After getting the RNA-seq data trimmed, it was time to perform alignments and determine expression levels of transcripts/isoforms using with HISAT2 and StringTie, respectively. StringTie was set to output tables formatted for import into ballgown. After those two analyses were complete, I ran gffcompare, using the merged StringTie GTF and the input GFF3. I caught this in one of Danielle Becker’s scripts and thought it might be interesting. The analsyes were run on Mox.
SBATCH Script (GitHub):
#!/bin/bash
## Job Name
#SBATCH --job-name=20230216-pver-stringtie-Pver_genome_assembly_v1.0-isoforms
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=07-00:00:00
## Memory per node
#SBATCH --mem=120G
##turn on e-mail notification
#SBATCH --mail-type=ALL
#SBATCH --mail-user=samwhite@uw.edu
## Specify the working directory for this job
#SBATCH --chdir=/gscratch/scrubbed/samwhite/outputs/20230216-pver-stringtie-Pver_genome_assembly_v1.0-isoforms
## Script using Stringtie with P.verrucosa v1.0 genome assembly
## and HiSat2 index generated on 20230131.
## Genome and GFF from here: http://pver.reefgenomics.org/download/
## GTF generated on 20230127 by SJW:
## https://robertslab.github.io/sams-notebook/2023/01/27/Data-Wrangling-P.verrucosa-Genome-GFF-to-GTF-Using-gffread.html
## HiSat2 index generated on 20230131 by SJW:
## https://robertslab.github.io/sams-notebook/2023/01/31/Genome-Indexing-P.verrucosa-v1.0-Assembly-with-HiSat2-on-Mox.html
## Using trimmed FastQs from 20230215.
## Expects FastQ input filenames to match <sample name>_R[12].fastp-trim.20230215.fq.gz
###################################################################################
# These variables need to be set by user
## Assign Variables
# Set total number of SAMPLES (NOT number of FastQ files)
total_samples=32
# Set number of CPUs to use
threads=28
# Index name for Hisat2 use
# Needs to match index naem used in previous Hisat2 indexing step
genome_index_name="Pver_genome_assembly_v1.0"
# HiSat2 indexes tarball
index_tarball="Pver_genome_assembly_v1.0-hisat2-indices.tar.gz"
# Set input FastQ patterns
R1_fastq_pattern='*R1*fq.gz'
R2_fastq_pattern='*R2*fq.gz'
fastq_pattern='*.fastp-trim.20230215.fq.gz'
# Location of Hisat2 index files
# Must keep variable name formatting, as it's used by HiSat2
HISAT2_INDEXES=$(pwd)
export HISAT2_INDEXES
# Paths to programs
gffcompare="/gscratch/srlab/programs/gffcompare-0.12.6.Linux_x86_64/gffcompare"
hisat2_dir="/gscratch/srlab/programs/hisat2-2.1.0"
hisat2="${hisat2_dir}/hisat2"
samtools="/gscratch/srlab/programs/samtools-1.10/samtools"
stringtie="/gscratch/srlab/programs/stringtie-2.2.1.Linux_x86_64/stringtie"
# Input/output files
genome_index_dir="/gscratch/srlab/sam/data/P_verrucosa/genomes"
genome_gff="${genome_index_dir}/Pver_genome_assembly_v1.0-valid.gff3"
fastq_dir="/gscratch/srlab/sam/data/P_verrucosa/RNAseq/"
gtf_list="gtf_list.txt"
merged_bam="20230216-pver-stringtie-pver_v1.0-sorted-bams-merged.bam"
# Declare associative array of sample names and metadata
declare -A samples_associative_array=()
# Programs associative array
declare -A programs_array
programs_array=(
[gffcompare]="${gffcompare}" \
[hisat2]="${hisat2}" \
[samtools_index]="${samtools} index" \
[samtools_merge]="${samtools} merge" \
[samtools_sort]="${samtools} sort" \
[samtools_view]="${samtools} view" \
[stringtie]="${stringtie}"
)
###################################################################################################
