User:Lindenb/Notebook/UMR915/20100615

20100614        Top        20100616       

merging all the bam per individuals:

  for I in `tr -s " " < ../Iomega_HDD/fastq/*_fastq.txt  | cut -d ' ' -f 4 | grep -v sample | sort | uniq`
  do
  	echo "Individual $I"
  	F=`tr -s " " < ../Iomega_HDD/fastq/*_fastq.txt  | cut -d ' ' -f 4,9 | grep -w $I | sed 's%.*/\([0-9]*_[0-9]*\)_[12].fastq%\1%' | sort | uniq | awk '{printf("bwa_%s.sorted.bam ",$1);}'`
  	samtools merge ${I}.bam ${F}
  	samtools index ${I}.bam
  done

Removing the duplicates from the bams with picard

 for F in X1.bam X2.bam ...
  do
     java -jar /usr/local/package/picard-tools-1.22/MarkDuplicates.jar \
               I=${F}.bam O=bwa_rmdup_${F}.bam \
               REMOVE_DUPLICATES=true AS=true VALIDATION_STRINGENCY=SILENT METRICS_FILE=${F}.rmdup.metrics
  done