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

Replace CSVTK_JOIN to improve processing in large amount of files #486

Merged
merged 10 commits into from
Dec 12, 2024
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
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

- [[#481]](https://github.com/nf-core/smrnaseq/pull/481) - Fix [MIRTOP_STATS IndexError](https://github.com/nf-core/smrnaseq/issues/477) - Fix mirtop process execution when mirgenedb is used.
- [[#482]](https://github.com/nf-core/smrnaseq/pull/482) - Update documentation regarding MirgeneDB input files.
- [[#486]](https://github.com/nf-core/smrnaseq/pull/486) - Replace `CSVTK_JOIN` to improve processing in large amount of files.

## v2.4.0 - 2024-10-14 - Navy Iron Boxer

Expand Down
29 changes: 29 additions & 0 deletions bin/pivot_longer.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
#!/usr/bin/env Rscript

library(optparse)
library(tidyr)
library(vroom)

option_list <- list(
make_option(c("--input"), type = "character", help = "Input TSV file", metavar = "character"),
make_option(c("--output"), type = "character", help = "Output CSV file", metavar = "character")
)

opt_parser <- OptionParser(option_list = option_list)
opt <- parse_args(opt_parser)

# Read CSV with vroom
data <- vroom::vroom(opt$input, delim = "\t", col_types = c(.default = "c"))

last_col <- names(data)[ncol(data)]

# Convert from wide to long format
long_data <- data %>%
pivot_longer(
cols = last_col,
names_to = "Sample_ID",
values_to = "Counts"
)

vroom_write(long_data, opt$output, delim = ",")

32 changes: 32 additions & 0 deletions bin/pivot_wider.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
#!/usr/bin/env Rscript

library(optparse)
library(tidyr)
library(vroom)
library(dplyr)

option_list <- list(
make_option(c("--input"), type = "character", help = "Input CSV file in long format", metavar = "character"),
make_option(c("--output"), type = "character", help = "Output CSV file in wide format", metavar = "character")
)

opt_parser <- OptionParser(option_list = option_list)
opt <- parse_args(opt_parser)

# Read CSV with vroom
long_data <- vroom::vroom(opt$input, delim = ",",
col_types = c(
Counts = "d",
.default = "c"
))

# Transform to wide format
wide_data <- long_data %>%
pivot_wider(
names_from = Sample_ID,
values_from = Counts,
values_fill = 0
)

# Export wide format
vroom_write(wide_data, opt$output, delim = "\t")
8 changes: 5 additions & 3 deletions conf/modules.config
Original file line number Diff line number Diff line change
Expand Up @@ -468,9 +468,11 @@ process {
]
}

withName: 'NFCORE_SMRNASEQ:MIRNA_QUANT:CSVTK_JOIN' {
ext.args = "--fields 'UID,Read,miRNA,Variant,iso_5p,iso_3p,iso_add3p,iso_snp,iso_5p_nt,iso_3p_nt,iso_add3p_nt,iso_snp_nt' --tabs --outer-join --na \"0\" --out-delimiter \"\t\""
ext.prefix = "joined_samples_mirtop"
withName: 'NFCORE_SMRNASEQ:MIRNA_QUANT:PIVOT_LONGER' {
publishDir = [ enabled: false ]
}

withName: 'NFCORE_SMRNASEQ:MIRNA_QUANT:PIVOT_WIDER' {
publishDir = [
path: { "${params.outdir}/mirna_quant/mirtop" },
mode: params.publish_dir_mode,
Expand Down
5 changes: 5 additions & 0 deletions modules/local/pivot/longer/environment.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
channels:
- conda-forge
dependencies:
- conda-forge::r-optparse
- conda-forge::r-tidyverse
29 changes: 29 additions & 0 deletions modules/local/pivot/longer/main.nf
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
process PIVOT_LONGER {
tag"$meta.id"
label 'process_single'

conda "${moduleDir}/environment.yml"
container "community.wave.seqera.io/library/r-optparse_r-tidyverse_r-vroom:3cbb224fea84a0e1"

input:
tuple val(meta), path(tsv)

output:
tuple val(meta), path("*_long.csv") , emit: csv
path "versions.yml" , emit: versions

script:
"""
pivot_longer.R \\
--input ${tsv} \\
--output ${meta.id}_long.csv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
r-base: \$(echo \$(R --version 2>&1) | sed 's/^.*R version //; s/ .*\$//')
tidyr: \$(Rscript -e "library(tidyr); cat(as.character(packageVersion('tidyr')))")
optparse: \$(Rscript -e "library(optparse); cat(as.character(packageVersion('optparse')))")
END_VERSIONS
"""