# Exit script if any command fails
set -e
# Load Python Mox module for Python module availability
module load intel-python3_2017
## Load associative array
## Only need to use one set of reads to capture sample name
# Set sample counter for array verification
sample_counter=0
# Load array
# DO NOT QUOTE ${R1_fastq_pattern} - WILL NOT POPULATE ARRAY!
for fastq in "${fastq_dir}"${R1_fastq_pattern}
do
# Increment counter
((sample_counter+=1))
# Remove path
sample_name="${fastq##*/}"
# Get sample name from first _-delimited field
sample_name=$(echo "${sample_name}" | awk -F "_" '{print $1}')
# Set treatment condition for each sample
# Used for setting read group (@RG) in SAM files
if [[ "${sample_name}" == "C17" ]] || \
[[ "${sample_name}" == "C18" ]] || \
[[ "${sample_name}" == "C19" ]] || \
[[ "${sample_name}" == "C20" ]] || \
[[ "${sample_name}" == "C21" ]] || \
[[ "${sample_name}" == "C22" ]] || \
[[ "${sample_name}" == "C23" ]] || \
[[ "${sample_name}" == "C24" ]] || \
[[ "${sample_name}" == "C25" ]] || \
[[ "${sample_name}" == "C26" ]] || \
[[ "${sample_name}" == "C27" ]] || \
[[ "${sample_name}" == "C28" ]] || \
[[ "${sample_name}" == "C29" ]] || \
[[ "${sample_name}" == "C30" ]] || \
[[ "${sample_name}" == "C31" ]] || \
[[ "${sample_name}" == "C32" ]];
then
treatment="control"
else
treatment="enriched"
fi
# Append to associative array
samples_associative_array+=(["${sample_name}"]="${treatment}")
done
# Check array size to confirm it has all expected samples
# Exit if mismatch
if [[ "${#samples_associative_array[@]}" != "${sample_counter}" ]] \
|| [[ "${#samples_associative_array[@]}" != "${total_samples}" ]]
then
echo "samples_associative_array doesn't have all ${total_samples} samples."
echo ""
echo "samples_associative_array contents:"
echo ""
for item in "${!samples_associative_array[@]}"
do
printf "%s\t%s\n" "${item}" "${samples_associative_array[${item}]}"
done
exit
fi
# Copy Hisat2 genome index files
echo ""
echo "Transferring HiSat2 index file now."
echo ""
rsync -av "${genome_index_dir}/${index_tarball}" .
echo ""
# Unpack Hisat2 index files
echo ""
echo "Unpacking Hisat2 index tarball: ${index_tarball}..."
echo ""
tar -xzvf ${index_tarball}
echo "Finished unpacking ${index_tarball}"
echo ""
#### BEGIN HISAT2 ALIGNMENTS ####
echo "Beginning HiSat2 alignments and StringTie analysis..."
echo ""
for sample in "${!samples_associative_array[@]}"
do
## Inititalize arrays
fastq_array_R1=()
fastq_array_R2=()
# Create array of fastq R1 files
# and generated MD5 checksums file.
# DO NOT QUOTE ${fastq_pattern}
for fastq in "${fastq_dir}"${R1_fastq_pattern}
do
# Remove path
sample_name="${fastq##*/}"
# Get sample name from first _-delimited field
sample_name=$(echo "${sample_name}" | awk -F "_" '{print $1}')
# Check sample names for match
if [[ "${sample_name}" == "${sample}" ]]
then
echo "Now working on ${sample} Read 1 FastQs."
fastq_array_R1+=("${fastq}")
echo "Generating checksum for ${fastq}..."
md5sum "${fastq}" >> input_fastqs_checksums.md5
echo "Checksum for ${fastq} completed."
echo ""
fi
done
# Create array of fastq R2 files
# DO NOT QUOTE ${fastq_pattern}
for fastq in "${fastq_dir}"${R2_fastq_pattern}
do
# Remove path
sample_name="${fastq##*/}"
# Get sample name from first _-delimited field
sample_name=$(echo "${sample_name}" | awk -F "_" '{print $1}')
# Check sample names for match
if [[ "${sample_name}" == "${sample}" ]]
then
echo "Now working on ${sample} Read 2 FastQs."
fastq_array_R2+=("${fastq}")
echo "Generating checksum for ${fastq}..."
md5sum "${fastq}" >> input_fastqs_checksums.md5
echo "Checksum for ${fastq} completed."
echo ""
fi
done
echo "Checksums for ${sample} Read 1 and 2 completed."
