HOWTO_barley.txt

# 1) Obtain PE and MP libraries from SRA using 'fastq-dump' from SRAtoolkit (https://github.com/ncbi/sra-tools)

# PE-library (9.2 GB, IS:267, orient:FR, encoding:Sanger)
fastq-dump --gzip -I --split-spot SRR491411

# MP-library (3.8 GB, IS:2364, orient:RF, encoding:Sanger)
fastq-dump --gzip -I --split-spot ERR126133
# alternative ERR126134

# 2) put raw reads in folder and uncompress

mkdir raw_reads_barley;

gunzip -c SRR491411.fastq.gz | head -240000000 > raw_reads_barley/SRR491411.fastq # (19 GB)
rm -f SRR491411.fastq.gz;

gunzip -c ERR126133.fastq.gz | head -120000000 > raw_reads_barley/ERR126133.fastq # (12 GB)
rm -f ERR126133.fastq.gz;

# 3) extract cp reads
# $CHLOROP is an env variable which points to the install directory of this protocol

$CHLOROP/0_get_cp_reads.pl raw_reads_barley cp_reads_barley $CHLOROP/poaceae.fna

# 4) Reference-guided assembly
# 4.1) clean reads
$CHLOROP/1_cleanreads.pl -folder cp_reads_barley -ref $CHLOROP/reference_barley.fna

# 4.2) create config file
cp cp_reads_barley/cleanreads.txt cp_reads_barley/assembly_conf

# Edit the file to contain the next:
1 SRR491411 cp-SRR491411.wind15_28.3crop95.mlen40.corr.12.fq.gz FR 267 Sanger
2 ERR126133 cp-ERR126133.wind15_28.3crop44.mlen40.corr.12.fq.gz RF 2364 Sanger

# 4.3) assemble reads +ref
$CHLOROP/2_assemble_reads.pl cp_reads_barley assembly_conf -ref $CHLOROP/reference.fna \
  -refcolumbus $CHLOROP/reference4columbus.fna
# final assembly: cp_reads_barley/assembly_conf_kmer47_sample500000/gapfiller.gapfilled.final.fa

# 5) de-novo assembly
# 5.1) clean reads
$CHLOROP/1_cleanreads.pl -folder cp_reads_barley

# 5.2) create config file
cp cp_reads_barley/cleanreads.txt cp_reads_barley/assembly_denovo

# Edit the file to contain the next:
1 SRR491411 cp-SRR491411.wind15_28.3crop95.mlen40.corr.12.fq.gz FR 267 Sanger
2 ERR126133 cp-ERR126133.wind15_28.3crop44.mlen40.corr.12.fq.gz RF 2364 Sanger

# 5.3) assemble reads -ref
$CHLOROP/2_assemble_reads.pl cp_reads_barley assembly_denovo
# final assembly: cp_reads_barley/assembly_denovo_kmer47_sample500000/gapfiller.gapfilled.final.fa