version update for LRSDAY: v1.3.0 -> v1.3.1

CHANGELOG.md

@@ -7,6 +7,19 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## [Unreleased]
 
+## [1.3.1] - 2019-01-22
+### Added
+- A script for generated demultiplexed fastq reads based on nanopore's guppy demultiplexing summary file.
+- A script for extracting all read IDs from the input fastq file.
+- A script for calculating the sequence length of each enclosed sequences from the input fasta file.
+### Changed
+- Software version updates for a number of dependencies. Importantly, nanopolish was bumped up to v0.11.0 to support the new multi-fast5 nanopore reads.
+- Downloading URL updates for testing data due to changes on the EBI data server. 
+- Adopting picard tools' new commandline syntax.
+### Fixed
+- A bug that prevents correct parameter parsing when multiple customized canu parameters are specified.
+- Minor bugs related with deleting intermediate files in special cases.
+
 ## [1.3.0] - 2018-11-13
 ### Added
 - Support for one more alternative assembler: wtdbg2.

Project_Template/00.Long_Reads/LRSDAY.00.Long_Reads_Preprocessing.sh

@@ -24,7 +24,7 @@ echo "genome_size=$genome_size, post_filtering_coverage=$post_filtering_coverage
 echo ""
 if [[ "$reads_type" == "nanopore-raw" || "$reads_type" == "nanopore-corrected" ]]
 then
-    $porechop_dir/porechop -i $reads -o $prefix.porechop.fastq.gz --threads $threads > $prefix.porechop.summary.txt
+    $porechop_dir/porechop -i $reads -o $prefix.porechop.fastq.gz --discard_middle --threads $threads > $prefix.porechop.summary.txt
     if [[ "$run_filtering" == "yes" ]]
     then
 	$filtlong_dir/filtlong --min_length 1000 --keep_percent 90 --target_bases $filtlong_target_bases $prefix.porechop.fastq.gz | gzip > $prefix.filtlong.fastq.gz

Project_Template/00.Long_Reads/LRSDAY.00.Retrieve_Sample_PacBio_Reads.sh

@@ -24,50 +24,77 @@ rm $file_name
 cd pacbio_fofn_files
 echo "download the metadata and raw PacBio reads in .h5 format ..."
 
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.metadata.xml
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.metadata.xml
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA535/ERA535258/pacbio_hdf5/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.metadata.xml
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.metadata.xml
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080522/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.metadata.xml
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080529/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.metadata.xml
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080536/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.metadata.xml
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080537/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.metadata.xml
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR112/ERR1124245/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.metadata.xml
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR114/ERR1140978/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.metadata.xml
 
 if [[ ! -d Analysis_Results ]]
 then
     mkdir Analysis_Results
 fi
 
 cd Analysis_Results
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.1.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.2.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.3.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.bas.h5
-
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.1.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.2.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.3.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.bas.h5
-
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA535/ERA535258/pacbio_hdf5/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.1.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA535/ERA535258/pacbio_hdf5/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.2.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA535/ERA535258/pacbio_hdf5/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.3.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA535/ERA535258/pacbio_hdf5/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.bas.h5
-
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.1.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.2.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.3.bax.h5
-wget ftp://ftp.sra.ebi.ac.uk/vol1/ERA525/ERA525888/pacbio_hdf5/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.bas.h5
+
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080522/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.1.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080522/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.2.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080522/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.3.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080522/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.bas.h5
+
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080529/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.1.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080529/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.2.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080529/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.3.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080529/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.bas.h5
+
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080536/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.1.bax.h5
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080536/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.2.bax.h5
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080536/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.3.bax.h5
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080536/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.bas.h5
+
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080537/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.1.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080537/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.2.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080537/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.3.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR108/ERR1080537/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.bas.h5
+
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR112/ERR1124245/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.1.bax.h5
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR112/ERR1124245/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.2.bax.h5
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR112/ERR1124245/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.3.bax.h5
+# wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR112/ERR1124245/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.bas.h5
+
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR114/ERR1140978/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.1.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR114/ERR1140978/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.2.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR114/ERR1140978/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.3.bax.h5
+wget ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR114/ERR1140978/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.bas.h5
+
+###
 
