外显子测序代码记录

#QC 使用SeqPrep进行质控
SeqPrep -f /home/qian.liu/gaoyang/F18FTSECWLJ0595_HUMcizE/1625668PA_all/clean_data/CL100072979_L02_561_1.fq -r /home/qian.liu/gaoyang/F18FTSECWLJ0595_HUMcizE/1625668PA_all/clean_data/CL100072979_L02_561_2.fq -1 /home/qian.liu/database/test_gaoyang/CL100072979_L02_561_1_tmp.fq -2 /home/qian.liu/database/test_gaoyang/CL100072979_L02_561_2_tmp.fq -q 20 -L 25 -B AGATCGGAAGAGCGTCGTGT -A AGATCGGAAGAGCACACGTC > /home/qian.liu/database/test_gaoyang/CL100072979_L02_561.QC.log;
;
sickle pe -f 1_N-tmp_1.fq -r 1_N-tmp_2.fq -t sanger -o 1_N_trim1.fastq -p 1_N_trim2.fastq -s 1_N_trim_unpaired.fastq > trim.QC.log;


##MAPPING 比对，使用bwa进行比对，利用samtools进行格式转换
mkdir -p ./3.mapping;
bwa mem -R '@RG\tID:HM170907XGY-B_S3_L003_L003\tSM:HM170907XGY-B_S3_L003_L003\tLB:HM170907XGY-B_S3_L003_L003\tPU:run barcode\tPL:Illumina\tDS:resequencing\tCN:MajorBio' -M -t 5 /home/yang.zou/Database/ucsc.hg19.fasta /home/yangzou/regional_capture48/rawdata/HM170907XGY-B_S3_L003_L003_R1_001.fastq.gz /home/yangzou/regional_capture48/rawdata/HM170907XGY-B_S3_L003_L003_R2_001.fastq.gz > HM170907XGY-B_S3_L003_L003.sam
samtools view -bS HM170907XGY-B_S3_L003_L003.sam >HM170907XGY-B_S3_L003_L003.bam  #将sam格式转换成bam格式
samtools sort  HM170907XGY-B_S3_L003_L003.bam -o HM170907XGY-B_S3_L003_L003.sort  #对bam文件进行排序
samtools index HM170907XGY-B_S3_L003_L003.sort.bam          ##构建Index数据库


#Mark duplicates 去重 
mkdir -p ./5.varcalling;
#利用picard软件去除PCR重复
java -Xmx10G -jar /home/yang.zou/software/exome/MarkDuplicates.jar TMP_DIR=./tmp MAX_FILE_HANDLES=10000 VALIDATION_STRINGENCY=SILENT ASSUME_SORTED=true REMOVE_DUPLICATES=true I=/home/qian.liu/database/3.mapping/HM170907XGY-B_S3_L003_L003.sort O=/home/qian.liu/database/5.varcalling/HM170907XGY-B_S3_L003_L003.