# Create comma-separated lists of FastQs for Hisat2
printf -v joined_R1 '%s,' "${fastq_array_R1[@]}"
fastq_list_R1=$(echo "${joined_R1%,}")
printf -v joined_R2 '%s,' "${fastq_array_R2[@]}"
fastq_list_R2=$(echo "${joined_R2%,}")
# Create and switch to dedicated sample directory
echo ""
echo "Creating ${sample} directory."
mkdir "${sample}" && cd "$_"
echo "Now in ${sample} directory."
# HiSat2 alignments
# Sets read group info (RG) using samples array
echo ""
echo "Running HiSat2 for sample ${sample}."
"${programs_array[hisat2]}" \
-x "${genome_index_name}" \
-1 "${fastq_list_R1}" \
-2 "${fastq_list_R2}" \
-S "${sample}".sam \
--rg-id "${sample}" \
--rg "SM:""${samples_associative_array[$sample]}" \
--threads "${threads}" \
2> "${sample}-hisat2_stats.txt"
echo ""
echo "Hisat2 for ${fastq_list_R1} and ${fastq_list_R2} complete."
echo ""
# Sort SAM files, convert to BAM, and index
echo ""
echo "Sorting ${sample}.sam and creating sorted BAM."
echo ""
${programs_array[samtools_view]} \
-@ "${threads}" \
-Su "${sample}".sam \
| ${programs_array[samtools_sort]} - \
-@ "${threads}" \
-o "${sample}".sorted.bam
echo "Created ${sample}.sorted.bam"
echo ""
# Index BAM
echo ""
echo "Indexing ${sample}.sorted.bam..."
${programs_array[samtools_index]} "${sample}".sorted.bam
echo ""
echo "Indexing complete for ${sample}.sorted.bam."
echo ""
echo ""
echo "HiSat2 completed for sample ${sample}."
echo ""
#### END HISAT2 ALIGNMENTS ####
#### BEGIN STRINGTIE ####
# Run stringtie on alignments
# Uses "-B" option to output tables intended for use in Ballgown
# Uses "-e" option; recommended when using "-B" option.
# Limits analysis to only reads alignments matching reference.
echo "Beginning StringTie analysis on ${sample}.sorted.bam."
"${programs_array[stringtie]}" "${sample}".sorted.bam \
-p "${threads}" \
-o "${sample}".gtf \
-G "${genome_gff}" \
-C "${sample}.cov_refs.gtf" \
-B
echo "StringTie analysis finished for ${sample}.sorted.bam."
echo ""
#### END STRINGTIE ####
# Add GTFs to list file, only if non-empty
# Identifies GTF files that only have header
echo ""
echo "Adding ${sample}.gtf to ../${gtf_list}."
gtf_lines=$(wc -l < "${sample}".gtf )
if [ "${gtf_lines}" -gt 2 ]; then
echo "$(pwd)/${sample}.gtf" >> ../"${gtf_list}"
fi
echo ""
# Delete unneeded SAM files
echo "Removing any SAM files."
echo ""
rm ./*.sam
# Generate checksums
for file in *
do
echo ""
echo "Generating MD5 checksum for ${file}."
echo ""
md5sum "${file}" | tee --append "${sample}_checksums.md5"
echo ""
echo "${file} checksum added to ${sample}_checksums.md5."
echo ""
done
# Move up to orig. working directory
echo "Moving to original working directory."