 echo $(pwd)/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.1.bax.h5 >> ./../$prefix.SMRTCell.1.RSII_bax.fofn
 echo $(pwd)/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.2.bax.h5 >> ./../$prefix.SMRTCell.1.RSII_bax.fofn
 echo $(pwd)/m150811_092723_00127_c100844062550000001823187612311514_s1_p0.3.bax.h5 >> ./../$prefix.SMRTCell.1.RSII_bax.fofn
+
 echo $(pwd)/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.1.bax.h5 >> ./../$prefix.SMRTCell.2.RSII_bax.fofn
 echo $(pwd)/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.2.bax.h5 >> ./../$prefix.SMRTCell.2.RSII_bax.fofn
 echo $(pwd)/m150814_233250_00127_c100823152550000001823177111031542_s1_p0.3.bax.h5 >> ./../$prefix.SMRTCell.2.RSII_bax.fofn
+
 echo $(pwd)/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.1.bax.h5 >> ./../$prefix.SMRTCell.3.RSII_bax.fofn
 echo $(pwd)/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.2.bax.h5 >> ./../$prefix.SMRTCell.3.RSII_bax.fofn
 echo $(pwd)/m150911_220012_00127_c100861772550000001823190702121671_s1_p0.3.bax.h5 >> ./../$prefix.SMRTCell.3.RSII_bax.fofn
+
 echo $(pwd)/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.1.bax.h5 >> ./../$prefix.SMRTCell.4.RSII_bax.fofn
 echo $(pwd)/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.2.bax.h5 >> ./../$prefix.SMRTCell.4.RSII_bax.fofn
 echo $(pwd)/m150813_110541_00127_c100823112550000001823177111031581_s1_p0.3.bax.h5 >> ./../$prefix.SMRTCell.4.RSII_bax.fofn
 
+# echo $(pwd)/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.1.bax.h5 >> ./../$prefix.SMRTCell.5.RSII_bax.fofn
+# echo $(pwd)/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.2.bax.h5 >> ./../$prefix.SMRTCell.5.RSII_bax.fofn
+# echo $(pwd)/m150814_201337_00127_c100823152550000001823177111031541_s1_p0.3.bax.h5 >> ./../$prefix.SMRTCell.5.RSII_bax.fofn
+
+# echo $(pwd)/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.1.bax.h5 >> ./../$prefix.SMRTCell.6.RSII_bax.fofn
+# echo $(pwd)/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.2.bax.h5 >> ./../$prefix.SMRTCell.6.RSII_bax.fofn
+# echo $(pwd)/m150910_184604_00127_c100822732550000001823176011031536_s1_p0.3.bax.h5 >> ./../$prefix.SMRTCell.6.RSII_bax.fofn
+
+
 cd ..
 cd ..
 

Project_Template/01.Long-read-based_Genome_Assembly/LRSDAY.01.Long-read-based_Genome_Assembly.sh

