Code

FASTQC

module load bioinfo-tools FastQC/0.11.9

fastqc -o /home/mathi/genome_analysis/durianproject/analyses/1_fastqc_illumina/ -t 2 *.fastq.gz

fastqc -o /home/mathi/genome_analysis/durianproject/analyses/2_fastqc_pacbio/ -t 2 *.fq.gz

fastqc -o /home/mathi/genome_analysis/durianproject/analyses/3_fastqc_transcriptome/trimmed/ -t 2 *.fastq.gz

fastqc -o /home/mathi/genome_analysis/durianproject/analyses/3_fastqc_transcriptome/untrimmed/ -t 2 *.fastq.gz

Following the trimming of the untrimmed transcriptome with trimmomatic, a quality control of the recently trimmed trancriptome was done with the code below.

fastqc -o /home/mathi/genome_analysis/durianproject/analyses/4_fastqc/4_fastqc_transcriptome_trimmed/ -t 2 *.fq.gz

CANU

#!/bin/bash -l
#SBATCH -A uppmax2022-2-5
#SBATCH -M snowy
#SBATCH -p core
#SBATCH -n 4
#SBATCH -t 19:00:00
#SBATCH -J 2_assembly_pacbio
#SBATCH --mail-type=ALL
#SBATCH --mail-user mathilda.stigenberg.5156@student.uu.se

# Load modules
module load bioinfo-tools
module load canu/2.2
# Your commands    

canu -d /home/mathi/genome_analysis/durianproject/analyses/2_assembly -p ass_pb genomeSize=24m useGrid=False corThreads=4 -pacbio /home/mathi/genome_analysis/durianproject/4_Tean_Teh_2017/pacbio_data/SRR6037732_scaffold_10.fq.gz

TRIMMOMATIC

#!/bin/bash -l
#SBATCH -A uppmax2022-2-5
#SBATCH -M snowy
#SBATCH -p core
#SBATCH -n 2
#SBATCH -t 2:00:00
#SBATCH -J 2_trim_transcript
#SBATCH -o trimming_transcriptome.output
#SBATCH --mail-type=ALL
#SBATCH --mail-user mathilda.stigenberg.5156@student.uu.se

# Load modules
module load bioinfo-tools
module load trimmomatic/0.39
# Your commands

trimmomatic PE -threads 2 /home/mathi/genome_analysis/durianproject/4_Tean_Teh_2017/transcriptome/untrimmed/SRR6040095_scaffold_10.1.fastq.gz /home/mathi/genome_analysis/durianproject/4_Tean_Teh_2017/transcriptome/untrimmed/SRR6040095_scaffold_10.2.fastq.gz -baseout /home/mathi/genome_analysis/durianproject/analyses/3_trim/3_trim_transcript/SRR6040095_scaffold_10.fq.gz ILLUMINACLIP:/sw/bioinfo/trimmomatic/0.39/snowy/adapters/TruSeq3-PE.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36

Mapping with BWA

#!/bin/bash -l
#SBATCH -A uppmax2022-2-5
#SBATCH -M snowy
#SBATCH -p core
#SBATCH -n 2
#SBATCH -t 1:30:00
#SBATCH -J 5_mapping_bwa
#SBATCH -o mapping_bwa.output
#SBATCH --mail-type=ALL
#SBATCH --mail-user mathilda.stigenberg.5156@student.uu.se

# Load modules
module load bioinfo-tools
module load bwa/0.7.17
module load samtools/1.14

# Your commands

bwa index /home/mathi/genome_analysis/durianproject/analyses/2_assembly/ass_pb.contigs.fasta 

bwa mem -t 2 /home/mathi/genome_analysis/durianproject/analyses/2_assembly/ass_pb.contigs.fasta /home/mathi/genome_analysis/durianproject/4_Tean_Teh_2017/illumina_data/SRR6058604_scaffold_10.1P.fastq.gz /home/mathi/genome_analysis/durianproject/4_Tean_Teh_2017/illumina_data/SRR6058604_scaffold_10.2P.fastq.gz > /home/mathi/genome_analysis/durianproject/analyses/5_mapping_bwa/aln_seq_bwa.sam

samtools sort /home/mathi/genome_analysis/durianproject/analyses/5_mapping_bwa/aln_seq_bwa.sam -o /home/mathi/genome_analysis/durianproject/analyses/5_mapping_bwa/aln_seq_bwa.bam

samtools index /home/mathi/genome_analysis/durianproject/analyses/5_mapping_bwa/aln_seq_bwa.bam /home/mathi/genome_analysis/durianproject/analyses/5_mapping_bwa/aln_seq_bwa.bai 

PILON

#!/bin/bash -l
#SBATCH -A uppmax2022-2-5
#SBATCH -M snowy
#SBATCH -p core
#SBATCH -n 2
#SBATCH -t 3:00:00
#SBATCH -J 6_pilon
#SBATCH -o pilon.output
#SBATCH --mail-type=ALL
#SBATCH --mail-user mathilda.stigenberg.5156@student.uu.se

# Load modules
module load bioinfo-tools
module load Pilon/1.24

# Your commands

java -jar $PILON_HOME/pilon.jar --genome /home/mathi/genome_analysis/durianproject/analyses/2_assembly/ass_pb.contigs.fasta --bam /home/mathi/genome_analysis/durianproject/analyses/5_mapping_bwa/aln_seq_bwa.bam --outdir /home/mathi/genome_analysis/durianproject/analyses/6_improvement_pilon --threads 2