}
5 changes: 5 additions & 0 deletions modules/local/pivot/wider/environment.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
channels:
- conda-forge
dependencies:
- conda-forge::r-optparse
- conda-forge::r-tidyverse
35 changes: 35 additions & 0 deletions modules/local/pivot/wider/main.nf
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
process PIVOT_WIDER {
tag"$meta.id"
label 'process_high'

conda "${moduleDir}/environment.yml"
container "community.wave.seqera.io/library/r-optparse_r-tidyverse_r-vroom:3cbb224fea84a0e1"

input:
tuple val(meta), path(csvs)

output:
tuple val(meta), path("*joined_samples_mirtop.tsv") , emit: csv
path "versions.yml" , emit: versions

script:
"""
awk 'NR == 1 || FNR > 1' ${csvs.join(' ')} > final_long_results_temp.csv

pivot_wider.R \\
--input final_long_results_temp.csv \\
--output ${meta.id}_concatenated_temp.csv

sort -t\$'\t' -k1,1 ${meta.id}_concatenated_temp.csv > joined_samples_mirtop.tsv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
r-base: \$(echo \$(R --version 2>&1) | sed 's/^.*R version //; s/ .*\$//')
tidyr: \$(Rscript -e "library(tidyr); cat(as.character(packageVersion('tidyr')))")
dplyr: \$(Rscript -e "library(dplyr); cat(as.character(packageVersion('dplyr')))")
optparse: \$(Rscript -e "library(optparse); cat(as.character(packageVersion('optparse')))")
vroom: \$(Rscript -e "library(vroom); cat(as.character(packageVersion('vroom')))")
END_VERSIONS
"""

}
19 changes: 16 additions & 3 deletions subworkflows/local/mirna_quant.nf
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,9 @@ include { EDGER_QC } from '../../modules/local/edger_qc/main'
include { BAM_STATS_MIRNA_MIRTOP } from '../../subworkflows/nf-core/bam_stats_mirna_mirtop/main'
include { CSVTK_JOIN } from '../../modules/nf-core/csvtk/join/main'

include { PIVOT_LONGER } from '../../modules/local/pivot/longer/main'
include { PIVOT_WIDER } from '../../modules/local/pivot/wider/main'

workflow MIRNA_QUANT {
take:
ch_reference_mature // channel: [ val(meta), fasta file]
Expand Down Expand Up @@ -105,10 +108,20 @@ workflow MIRNA_QUANT {
.collect{it[1]}
.map{it -> return [[id:"TSVs"], it]}

CSVTK_JOIN ( ch_tsvs )
ch_versions = ch_versions.mix(CSVTK_JOIN.out.versions)
PIVOT_LONGER( BAM_STATS_MIRNA_MIRTOP.out.counts )
ch_versions = ch_versions.mix(PIVOT_LONGER.out.versions)

ch_long_files = PIVOT_LONGER.out.csv
.map { meta, file -> file }
.collect()
.map { files ->
return [[id: "Long_Files"], files]
}

PIVOT_WIDER( ch_long_files )
ch_versions = ch_versions.mix(PIVOT_WIDER.out.versions)

DATATABLE_MERGE ( CSVTK_JOIN.out.csv )
DATATABLE_MERGE ( PIVOT_WIDER.out.csv )
ch_versions = ch_versions.mix(DATATABLE_MERGE.out.versions)

ch_reads_genome = BOWTIE_MAP_HAIRPIN.out.fastq
Expand Down
2 changes: 1 addition & 1 deletion tests/test_contamination_tech_reps.nf.test
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ nextflow_pipeline {
assertAll(
{ assert workflow.success },
{ assert snapshot(UTILS.removeNextflowVersion("$outputDir")).match("software_versions") },
{ assert workflow.trace.succeeded().size() == 100 },
{ assert workflow.trace.succeeded().size() == 103 },