@@ -12,8 +12,8 @@ long_reads="./../00.Long_Reads/SK1.filtered_subreads.fastq.gz" # The file path o
 long_reads_type="pacbio-raw" # The long reads data type. Use "pacbio-raw" or "pacbio-corrected" or "nanopore-raw" or "nanopore-corrected". Default = "pacbio-raw" for the testing example
 genome_size="12.5m" # The estimated genome size with the format of <number>[g|m|k], e.g. 12.5m for 12.5 Mb. Default = "12.5m".
 assembler="canu" # The long-read assembler: Use "canu" or "flye" or "wtdbg2" or "smartdenovo" or "canu-flye" or "canu-wtdbg2" or "canu-smartdenovo". For "canu-flye", "canu-wtdbg2", and "canu-smartdenovo", the assembler canu is used first to generate error-corrected reads from the raw reads and then the assembler flye/wtdbg2/smartdenovo is used to assemble the genome. Based on our test, assembler="canu" generally gives the best result but will take substantially longer time than the other options.
-customized_canu_parameters="-correctedErrorRate=0.04" # For assembler="canu" only. Users can set customized Canu assembly parameters here or simply leave it empty like "" to use Canu's default assembly parameter. For example you could set "-correctedErrorRate=0.04" for high coverage (>60X) PacBio data and "-overlapper=mhap -utgReAlign=true" for high coverage (>60X) Nanopore data to improve the assembly speed. More than one customized parameters can be set here as long as they are separeted by space (e.g. "-option1=XXX -option2=YYY -option3=ZZZ"). Please consult Canu's manual "http://canu.readthedocs.io/en/latest/faq.html#what-parameters-can-i-tweak" for advanced customization settings. Default = "-correctedErrorRate=0.04" for the testing example.
-threads=1 # The number of threads to use. Default = 1.
+customized_canu_parameters="correctedErrorRate=0.04" # For assembler="canu" only. Users can set customized Canu assembly parameters here or simply leave it empty like customized_canu_parameters="" to use Canu's default assembly parameter. For example you could set customized_canu_parameters="correctedErrorRate=0.04" for high coverage (>60X) PacBio data and customized_canu_parameters="overlapper=mhap;utgReAlign=true" for high coverage (>60X) Nanopore data to improve the assembly speed. When assembling genomes with high heterozygosity, you can could set customized_canu_parameters="corOutCoverage=200;batOptions=-dg 3 -db 3 -dr 1 -ca 500 -cp 50" to avoid collasping haplotypes. As shown in these examples, more than one customized parameters can be set here as long as they are separeted by a semicolon and contained in a pair of double quotes (e.g. customized_canu_parameters="option1=XXX;option2=YYY;option3=ZZZ"). Please consult Canu's manual "http://canu.readthedocs.io/en/latest/faq.html#what-parameters-can-i-tweak" for advanced customization settings. Default = "correctedErrorRate=0.04" for the testing example.
+threads=2 # The number of threads to use. Default = 2.
 vcf="yes" # Use "yes" if prefer to have vcf file generated to show SNP and INDEL differences between the assembled genome and the reference genome for their uniquely alignable regions. Otherwise use "no". Default = "yes".
 dotplot="yes" # Use "yes" if prefer to plot genome-wide dotplot based on the comparison with the reference genome below. Otherwise use "no". Default = "yes".
 ref_genome_raw="./../00.Ref_Genome/S288C.ASM205763v1.fa" # The file path of the raw reference genome. This is only needed when the option "dotplot=" or "vcf=" has been set as "yes".
@@ -45,20 +45,23 @@ then
     fi
 fi
 
-
-
 out_dir=${prefix}_${assembler}_out
 
 if [[ "$assembler" == "canu" ]]
 then
+    OLDIFS=$IFS;
+    IFS=";"
+    customized_canu_parameters_array=($customized_canu_parameters)
+    IFS=$OLDIFS;
+    printf "%s\n" "${customized_canu_parameters_array[@]}" > $prefix.customized_canu_parameters.spec
     $canu_dir/canu -p $prefix -d $out_dir \
+	-s $prefix.customized_canu_parameters.spec \
 	useGrid=false \
 	maxThreads=$threads \
 	genomeSize=$genome_size \
 	gnuplot=$gnuplot_dir/gnuplot \
-	-${long_reads_type} $long_reads \
-	$customized_canu_parameters
-
+	-${long_reads_type} $long_reads
+    mv $prefix.customized_canu_parameters.spec ./$out_dir/
     perl $LRSDAY_HOME/scripts/simplify_seq_name.pl -i $out_dir/$prefix.contigs.fasta -o $prefix.assembly.$assembler.fa
 elif [[ "$assembler" == "flye" ]]
 then
@@ -104,7 +107,6 @@ then
 	genomeSize=$genome_size \
 	gnuplot=$gnuplot_dir/gnuplot \
 	-${long_reads_type} $long_reads \
-	# $customized_canu_parameters
 
     if [[ "$long_reads_type" == "pacbio-raw" ]]
     then
@@ -133,7 +135,6 @@ then
         genomeSize=$genome_size \
         gnuplot=$gnuplot_dir/gnuplot \
         -${long_reads_type} $long_reads \
-	# $customized_canu_parameters
 
     mkdir -p $out_dir/wtdbg2
     cd $out_dir/wtdbg2
@@ -149,7 +150,6 @@ then
         genomeSize=$genome_size \
         gnuplot=$gnuplot_dir/gnuplot \
         -${long_reads_type} $long_reads \
-	# $customized_canu_parameters
 
     mkdir -p $out_dir/smartdenovo
     cd $out_dir/smartdenovo
@@ -195,7 +195,6 @@ then
     rm *.delta
     rm *.delta_filter
     rm ref_genome.fa
-    rm ref_genome.fa.fai
     if [[ $vcf == "yes" ]] 
     then
 	rm *.filter.coords