echo ""
cd ../
echo "Now in $(pwd)."
echo ""
echo "Finished HiSat2 alignments and StringTie analysis for ${sample} FastQs."
echo ""
done
echo "Finished all HiSat2 alignments and StringTie analysis."
echo ""
#### BEGIN MERGING BAMs ####
# Merge all BAMs to singular BAM for use in transcriptome assembly later
## Create list of sorted BAMs for merging
echo ""
echo "Creating list file of sorted BAMs..."
find . -name "*sorted.bam" > sorted_bams.list
echo "List of BAMs created: sorted_bams.list"
echo ""
## Merge sorted BAMs
echo "Merging all BAM files..."
echo ""
${programs_array[samtools_merge]} \
-b sorted_bams.list \
${merged_bam} \
--threads ${threads}
echo ""
echo "Finished creating ${merged_bam}."
#### END MERGING BAMs ####
#### BEGIN INDEXING MERGED BAM ####
## Index merged BAM
echo ""
echo "Indexing ${merged_bam}..."
echo ""
${programs_array[samtools_index]} ${merged_bam}
echo "Finished indexing ${merged_bam}."
echo ""
#### END INDEXING MERGED BAM ####
#### BEGIN MERGE STRINGTIE GTFs ####
# Create singular transcript file, using GTF list file
echo "Merging GTFs..."
echo ""
"${programs_array[stringtie]}" --merge \
"${gtf_list}" \
-p "${threads}" \
-G "${genome_gff}" \
-o "${genome_index_name}.stringtie.gtf"
echo ""
echo "Finished merging GTFs into ${genome_index_name}.stringtie.gtf"
echo ""
#### END MERGE STRINGTIE GTFs ####
# Delete unneccessary index files
echo ""
echo "Removing HiSat2 *.ht2 genome index files..."
echo ""
rm "${genome_index_name}"*.ht2
echo "All genome index files removed."
echo ""
#### BEGIN GFFCOMPARE ####
echo ""
echo "Beginning gffcompare..."
echo ""
# Make ggfcompare output directory and
# change into that directory
mkdir --parents gffcompare && cd "$_"
"${programs_array[gffcompare]}" \
-r "${genome_gff}" \
-o "${genome_index_name}-gffcmp" \
../"${genome_index_name}.stringtie.gtf"
echo ""
echo "Finished gffcompare"
echo ""
# Generate checksums
for file in *
do
echo ""
echo "Generating checksum for ${file}..."
echo ""
md5sum "${file}" | tee --append checksums.md5
echo "Checksum generated."
done
# Move to previous directory
echo "Moving to previous directory..."
echo ""
cd -
echo "Now in $(pwd)."
echo ""
#### END GFFCOMPARE ####
# Generate checksums
echo "Generating checksums for files in $(pwd)."
for file in *
do
echo ""
echo "Generating checksum for ${file}..."
echo ""
md5sum "${file}" | tee --append checksums.md5
echo "Checksum generated."
done
# Remove genome index tarball
echo ""
echo "Removing ${index_tarball}."
rm "${index_tarball}"
echo "${index_tarball} has been deleted."
echo ""
#######################################################################################################
# Capture program options
if [[ "${#programs_array[@]}" -gt 0 ]]; then
echo "Logging program options..."
for program in "${!programs_array[@]}"
do
{
echo "Program options for ${program}: "
echo ""
# Handle samtools help menus
if [[ "${program}" == "samtools_index" ]] \
|| [[ "${program}" == "samtools_sort" ]] \
|| [[ "${program}" == "samtools_view" ]]
then
${programs_array[$program]}
# Handle DIAMOND BLAST menu
elif [[ "${program}" == "diamond" ]]; then
${programs_array[$program]} help
# Handle NCBI BLASTx menu
elif [[ "${program}" == "blastx" ]]; then
${programs_array[$program]} -help
fi
${programs_array[$program]} -h
echo ""
echo ""
echo "----------------------------------------------"
echo ""
echo ""
} &>> program_options.log || true
# If MultiQC is in programs_array, copy the config file to this directory.
if [[ "${program}" == "multiqc" ]]; then
cp --preserve ~/.multiqc_config.yaml multiqc_config.yaml
fi
done
echo "Finished logging programs options."
echo ""
fi
# Document programs in PATH (primarily for program version ID)
echo "Logging system $PATH..."
