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.

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

TheiaCoV_ONT_PHB Influenza Track #233

Merged
merged 4 commits into from
Nov 21, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
27 changes: 17 additions & 10 deletions tasks/assembly/task_irma.wdl
Original file line number Diff line number Diff line change
Expand Up @@ -3,12 +3,12 @@ version 1.0
task irma {
input {
File read1
File read2
File? read2
String seq_method
String samplename
Boolean keep_ref_deletions = true
String irma_module = "FLU"
String read_basename = basename(read1)
String docker = "us-docker.pkg.dev/general-theiagen/staphb/irma:1.0.3"
String docker = "cdcgov/irma:v1.1.3"
Int memory = 8
Int cpu = 4
Int disk_size = 100
Expand All @@ -17,7 +17,9 @@ task irma {
date | tee DATE
#capture reads as bash variables
read1=~{read1}
read2=~{read2}
if [[ "~{read2}" ]]; then
read2=~{read2}
fi
# set cat command based on compression
if [[ "~{read1}" == *".gz" ]] ; then
cat_reads="zcat"
Expand All @@ -38,15 +40,20 @@ task irma {
echo "Read headers may lead to IRMA failure; reformatting to meet IRMA input requirements"
sra_id=$(echo "~{read_basename}" | awk -F "_" '{ print $1 }')
eval "${cat_reads} ~{read1}" | awk '{print (NR%4 == 1) ? "@'${sra_id}'-" ++i " 1:1" : $0}' | gzip -c > "${sra_id}-irmafix_R1.fastq.gz"
eval "${cat_reads} ~{read2}" | awk '{print (NR%4 == 1) ? "@'${sra_id}'-" ++i " 2:2" : $0}' | gzip -c > "${sra_id}-irmafix_R2.fastq.gz"
#modify read variables
read1="${sra_id}-irmafix_R1.fastq.gz"
read2="${sra_id}-irmafix_R2.fastq.gz"
if [[ "~{read2}" ]]; then
eval "${cat_reads} ~{read2}" | awk '{print (NR%4 == 1) ? "@'${sra_id}'-" ++i " 2:2" : $0}' | gzip -c > "${sra_id}-irmafix_R2.fastq.gz"
read2="${sra_id}-irmafix_R2.fastq.gz"
fi
else
echo "Read headers match IRMA formatting requirements"
fi
# run IRMA
IRMA "~{irma_module}" "${read1}" "${read2}" ~{samplename}
# set IRMA module depending on sequencing technology
if [[ ~{seq_method} == "OXFORD_NANOPORE" ]]; then
IRMA "FLU-minion" "${read1}" ~{samplename}
else
IRMA "FLU" "${read1}" "${read2}" ~{samplename}
fi
# capture IRMA type
if compgen -G "~{samplename}/*fasta"; then
echo "Type_"$(basename "$(echo "$(find ~{samplename}/*.fasta | head -n1)")" | cut -d_ -f1) > IRMA_TYPE
Expand Down Expand Up @@ -102,4 +109,4 @@ task irma {
maxRetries: 3
preemptible: 0
}
}
}
2 changes: 1 addition & 1 deletion tests/inputs/theiacov/wf_theiacov_ont.json
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
{
"theiacov_ont.samplename": "ont",
"theiacov_ont.demultiplexed_reads": "tests/data/theiacov/fastqs/ont/ont.fastq.gz",
"theiacov_ont.read1": "tests/data/theiacov/fastqs/ont/ont.fastq.gz",
"theiacov_ont.primer_bed": "tests/data/theiacov/primers/artic-v3.primers.bed"
}
1 change: 1 addition & 0 deletions workflows/theiacov/wf_theiacov_illumina_pe.wdl
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ workflow theiacov_illumina_pe {
read1 = read_QC_trim.read1_clean,
read2 = read_QC_trim.read2_clean,
samplename = samplename,
seq_method = seq_method
}
if (defined(irma.irma_assemblies)) {
call abricate.abricate_flu {
Expand Down
Loading