system_genetics/rnaseq/step2_trim/snippet.sh

55 lines
1.6 KiB
Bash

#!/bin/bash
#
# Reference: http://www.usadellab.org/cms/?page=trimmomatic
module load Trimmomatic
PROJECT_DIRECTORY="/groups/umcg-griac/tmp01/rawdata/$(whoami)/rnaseq"
FASTQ_OUT="${PROJECT_DIRECTORY}/step2/"
mkdir -p "${FASTQ_OUT}"
# Adapters can be found at
# https://github.com/timflutre/trimmomatic/tree/master/adapters
# But should be verified with FastQC, or in another way.
# Trimmomatic example Paired end data.
#
# Flags:
# - ILLUMINACLIP: Cut adapter and other illumina-specific sequences from the
# read.
# - SLIDINGWINDOW: Perform a sliding window trimming, cutting once the average
# quality within the window falls below a threshold.
# - LEADING: Cut bases off the start of a read, if below a threshold quality.
# - TRAILING: Cut bases off the end of a read, if below a threshold quality.
# - HEADCROP: Cut the specified number of bases from the start of the read.
# - MINLEN: Drop the read if it is below a specified length.
java -jar $EBROOTTRIMMOMATIC/trimmomatic.jar PE \
-phred33 \
sample1_R1.fastq.gz \
sample1_R2.fastq.gz \
"${FASTQ_OUT}/sample1_R1_paired.fastq.gz" \
"${FASTQ_OUT}/sample1_R1_unpaired.fastq.gz" \
"${FASTQ_OUT}/sample1_R2_paired.fastq.gz" \
"${FASTQ_OUT}/sample1_R2_unpaired.fastq.gz" \
ILLUMINACLIP: TruSeq3-PE.fa:2:30:10 \
LEADING:3 \
TRAILING:3 \
SLIDINGWINDOW:4:25 \
HEADCROP:8 \
MINLEN:50
# Example single end data.
java -jar $EBROOTTRIMMOMATIC/trimmomatic.jar SE \
-phred33 \
sample1.fastq.gz \
output.fastq.gz \
ILLUMINACLIP:TruSeq3-SE:2:30:10 \
LEADING:3 \
TRAILING:3 \
SLIDINGWINDOW:4:15 \
HEADCROP:8 \
MINLEN:50