{
date
echo ""
echo "System PATH for $SLURM_JOB_ID"
echo ""
printf "%0.s-" {1..10}
echo "${PATH}" | tr : \\n
} >> system_path.log
echo "Finished logging system $PATH."
RESULTS
This took a bit over 2 days to run. I’m not posting a screencap of runtime like I usually do because the job died due to the Mox scrubbed partition being full. I ran the remaining commands manually in order to get this done while that storage issue got resolved.
Output folder:
-
20230216-pver-stringtie-Pver_genome_assembly_v1.0-isoforms
-
List of input FastQs and checksums (text):
-
Merged GTF file (GTF; 37MB):
-
Merged BAM file (95GB):
-
-
MD5 checksum:
6b57660fa1795fdb478850ad09b88b51
-
-
Merged BAM index file (useful for IGV; 11MB):
-
gffcomparefiles (text):-
Pver_genome_assembly_v1.0-gffcmp*: See link above for file descriptions. Contents of summary file (Pver_genome_assembly_v1.0-gffcmp):# gffcompare v0.12.6 | Command line was: #/gscratch/srlab/programs/gffcompare-0.12.6.Linux_x86_64/gffcompare -r /gscratch/srlab/sam/data/P_verrucosa/genomes/Pver_genome_assembly_v1.0-valid.gff3 -o Pver_genome_assembly_v1.0-gffcmp Pver_genome_assembly_v1.0.stringtie.gtf # #= Summary for dataset: Pver_genome_assembly_v1.0.stringtie.gtf # Query mRNAs : 27730 in 27400 loci (24124 multi-exon transcripts) # (294 multi-transcript loci, ~1.0 transcripts per locus) # Reference mRNAs : 27695 in 27400 loci (24124 multi-exon) # Super-loci w/ reference transcripts: 27400 #-----------------| Sensitivity | Precision | Base level: 100.0 | 100.0 | Exon level: 100.0 | 100.0 | Intron level: 100.0 | 100.0 | Intron chain level: 100.0 | 100.0 | Transcript level: 100.0 | 99.9 | Locus level: 100.0 | 100.0 | Matching intron chains: 24124 Matching transcripts: 27695 Matching loci: 27400 Missed exons: 0/208892 ( 0.0%) Novel exons: 0/208892 ( 0.0%) Missed introns: 0/181193 ( 0.0%) Novel introns: 0/181193 ( 0.0%) Missed loci: 0/27400 ( 0.0%) Novel loci: 0/27400 ( 0.0%) Total union super-loci across all input datasets: 27400 27730 out of 27730 consensus transcripts written in Pver_genome_assembly_v1.0-gffcmp.annotated.gtf (0 discarded as redundant)
-
-
-
Since there are a large number of folders/files, the resulting directory structure for all of the StringTie output is shown at the end of this post. Here’s a description of all the file types found in each directory:
-
*.ctab: Seeballgowndocumentation for description of these. -
*.checksums.md5: MD5 checksums for all files in each directory. -
*.cov_refs.gtf: Coverage GTF generate byStringTieand used to generate final GTF for each sample. -
*.gtf: Final GTF file produced byStringTiefor each sample. -
*_hisat2.err: Standard error output fromHISAT2. Contains alignment info. -
*.sorted.bam: Sorted BAM alignments file produced byHISAT2. -
*.sorted.bam.bai: BAM index file.
Next up is to get these files imported into ballgown for expression/isoform analyses.