{ assert snapshot(
path("$outputDir/contaminant_filter/filter/Clone1_N1_trimmed.contamination_mqc.yaml").exists(), //TODO see if we can make these deterministic or why they are non-deterministic
Expand Down
20 changes: 10 additions & 10 deletions tests/test_contamination_tech_reps.nf.test.snap
Original file line number Diff line number Diff line change
Expand Up @@ -34,13 +34,13 @@
},
"software_versions": {
"content": [
"{BLAT_CDNA={blat=36}, BLAT_NCRNA={blat=36}, BOWTIE2_ALIGN_CDNA={bowtie2=2.5.2, samtools=1.18, pigz=2.6}, BOWTIE2_ALIGN_NCRNA={bowtie2=2.5.2, samtools=1.18, pigz=2.6}, BOWTIE2_ALIGN_TRNA={bowtie2=2.5.2, samtools=1.18, pigz=2.6}, BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, CAT_FASTQ={cat=8.3}, CSVTK_JOIN={csvtk=0.30.0}, DATATABLE_MERGE={r-base=3.6.2}, FASTP={fastp=0.23.4}, FILTER_STATS={BusyBox=1.32.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, GAWK_CDNA={gawk=5.3.0}, GAWK_NCRNA={gawk=5.3.0}, INDEX_CDNA={bowtie2=2.5.2}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, INDEX_NCRNA={bowtie2=2.5.2}, INDEX_TRNA={bowtie2=2.5.2}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, MIRTRACE_QC={mirtrace=1.0.1}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, SEQKIT_GREP_CDNA={seqkit=2.8.0}, SEQKIT_GREP_NCRNA={seqkit=2.8.0}, STATS_GAWK_CDNA={gawk=5.3.0}, STATS_GAWK_NCRNA={gawk=5.3.0}, STATS_GAWK_TRNA={gawk=5.3.0}, Workflow={nf-core/smrnaseq=v2.4.0}}"
"{BLAT_CDNA={blat=36}, BLAT_NCRNA={blat=36}, BOWTIE2_ALIGN_CDNA={bowtie2=2.5.2, samtools=1.18, pigz=2.6}, BOWTIE2_ALIGN_NCRNA={bowtie2=2.5.2, samtools=1.18, pigz=2.6}, BOWTIE2_ALIGN_TRNA={bowtie2=2.5.2, samtools=1.18, pigz=2.6}, BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, CAT_FASTQ={cat=8.3}, DATATABLE_MERGE={r-base=3.6.2}, FASTP={fastp=0.23.4}, FILTER_STATS={BusyBox=1.32.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, GAWK_CDNA={gawk=5.3.0}, GAWK_NCRNA={gawk=5.3.0}, INDEX_CDNA={bowtie2=2.5.2}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, INDEX_NCRNA={bowtie2=2.5.2}, INDEX_TRNA={bowtie2=2.5.2}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, MIRTRACE_QC={mirtrace=1.0.1}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, PIVOT_LONGER={r-base=4.4.2, tidyr=1.3.1, optparse=1.7.5}, PIVOT_WIDER={r-base=4.4.2, tidyr=1.3.1, dplyr=1.1.4, optparse=1.7.5, vroom=1.6.5}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, SEQKIT_GREP_CDNA={seqkit=2.8.0}, SEQKIT_GREP_NCRNA={seqkit=2.8.0}, STATS_GAWK_CDNA={gawk=5.3.0}, STATS_GAWK_NCRNA={gawk=5.3.0}, STATS_GAWK_TRNA={gawk=5.3.0}, Workflow={nf-core/smrnaseq=v2.4.0}}"
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.04.4"
"nextflow": "24.10.2"
},
"timestamp": "2024-10-08T23:16:26.853242481"
"timestamp": "2024-12-10T00:29:32.052341"
},
"mirna_quant_bam": {
"content": [
Expand All @@ -65,9 +65,9 @@
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.04.4"
"nextflow": "24.10.2"
},
"timestamp": "2024-10-01T20:06:04.974546479"
"timestamp": "2024-12-10T00:29:32.116301175"
},
"mirna_quant_edger_qc": {
"content": [
Expand All @@ -90,9 +90,9 @@
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.04.4"
"nextflow": "24.10.2"
},
"timestamp": "2024-10-01T20:06:05.025175321"
"timestamp": "2024-12-10T00:29:32.164075991"
},
"contaminant_filter_filter": {
"content": [
Expand All @@ -113,8 +113,8 @@
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.04.4"
"nextflow": "24.10.2"
},
"timestamp": "2024-10-01T20:06:05.070939602"
"timestamp": "2024-12-10T00:29:32.208602197"
}
}
}
2 changes: 1 addition & 1 deletion tests/test_mirgenedb.nf.test
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ nextflow_pipeline {
assertAll(
{ assert workflow.success },
{ assert snapshot(UTILS.removeNextflowVersion("$outputDir")).match("software_versions") },
{ assert workflow.trace.succeeded().size() == 104 },
{ assert workflow.trace.succeeded().size() == 107 },
{ assert workflow.trace.failed().size() == 1 },