Project_Template/02.Long-read-based_Assembly_Polishing/LRSDAY.02.Long-read-based_Assembly_Polishing.sh

@@ -17,7 +17,7 @@ pacbio_reads_type="RSII" # The sequencing machine used to generate the input Pac
 
 ### When long_read_technology="nanopore" ###
 nanopore_fast5_files="./../00.Long_Reads/nanopore_fast5_files" # The file path to the directory containing raw Oxford Nanopore FAST5 files.
-nanopore_albacore_sequencing_summary="./../00.Long_Reads/nanopore_fast5_files/sequencing_summary.txt" # The file path to the albacore basecaller sequencing summary output. This summary file is not necessary but it can help the polishing step to run much faster when available. When this file is unavailable, set nanopore_albacore_sequencing_summary="".
+nanopore_basecalling_sequencing_summary="./../00.Long_Reads/nanopore_fast5_files/sequencing_summary.txt" # The file path to the nanopore albacore/guppy basecaller sequencing summary output. This summary file is not necessary but it can help the polishing step to run much faster when available. When this file is unavailable, set nanopore_albacore_sequencing_summary="".
 
 prefix="SK1" # The file name prefix for the output files. Default = "SK1" for the testing example.
 
@@ -46,7 +46,7 @@ then
 	    $conda_pacbio_dir/variantCaller --algorithm=quiver -x 5 -X 120 -q 20 -v -j $threads $prefix.pbalign.bam -r $prefix.assembly.raw.fa -o $prefix.assembly.consensus.fa -o $prefix.assembly.consensus.fq -o $prefix.assembly.consensus.vcf --diploid 
 	fi
     else
-	$conda_pacbio_dir/pbalign --nproc $threads --algorithm blasr --tmpDir ./tmp $pacbio_fofn_file $prefix.assembly.raw.fa $prefix.pbalign.bam
+	$conda_pacbio_dir/pbalign --nproc $threads --algorithm blasr --tmpDir ./tmp $pacbio_bam_fofn_file $prefix.assembly.raw.fa $prefix.pbalign.bam
 	if [[ $ploidy == "1" ]]
 	then
 	    $conda_pacbio_dir/variantCaller --algorithm=arrow -x 5 -X 120 -q 20 -v -j $threads $prefix.pbalign.bam -r $prefix.assembly.raw.fa -o $prefix.assembly.consensus.fa -o $prefix.assembly.consensus.fq -o $prefix.assembly.consensus.vcf
@@ -61,11 +61,11 @@ then
 else
     # perform correction using the minimap2-nanopolish pipeline
     source $nanopolish_dir/py3_virtualenv_nanopolish/bin/activate
-    if [[ -z "$nanopore_albacore_sequencing_summary" ]]
+    if [[ -z "$nanopore_basecalling_sequencing_summary" ]]
     then
 	$nanopolish_dir/nanopolish index -d $nanopore_fast5_files $long_reads_in_fastq
     else
-	$nanopolish_dir/nanopolish index -d $nanopore_fast5_files -s $nanopore_albacore_sequencing_summary $long_reads_in_fastq
+	$nanopolish_dir/nanopolish index -d $nanopore_fast5_files -s $nanopore_basecalling_sequencing_summary $long_reads_in_fastq
     fi
     java -Djava.io.tmpdir=./tmp -XX:ParallelGCThreads=$threads -jar $picard_dir/picard.jar CreateSequenceDictionary  REFERENCE=$prefix.assembly.raw.fa OUTPUT=$prefix.assembly.raw.dict
     $minimap2_dir/minimap2 -ax map-ont $prefix.assembly.raw.fa $long_reads_in_fastq > $prefix.minimap2.sam