User:Lindenb/Notebook/UMR915/20100614

20100611        Top        20100615       

converting, indexing, sorting BAM

   gunzip -c bwa_xxxx.sam.gz | samtools view -b -t /GENOTYPAGE/data/pubdb/ucsc/hg18/chromosomes/hg18.fa.fai - > jeter.bam
   samtools sort jeter.bam jeter.sorted.bam ## hum should NOT use jeter.sorted.bam but jeter.sorted  because '.bam' was added at the end
   cp jeter.sorted.bam.bam jeter2.sorted.bam.bam #just for testing 'merge'
   samtools merge merged.bam jeter.sorted.bam.bam jeter2.sorted.bam.bam
   
   ls -lah merged.bam jeter.sorted.bam.bam jeter2.sorted.bam.bam
   -rw-r--r-- 1 lindenb users 4,2G jun 14 10:48 jeter2.sorted.bam.bam
   -rw-r--r-- 1 lindenb users 4,2G jun 14 10:42 jeter.sorted.bam.bam
   -rw-r--r-- 1 lindenb users 4,8G jun 14 11:10 merged.bam

uh ??? size merged not the same...

    samtools index merged.bam
    samtools view merged.bam chrXX | grep XX | head -n 2
    ILXXXXX1	99	chrXX	1440634	23	54M	=	14430863	283	XXXX	IGGDIBII>IIIIDIIIIIFIEEGIIGIIIIIGEG>I?DFIDDEIAICFDI@B>	XT:A:U	NM:i:0	SM:i:23	AM:i:0	X0:i:1	X1:i:1	XM:i:0	XO:i:0	XG:i:0	MD:Z:54	XA:Z:chr14,-18862314,54M,1;
    ILXXXXX2	99	chrXX	1440634	23	54M	=	14430863	283	XXXX	IGGDIBII>IIIIDIIIIIFIEEGIIGIIIIIGEG>I?DFIDDEIAICFDI@B>	XT:A:U	NM:i:0	SM:i:23	AM:i:0	X0:i:1	X1:i:1	XM:i:0	XO:i:0	XG:i:0	MD:Z:54	XA:Z:chr14,-18862314,54M,1;

script used was

 HG18=/GENOTYPAGE/data/pubdb/ucsc/hg18/chromosomes/hg18.fa
 
 for SAM in  bwa_*.sam.gz
 do
       echo ${SAM}
       BAM=`echo ${SAM}| sed 's/\.sam\.gz$/\.bam/'`
       SORTED=`echo ${SAM}| sed 's/\.sam\.gz$/\.sorted/'`
       gunzip -c ${SAM} | samtools view -b -t ${HG18}.fai - >  ${BAM}
       samtools sort ${BAM} ${SORTED}
       samtools index ${SORTED}.bam
 done