Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

KMC on TheiaProk_ONT and TheiaCoV_ONT #193

Merged
merged 1 commit into from
Sep 22, 2023
Merged

KMC on TheiaProk_ONT and TheiaCoV_ONT #193

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions tasks/utilities/task_kmc.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,9 @@ task kmc {
command <<<
kmc | head -n 1 | tee VERSION

# initialize kmc output
echo 0 > UNIQUE_COUNTED

# run kmc
# kmc [options] <input_file> <output_file> <working_dir>
# -sm - uses strict memory mode (memory from -m<size> switch will not be exceeded)
Expand All @@ -38,13 +41,13 @@ task kmc {
# kmc_outputs is a mess of files that are not human readable
# however, the stdout does produce some useful stats.
# the no. of unique counted k-mers can be used as an estimate of genome size
grep "unique counted k" LOG | tr -s ' ' | cut -d ' ' -f8 > UNIQUE_COUNTED
grep "unique counted k" LOG | tr -s ' ' | cut -d ' ' -f8 >> UNIQUE_COUNTED

# extracting only the kmer statistics and writing to file:
tail -n8 LOG > ~{samplename}_kmer_stats.txt
>>>
output {
String est_genome_size = read_string("UNIQUE_COUNTED")
Int est_genome_size = read_int("UNIQUE_COUNTED")
File kmer_stats = "~{samplename}_kmer_stats.txt"
String kmc_version = read_string("VERSION")
}
Expand Down
2 changes: 1 addition & 1 deletion workflows/theiaprok/wf_theiaprok_ont.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -489,7 +489,7 @@ workflow theiaprok_ont {
String? nanoplot_version = nanoplot_raw.nanoplot_version
String? nanoplot_docker = nanoplot_raw.nanoplot_docker
# Read QC - kmc outputs
String? kmc_est_genome_size = read_qc_trim.est_genome_size
Int? kmc_est_genome_size = read_qc_trim.est_genome_size
File? kmc_kmer_stats = read_qc_trim.kmc_kmer_stats
String? kmc_version = read_qc_trim.kmc_version
# Read QC - rasusa outputs
Expand Down
22 changes: 11 additions & 11 deletions workflows/utilities/wf_read_QC_trim_ont.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,12 +27,6 @@ workflow read_QC_trim_ont {
# kraken inputs
String? target_org
}
# kmc for genome size estimation
call kmc_task.kmc {
input:
read1 = read1,
samplename = samplename
}
if ("~{workflow_series}" == "theiacov") {
call ncbi_scrub.ncbi_scrub_se {
input:
Expand Down Expand Up @@ -61,6 +55,12 @@ workflow read_QC_trim_ont {
}
}
if ("~{workflow_series}" == "theiaprok") {
# kmc for genome size estimation
call kmc_task.kmc {
input:
read1 = read1,
samplename = samplename
}
# rasusa for random downsampling
call rasusa_task.rasusa {
input:
Expand All @@ -83,11 +83,6 @@ workflow read_QC_trim_ont {
}
}
output {
# kmc outputs
String est_genome_size = kmc.est_genome_size
File kmc_kmer_stats = kmc.kmer_stats
String kmc_version = kmc.kmc_version

# theiacov outputs
# ncbi scrub outputs
File? read1_dehosted = ncbi_scrub_se.read1_dehosted
Expand All @@ -109,6 +104,11 @@ workflow read_QC_trim_ont {
File? kraken_report_dehosted = kraken2_dehosted.kraken_report

# theiaprok outputs
# kmc outputs
Int? est_genome_size = kmc.est_genome_size
File? kmc_kmer_stats = kmc.kmer_stats
String? kmc_version = kmc.kmc_version

# nanoq outputs
File read1_clean = select_first([nanoq.filtered_read1, read_filtering.filtered_reads])
String? nanoq_version = nanoq.version
Expand Down