Dinh/Dinh 2013/NOTES/2013-6-24: Difference between revisions

From ZhangLabWiki
Jump to navigation Jump to search
>Dinh
mNo edit summary
>Dinh
mNo edit summary
Line 41: Line 41:
| 7||546,091||35,800||6.55568||239459||43.8497
| 7||546,091||35,800||6.55568||239459||43.8497
|}
|}
== Alignment with Bowtie2 ==
* The long reads were not compatible with our pipeline using Bowtie2, because the aligner suppresses read name lines which are longer than 256 characters.
* Added code to split long reads into multiple short reads to use Bowtie2
* Ran mapping pipeline:
<nowiki>
cur_dir="/media/3TB_Dinh/Blueprint"
reads_dir="/media/3TB_Dinh/Blueprint"
email="diep.hue.dinh@gmail.com"
bisReadMapper="/home/ddiep/scripts/MethylationPipeline/scripts/smartBisReadMapper.pl"
template_fwd="/media/2TB_storeA/BisRef/bisHg19/hg19.fa.bis.fwd.bowtie2"
template_rev="/media/2TB_storeA/BisRef/bisHg19/hg19.fa.bis.rev.bowtie2"
template_fa="/media/2TB_storeA/BisRef/bisHg19/hg19.fa"
soap="/home/ddiep/softwares/soap2.21release/soap"
bowtie="bowtie2"
cpg="/media/2TB_storeA/BisRef/bisHg19/C_Pos/hg19.fa.cpg.positions.txt"
INDX="1Index1_S1 1Index2_S2 1Index3_S3 2Index4_S6 1Index5_S4 2Index6_S7 2Index7_S8 1Index8_S5"
# make sure the qual_base variable is set correctly
cd $cur_dir
for s in ${INDX}
do
f="$s.fq"
g="$s.leftR1.fq"
h="$s.leftR2.fq"
n="$s-MS"
mkdir $n
echo "cd $cur_dir/$n" >> $n.job
echo "$bisReadMapper -r $reads_dir/$f -W $template_fwd -C $template_rev -g $template_fa -a $bowtie -p 16 -b 33 -n $n.f1 -q 20 -l $cpg > $n.f1.statusMbias 2>$n.f1.err" >> $n.job
echo "$bisReadMapper -r $reads_dir/$g -W $template_fwd -C $template_rev -g $template_fa -a $bowtie -p 16 -b 33 -n $n.f2 -q 20 -l $cpg > $n.f2.statusMbias 2>$n.f2.err" >> $n.job
echo "$bisReadMapper -r $reads_dir/$h -W $template_fwd -C $template_rev -g $template_fa -a $bowtie -p 16 -b 33 -n $n.f3 -q 20 -l $cpg > $n.f3.statusMbias 2>$n.f3.err" >> $n.job
echo "rm *encoded" >> $n.job
#sh $n.job
#qsub -q home-k4zhang $n.job
done
</nowiki>

Revision as of 20:56, 24 June 2013

Analysis of Blueprint MiSeq Test Run

Pre-processing

  • Obtain UMI from the first 10bp of read 1, label both reads with UMI
  • Trim 27 bp from 5 prime end of read 1 and read 2
  • Create kmer_table for COPE
  • Use COPE to combine overlapping read 1 and read 2
for f in 1Index1_S1 1Index2_S2 1Index3_S3 2Index4_S6 1Index5_S4 2Index6_S7 2Index7_S8 1Index8_S5
do

	./getUMI.pl 130620_MiSeq/TES1-${f}_L001_R1_001.fastq 130620_MiSeq/TES1-${f}_L001_R2_001.fastq $f
	~/softwares/cope-src-v1.1.3/src/cope -a $f.R1.fq -b $f.R2.fq -o $f.fq -2 $f.leftR1.fq -3 $f.leftR2.fq -m 1  -t kmer_table.freq.cz -f kmer_table.freq.cz.len >cope.$f.log 2>cope.$f.error
	rm $f.R1.fq $f.R2.fq
done

COPE results

index total_pairs connected_pairs connect_ratio(%) low_quality_pairs low_quality_ratio(%)
1 546,091 37,624 6.88969 239413 43.8412
2 1,201,482 76,332 6.35315 603335 50.2159
3 2,107,061 120,889 5.73733 1155859 54.8565
5 2,416,376 157,448 6.51587 1124046 46.5178
8 2,699,273 191,332 7.08828 1138412 42.1748
4 1,576,107 100,314 6.36467 805229 51.0897
6 2,025,366 131,396 6.48752 990421 48.9008
7 546,091 35,800 6.55568 239459 43.8497

Alignment with Bowtie2

  • The long reads were not compatible with our pipeline using Bowtie2, because the aligner suppresses read name lines which are longer than 256 characters.
  • Added code to split long reads into multiple short reads to use Bowtie2
  • Ran mapping pipeline:
cur_dir="/media/3TB_Dinh/Blueprint"
reads_dir="/media/3TB_Dinh/Blueprint"
email="diep.hue.dinh@gmail.com"

bisReadMapper="/home/ddiep/scripts/MethylationPipeline/scripts/smartBisReadMapper.pl"
template_fwd="/media/2TB_storeA/BisRef/bisHg19/hg19.fa.bis.fwd.bowtie2"
template_rev="/media/2TB_storeA/BisRef/bisHg19/hg19.fa.bis.rev.bowtie2"
template_fa="/media/2TB_storeA/BisRef/bisHg19/hg19.fa"
soap="/home/ddiep/softwares/soap2.21release/soap"
bowtie="bowtie2"
cpg="/media/2TB_storeA/BisRef/bisHg19/C_Pos/hg19.fa.cpg.positions.txt"

INDX="1Index1_S1 1Index2_S2 1Index3_S3 2Index4_S6 1Index5_S4 2Index6_S7 2Index7_S8 1Index8_S5"

# make sure the qual_base variable is set correctly
cd $cur_dir

for s in ${INDX}
do

f="$s.fq"
g="$s.leftR1.fq"
h="$s.leftR2.fq"
n="$s-MS"
mkdir $n
echo "cd $cur_dir/$n" >> $n.job
echo "$bisReadMapper -r $reads_dir/$f -W $template_fwd -C $template_rev -g $template_fa -a $bowtie -p 16 -b 33 -n $n.f1 -q 20 -l $cpg > $n.f1.statusMbias 2>$n.f1.err" >> $n.job
echo "$bisReadMapper -r $reads_dir/$g -W $template_fwd -C $template_rev -g $template_fa -a $bowtie -p 16 -b 33 -n $n.f2 -q 20 -l $cpg > $n.f2.statusMbias 2>$n.f2.err" >> $n.job
echo "$bisReadMapper -r $reads_dir/$h -W $template_fwd -C $template_rev -g $template_fa -a $bowtie -p 16 -b 33 -n $n.f3 -q 20 -l $cpg > $n.f3.statusMbias 2>$n.f3.err" >> $n.job
echo "rm *encoded" >> $n.job
#sh $n.job
#qsub -q home-k4zhang $n.job

done