Genome Informatics Laboratory at KRIBB

This is an old revision of the document!

---

#########################

#   2017 C&K Workshop   #

#   Resequencing Code   #

#        2017. 11       #

#########################

########Resequencing ###########

cd /home/workshop/1.WGS_practice/Genome_analysis

### FASTQC

fastqc --nogroup paired_end_sep1.fq paired_end_sep2.fq

### TRIMMOMATIC

java -jar /home/Program/Trimmomatic-0.33/trimmomatic-0.33.jar \

PE paired_end_sep1.fq paired_end_sep2.fq paired_end_1P.fastq.gz paired_end_1U.fastq.gz \

paired_end_2P.fastq.gz paired_end_2U.fastq.gz \

ILLUMINACLIP:/home/Program/Trimmomatic-0.33/adapters/total-TruSeq-PE.fa:2:30:10 \

TRAILING:20 MINLEN:75

### REFERENCE INDEXING

/home/Program/bowtie2-2.2.5/bowtie2-build Reference.fa Reference

### READ MAPPING

/home/Program/bowtie2-2.2.5/bowtie2 \

1. x Reference \

1. 1 paired_end_1P.fastq.gz -2 paired_end_2P.fastq.gz \

1. S paired_end.sam \

2> /home/workshop/1.WGS_practice/Genome_analysis/paired_end.bowtie2stat

### ADD_RG 

java -jar /home/Program/picard-tools-1.138/picard.jar AddOrReplaceReadGroups \

INPUT=paired_end.sam \

OUTPUT=paired_end_RG.bam \

SORT_ORDER=coordinate RGID=paired_end RGLB=paired_end RGPL=illumina RGPU=non RGSM=paired_end \

VALIDATION_STRINGENCY=LENIENT

### REMOVE_DU

java -jar /home/Program/picard-tools-1.138/picard.jar MarkDuplicates \

INPUT=paired_end_RG.bam \

OUTPUT=paired_end_RG_DU.bam \

METRICS_FILE=paired_end_RG_DU.metrics REMOVE_DUPLICATES=true ASSUME_SORTED=true \

VALIDATION_STRINGENCY=LENIENT 

### FIXMATE

java -jar /home/Program/picard-tools-1.138/picard.jar FixMateInformation \

INPUT=paired_end_RG_DU.bam \

OUTPUT=paired_end_RG_DU_FIX.bam \

SORT_ORDER=coordinate \

VALIDATION_STRINGENCY=LENIENT

### INDEXING

/home/Program/samtools-1.2/samtools faidx Reference.fa

/home/Program/samtools-1.2/samtools index paired_end_RG_DU_FIX.bam

### REALIGN

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar -T RealignerTargetCreator \

1. R Reference.fa \

1. I paired_end_RG_DU_FIX.bam \

1. o paired_end_RG_DU_FIX_Realign.intervals

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar -T IndelRealigner \

1. R Reference.fa \

1. I paired_end_RG_DU_FIX.bam \

1. o paired_end_RG_DU_FIX_Realign.bam \

1. targetIntervals paired_end_RG_DU_FIX_Realign.intervals

### BQ_RECAL

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar -T BaseRecalibrator \

1. R Reference.fa \

1. I paired_end_RG_DU_FIX_Realign.bam \

1. cov ReadGroupCovariate -cov QualityScoreCovariate -cov CycleCovariate -cov ContextCovariate \

1. knownSites Reference.vcf \

1. o paired_end_RECAL.grp

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar -T PrintReads \

1. R Reference.fa \

1. I paired_end_RG_DU_FIX_Realign.bam \

1. BQSR paired_end_RECAL.grp \

1. o paired_end_RECAL.bam

### INDEXING

/home/Program/samtools-1.2/samtools index paired_end_RECAL.bam

### IGV

java -Xmx1500m -jar /home/Program/IGV_2.3.80/igv.jar

############ VARIANT CALLING #########

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar -T UnifiedGenotyper \

1. R Reference.fa \

1. I paired_end_RECAL.bam \

1. o sample01.raw.vcf \

1. glm BOTH

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar \

1. R Reference.fa \

1. T SelectVariants \

1. -variant sample01.raw.vcf \

1. o snp_sample01.raw.vcf \

1. selectType SNP

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar \

1. R Reference.fa \

1. T SelectVariants \

1. -variant sample01.raw.vcf \

1. o indel_sample01.raw.vcf \

1. selectType INDEL

### VARIANT FILTERING

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar \

1. R Reference.fa \

1. T VariantFiltration \

1. -variant indel_sample01.raw.vcf \

1. o filtered_indel_sample01.vcf \

1. -filterExpression “MQ0 >= 4 && ¹⁾ > 0.1)” –filterName “HARD_TO_VALIDATE” \

1. -filterExpression “QUAL < 30” –filterName “QualFilter” \

1. -filterExpression “QD < 5.0” –filterName “QD5” \

1. -filterExpression “FS > 200.0” –filterName “FS200”

java -jar /home/Program/GenomeAnalysisTK-3.4-46/GenomeAnalysisTK.jar \

1. R Reference.fa \

1. T VariantFiltration \

1. -variant snp_sample01.raw.vcf \

1. o filtered_snp_sample01.vcf \

1. -clusterSize 3 –clusterWindowSize 10 \

1. -mask filtered_indel_sample01.vcf –maskName “InDel” \

1. -filterExpression “MQ0 >= 4 && ²⁾ > 0.1)” –filterName “HARD_TO_VALIDATE” \

1. -filterExpression “QUAL < 30” –filterName “QualFilter” \

1. -filterExpression “FS > 200.0 ” –filterName “FS200”

### VARIANT ANNOTATION

#java -jar /home/Program/snpEff/snpEff.jar databases | more

#java -jar /home/Program/snpEff/snpEff.jar -download GRCh38.82

java -jar /home/Program/snpEff/snpEff.jar Human3 filtered_snp_sample01.vcf -s filtered_snp_sample01.ann.html >filtered_snp_sample01.ann.vcf

java -jar /home/Program/snpEff/snpEff.jar Human3 filtered_indel_sample01.vcf -s filtered_indel_sample01.ann.html >filtered_indel_sample01.ann.vcf

### IGV

java -Xmx1500m -jar /home/Program/IGV_2.3.80/igv.jar

### END ###