[205G] .
|-- [ 12K] 20230216-pver-stringtie-Pver_genome_assembly_v1.0-isoforms.sh
|-- [ 95G] 20230216-pver-stringtie-pver_v1.0-sorted-bams-merged.bam
|-- [ 11M] 20230216-pver-stringtie-pver_v1.0-sorted-bams-merged.bam.bai
|-- [3.0G] C17
| |-- [ 474] C17_checksums.md5
| |-- [7.8M] C17.cov_refs.gtf
| |-- [ 36M] C17.gtf
| |-- [1014] C17-hisat2_stats.txt
| |-- [3.0G] C17.sorted.bam
| |-- [1.7M] C17.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.6G] C18
| |-- [ 474] C18_checksums.md5
| |-- [7.9M] C18.cov_refs.gtf
| |-- [ 36M] C18.gtf
| |-- [1011] C18-hisat2_stats.txt
| |-- [2.5G] C18.sorted.bam
| |-- [1.6M] C18.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] C19
| |-- [ 474] C19_checksums.md5
| |-- [7.8M] C19.cov_refs.gtf
| |-- [ 36M] C19.gtf
| |-- [1012] C19-hisat2_stats.txt
| |-- [2.7G] C19.sorted.bam
| |-- [1.6M] C19.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] C20
| |-- [ 474] C20_checksums.md5
| |-- [7.9M] C20.cov_refs.gtf
| |-- [ 36M] C20.gtf
| |-- [1011] C20-hisat2_stats.txt
| |-- [2.7G] C20.sorted.bam
| |-- [1.6M] C20.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [1.9G] C21
| |-- [ 474] C21_checksums.md5
| |-- [7.4M] C21.cov_refs.gtf
| |-- [ 36M] C21.gtf
| |-- [1008] C21-hisat2_stats.txt
| |-- [1.9G] C21.sorted.bam
| |-- [1.4M] C21.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] C22
| |-- [ 474] C22_checksums.md5
| |-- [7.7M] C22.cov_refs.gtf
| |-- [ 36M] C22.gtf
| |-- [1014] C22-hisat2_stats.txt
| |-- [2.7G] C22.sorted.bam
| |-- [1.6M] C22.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.4G] C23
| |-- [ 474] C23_checksums.md5
| |-- [7.5M] C23.cov_refs.gtf
| |-- [ 36M] C23.gtf
| |-- [1011] C23-hisat2_stats.txt
| |-- [2.3G] C23.sorted.bam
| |-- [1.5M] C23.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] C24
| |-- [ 474] C24_checksums.md5
| |-- [7.7M] C24.cov_refs.gtf
| |-- [ 36M] C24.gtf
| |-- [1014] C24-hisat2_stats.txt
| |-- [2.7G] C24.sorted.bam
| |-- [1.7M] C24.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.6G] C25
| |-- [ 474] C25_checksums.md5
| |-- [8.2M] C25.cov_refs.gtf
| |-- [ 36M] C25.gtf
| |-- [1014] C25-hisat2_stats.txt
| |-- [3.5G] C25.sorted.bam
| |-- [1.8M] C25.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] C26
| |-- [ 474] C26_checksums.md5
| |-- [7.8M] C26.cov_refs.gtf
| |-- [ 36M] C26.gtf
| |-- [1014] C26-hisat2_stats.txt
| |-- [2.8G] C26.sorted.bam
| |-- [1.7M] C26.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.0G] C27
| |-- [ 474] C27_checksums.md5
| |-- [7.9M] C27.cov_refs.gtf
| |-- [ 36M] C27.gtf
| |-- [1014] C27-hisat2_stats.txt
| |-- [2.9G] C27.sorted.bam
| |-- [1.7M] C27.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.9G] C28
| |-- [ 474] C28_checksums.md5
| |-- [8.0M] C28.cov_refs.gtf
| |-- [ 36M] C28.gtf
| |-- [1014] C28-hisat2_stats.txt
