NGS training @GIS - continued

###########day 2 de novo assemble


PATH=/mnt/software/assemblers/velvet:/usr/local/samtools:/usr/local/samtools/bcftools:/mnt/software/mappers/bwa:$PATH

#1. create simulated data
cd ~/refgenome
/mnt/software/mappers/samtools/samtools-0.1.7/misc/wgsim reference.fa NC_1.fastq NC_2.fastq
cd ~/prj2
mv ../refgenome/NC_*.fastq ./
shuffleSequences_fastq.pl ./NC_1.fastq ./NC_2.fastq NC.fastq

#2. velvet
velveth velvet 21 -fastq -shortPaired NC.fastq
velvetg velvet -ins_length 300 -exp_cov 1 -read_trkg yes -amos_file yes



#############day 2 ANNOVAR
PATH=$PATH:/home/javeda/ANNOVAR/annovar
cd ~/prj3
cp ../prj1/var.filt.vcf ./
convert2annovar.pl ./var.filt.vcf -format vcf4 -includeinfo >var.filt.vcf.avinput
awk 'BEGIN {FS="\t"} {$1="chr17"; $2=$2+46000000; $3=$3+46000000; print}' var.filt.vcf.avinput >variant1.avinput

#Gene-based annotation
annotate_variation.pl -buildver hg19 variant1.avinput /home/javeda/ANNOVAR/annovar/humandb/
more variant1.avinput.exonic_variant_function

#Region-based annotation
annotate_variation.pl -dbtype band -regionanno  -buildver hg19 variant1.avinput /home/javeda/ANNOVAR/annovar/humandb/
more variant1.avinput.hg19_cytoBand

#Filter-based annotation
annotate_variation.pl -buildver hg19 -filter -dbtype snp131 variant1.avinput /home/javeda/ANNOVAR/annovar/humandb/
more variant1.avinput.hg19_cytoBand

#snps found in dbsnp131
more variant1.avinput.hg19_snp131_dropped

#snps not in dbsnp131
more variant1.avinput.hg19_snp131_filtered