../CAR_Batch1_106Samples.vcf.log