| |-- [2.8G] C28.sorted.bam
| |-- [1.7M] C28.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.2G] C29
| |-- [ 474] C29_checksums.md5
| |-- [7.6M] C29.cov_refs.gtf
| |-- [ 36M] C29.gtf
| |-- [1010] C29-hisat2_stats.txt
| |-- [2.1G] C29.sorted.bam
| |-- [1.6M] C29.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.2G] C30
| |-- [ 474] C30_checksums.md5
| |-- [7.9M] C30.cov_refs.gtf
| |-- [ 36M] C30.gtf
| |-- [1014] C30-hisat2_stats.txt
| |-- [3.1G] C30.sorted.bam
| |-- [1.7M] C30.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] C31
| |-- [ 474] C31_checksums.md5
| |-- [7.9M] C31.cov_refs.gtf
| |-- [ 36M] C31.gtf
| |-- [1012] C31-hisat2_stats.txt
| |-- [2.7G] C31.sorted.bam
| |-- [1.6M] C31.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.2G] C32
| |-- [ 474] C32_checksums.md5
| |-- [8.0M] C32.cov_refs.gtf
| |-- [ 36M] C32.gtf
| |-- [1014] C32-hisat2_stats.txt
| |-- [3.1G] C32.sorted.bam
| |-- [1.7M] C32.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [1.1K] checksums.md5
|-- [ 23G] E1
| |-- [ 469] E1_checksums.md5
| |-- [9.8M] E1.cov_refs.gtf
| |-- [ 36M] E1.gtf
| |-- [1022] E1-hisat2_stats.txt
| |-- [ 22G] E1.sorted.bam
| |-- [4.0M] E1.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 19M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 11M] i_data.ctab
| `-- [2.9M] t_data.ctab
|-- [3.5G] E10
| |-- [ 474] E10_checksums.md5
| |-- [8.0M] E10.cov_refs.gtf
| |-- [ 36M] E10.gtf
| |-- [1014] E10-hisat2_stats.txt
| |-- [3.4G] E10.sorted.bam
| |-- [1.8M] E10.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.2G] E11
| |-- [ 474] E11_checksums.md5
| |-- [7.6M] E11.cov_refs.gtf
| |-- [ 36M] E11.gtf
| |-- [1008] E11-hisat2_stats.txt
| |-- [2.1G] E11.sorted.bam
| |-- [1.5M] E11.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.4G] E12
| |-- [ 474] E12_checksums.md5
| |-- [8.0M] E12.cov_refs.gtf
| |-- [ 36M] E12.gtf
| |-- [1014] E12-hisat2_stats.txt
| |-- [3.3G] E12.sorted.bam
| |-- [1.7M] E12.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.0G] E13
| |-- [ 474] E13_checksums.md5
| |-- [7.9M] E13.cov_refs.gtf
| |-- [ 36M] E13.gtf
| |-- [1014] E13-hisat2_stats.txt
| |-- [2.9G] E13.sorted.bam
| |-- [1.7M] E13.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.6G] E14
| |-- [ 474] E14_checksums.md5
| |-- [7.8M] E14.cov_refs.gtf
| |-- [ 36M] E14.gtf
| |-- [1011] E14-hisat2_stats.txt
| |-- [2.5G] E14.sorted.bam
| |-- [1.6M] E14.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] E15
| |-- [ 474] E15_checksums.md5
| |-- [7.7M] E15.cov_refs.gtf
| |-- [ 36M] E15.gtf
| |-- [1013] E15-hisat2_stats.txt
| |-- [2.8G] E15.sorted.bam
| |-- [1.6M] E15.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.3G] E16
| |-- [ 474] E16_checksums.md5
| |-- [8.1M] E16.cov_refs.gtf
| |-- [ 36M] E16.gtf
