User:Timothee Flutre/Notebook/Postdoc/2012/01/30: Difference between revisions
From OpenWetWare
(Autocreate 2012/01/30 Entry for User:Timothee_Flutre/Notebook/Postdoc) |
(→Entry title: first version) |
||
| Line 6: | Line 6: | ||
| colspan="2"| | | colspan="2"| | ||
<!-- ##### DO NOT edit above this line unless you know what you are doing. ##### --> | <!-- ##### DO NOT edit above this line unless you know what you are doing. ##### --> | ||
== | ==Use BWA== | ||
* index the whole genome: | |||
echo "bwa index -p wholegenome_bwaidx -a bwtsw wholegenome.fa" | qsub -l h_vmem=5g -N job_wholegenome_bwaidx -j y -cwd -V | |||
* map short sequences on it: | |||
fasta2fastq.py shortseq.fa shortseq.fq 1 | |||
echo "bwa aln wholegenome_bwaidx shortseq.fq > shortseq_bwa_aln.sai" | qsub -l h_vmem=5g -N job_bwa_aln -j y -cwd -V | |||
echo "bwa samse wholegenome_bwaidx shortseq_bwa_aln.sai shortseq.fq > shortseq_bwa_samse.sam" | qsub -l h_vmem=5g -N job_bwa_samse -j y -cwd -V | |||
grep -v "@" shortseq_bwa_samse.sam | awk -F"\t" 'BEGIN{print "flag\toccurrences"} {a[$2]++} END{for(i in a)print i"\t"a[i]}' | |||
parse_sam.py -i shortseq_bwa_samse.sam -e 2 -o shortseq_bwa_uniq_perfect_e2 | |||
* Example for hg19: | |||
wget --timestamping 'ftp://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/chromFa.tar.gz' | |||
tar xzvf chromFa.tar.gz | |||
rm -f hg19_autosomes.fa; for i in {1..22}; do cat "chr"$i".fa" >> hg19_autosomes.fa; done | |||
rm -f hg19_autosomes_sex.fa; for i in "hg19_autosomes.fa" "chrX.fa" "chrY.fa"; do cat $i >> hg19_autosomes_sex.fa; done | |||
<!-- ##### DO NOT edit below this line unless you know what you are doing. ##### --> | <!-- ##### DO NOT edit below this line unless you know what you are doing. ##### --> | ||
Revision as of 08:28, 30 January 2012
 Project name
|
<html><img src="/images/9/94/Report.png" border="0" /></html> Main project page <html><img src="/images/c/c3/Resultset_previous.png" border="0" /></html>Previous entry<html> </html>Next entry<html><img src="/images/5/5c/Resultset_next.png" border="0" /></html> |
Use BWA
echo "bwa index -p wholegenome_bwaidx -a bwtsw wholegenome.fa" | qsub -l h_vmem=5g -N job_wholegenome_bwaidx -j y -cwd -V
fasta2fastq.py shortseq.fa shortseq.fq 1
echo "bwa aln wholegenome_bwaidx shortseq.fq > shortseq_bwa_aln.sai" | qsub -l h_vmem=5g -N job_bwa_aln -j y -cwd -V
echo "bwa samse wholegenome_bwaidx shortseq_bwa_aln.sai shortseq.fq > shortseq_bwa_samse.sam" | qsub -l h_vmem=5g -N job_bwa_samse -j y -cwd -V
grep -v "@" shortseq_bwa_samse.sam | awk -F"\t" 'BEGIN{print "flag\toccurrences"} {a[$2]++} END{for(i in a)print i"\t"a[i]}'
parse_sam.py -i shortseq_bwa_samse.sam -e 2 -o shortseq_bwa_uniq_perfect_e2
wget --timestamping 'ftp://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/chromFa.tar.gz' tar xzvf chromFa.tar.gz rm -f hg19_autosomes.fa; for i in {1..22}; do cat "chr"$i".fa" >> hg19_autosomes.fa; done rm -f hg19_autosomes_sex.fa; for i in "hg19_autosomes.fa" "chrX.fa" "chrY.fa"; do cat $i >> hg19_autosomes_sex.fa; done | |