| |-- [1013] E16-hisat2_stats.txt
| |-- [3.2G] E16.sorted.bam
| |-- [1.7M] E16.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.9G] E2
| |-- [ 469] E2_checksums.md5
| |-- [8.0M] E2.cov_refs.gtf
| |-- [ 36M] E2.gtf
| |-- [1014] E2-hisat2_stats.txt
| |-- [2.8G] E2.sorted.bam
| |-- [1.7M] E2.sorted.bam.bai
| |-- [2.4M] e2t.ctab
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.9G] E3
| |-- [2.4M] e2t.ctab
| |-- [ 469] E3_checksums.md5
| |-- [7.9M] E3.cov_refs.gtf
| |-- [ 36M] E3.gtf
| |-- [1012] E3-hisat2_stats.txt
| |-- [2.8G] E3.sorted.bam
| |-- [1.6M] E3.sorted.bam.bai
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.5G] E4
| |-- [2.4M] e2t.ctab
| |-- [ 469] E4_checksums.md5
| |-- [7.7M] E4.cov_refs.gtf
| |-- [ 36M] E4.gtf
| |-- [1011] E4-hisat2_stats.txt
| |-- [2.4G] E4.sorted.bam
| |-- [1.5M] E4.sorted.bam.bai
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.0G] E5
| |-- [2.4M] e2t.ctab
| |-- [ 469] E5_checksums.md5
| |-- [7.5M] E5.cov_refs.gtf
| |-- [ 36M] E5.gtf
| |-- [1010] E5-hisat2_stats.txt
| |-- [2.0G] E5.sorted.bam
| |-- [1.5M] E5.sorted.bam.bai
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.8G] E6
| |-- [2.4M] e2t.ctab
| |-- [ 469] E6_checksums.md5
| |-- [7.7M] E6.cov_refs.gtf
| |-- [ 36M] E6.gtf
| |-- [1011] E6-hisat2_stats.txt
| |-- [2.7G] E6.sorted.bam
| |-- [1.6M] E6.sorted.bam.bai
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.7G] E7
| |-- [2.4M] e2t.ctab
| |-- [ 469] E7_checksums.md5
| |-- [8.0M] E7.cov_refs.gtf
| |-- [ 36M] E7.gtf
| |-- [1011] E7-hisat2_stats.txt
| |-- [2.7G] E7.sorted.bam
| |-- [1.6M] E7.sorted.bam.bai
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [2.7G] E8
| |-- [2.4M] e2t.ctab
| |-- [ 469] E8_checksums.md5
| |-- [7.8M] E8.cov_refs.gtf
| |-- [ 36M] E8.gtf
| |-- [1011] E8-hisat2_stats.txt
| |-- [2.6G] E8.sorted.bam
| |-- [1.6M] E8.sorted.bam.bai
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.1G] E9
| |-- [2.4M] e2t.ctab
| |-- [ 469] E9_checksums.md5
| |-- [7.8M] E9.cov_refs.gtf
| |-- [ 36M] E9.gtf
| |-- [1014] E9-hisat2_stats.txt
| |-- [3.0G] E9.sorted.bam
| |-- [1.7M] E9.sorted.bam.bai
| |-- [ 18M] e_data.ctab
| |-- [2.1M] i2t.ctab
| |-- [ 10M] i_data.ctab
| `-- [2.8M] t_data.ctab
|-- [3.3K] gtf_list.txt
|-- [8.4K] input_fastqs_checksums.md5
|-- [1.5K] Pver_genome_assembly_v1.0-gffcmp
|-- [ 33M] Pver_genome_assembly_v1.0-gffcmp.annotated.gtf
|-- [2.6M] Pver_genome_assembly_v1.0-gffcmp.loci
|-- [1.6M] Pver_genome_assembly_v1.0-gffcmp.Pver_genome_assembly_v1.0.stringtie.gtf.refmap
|-- [3.1M] Pver_genome_assembly_v1.0-gffcmp.Pver_genome_assembly_v1.0.stringtie.gtf.tmap
|-- [3.3M] Pver_genome_assembly_v1.0-gffcmp.tracking
|-- [ 37M] Pver_genome_assembly_v1.0.stringtie.gtf
|-- [ 87K] slurm-4469382.out
`-- [ 654] sorted_bams.list
205G used in 32 directories, 367 files