{ assert snapshot(
Expand Down
6 changes: 3 additions & 3 deletions tests/test_mirgenedb.nf.test.snap
Original file line number Diff line number Diff line change
Expand Up @@ -19,13 +19,13 @@
},
"software_versions": {
"content": [
"{BOWTIE_MAP_GENOME={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, CSVTK_JOIN={csvtk=0.30.0}, DATATABLE_MERGE={r-base=3.6.2}, FASTP={fastp=0.23.4}, FASTQC_RAW={fastqc=0.12.1}, FASTQC_TRIM={fastqc=0.12.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, MIRDEEP2_MAPPER={mirdeep2=2.0.1}, MIRDEEP2_MIRDEEP2={mirdeep2=2.0.1}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, SEQKIT_FQ2FA={seqkit=2.8.0}, SEQKIT_REPLACE={seqkit=2.8.0}, Workflow={nf-core/smrnaseq=v2.4.0}}"
"{BOWTIE_MAP_GENOME={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, DATATABLE_MERGE={r-base=3.6.2}, FASTP={fastp=0.23.4}, FASTQC_RAW={fastqc=0.12.1}, FASTQC_TRIM={fastqc=0.12.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, MIRDEEP2_MAPPER={mirdeep2=2.0.1}, MIRDEEP2_MIRDEEP2={mirdeep2=2.0.1}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, PIVOT_LONGER={r-base=4.4.2, tidyr=1.3.1, optparse=1.7.5}, PIVOT_WIDER={r-base=4.4.2, tidyr=1.3.1, dplyr=1.1.4, optparse=1.7.5, vroom=1.6.5}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, SEQKIT_FQ2FA={seqkit=2.8.0}, SEQKIT_REPLACE={seqkit=2.8.0}, Workflow={nf-core/smrnaseq=v2.4.0}}"
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.10.0"
"nextflow": "24.10.2"
},
"timestamp": "2024-11-11T13:44:14.583324793"
"timestamp": "2024-12-10T00:35:18.448206326"
},
"mirna_quant_bam": {
"content": [
Expand Down
2 changes: 1 addition & 1 deletion tests/test_nextflex.nf.test
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ nextflow_pipeline {
assertAll(
{ assert workflow.success },
{ assert snapshot(UTILS.removeNextflowVersion("$outputDir")).match("software_versions") },
{ assert workflow.trace.succeeded().size() == 79 },
{ assert workflow.trace.succeeded().size() == 82 },

{ assert snapshot(
path("$outputDir/mirna_quant/bam/mature/sample2_mature.sorted.idxstats"),
Expand Down
8 changes: 4 additions & 4 deletions tests/test_nextflex.nf.test.snap
Original file line number Diff line number Diff line change
Expand Up @@ -34,13 +34,13 @@
},
"software_versions": {
"content": [
"{BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, CSVTK_JOIN={csvtk=0.30.0}, DATATABLE_MERGE={r-base=3.6.2}, FASTP={fastp=0.23.4}, FASTQC_RAW={fastqc=0.12.1}, FASTQC_TRIM={fastqc=0.12.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, MIRTRACE_QC={mirtrace=1.0.1}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, Workflow={nf-core/smrnaseq=v2.4.0}}"
"{BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, DATATABLE_MERGE={r-base=3.6.2}, FASTP={fastp=0.23.4}, FASTQC_RAW={fastqc=0.12.1}, FASTQC_TRIM={fastqc=0.12.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, MIRTRACE_QC={mirtrace=1.0.1}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, PIVOT_LONGER={r-base=4.4.2, tidyr=1.3.1, optparse=1.7.5}, PIVOT_WIDER={r-base=4.4.2, tidyr=1.3.1, dplyr=1.1.4, optparse=1.7.5, vroom=1.6.5}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, Workflow={nf-core/smrnaseq=v2.4.0}}"
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.04.4"
"nextflow": "24.10.2"
},
"timestamp": "2024-10-08T23:25:57.880948228"
"timestamp": "2024-12-10T00:37:47.333537716"
},
"mirna_quant_bam": {
"content": [
Expand Down Expand Up @@ -142,4 +142,4 @@
},
"timestamp": "2024-09-20T17:11:24.369706104"
}
}
}
2 changes: 1 addition & 1 deletion tests/test_skipfastp.nf.test
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ nextflow_pipeline {
assertAll(
{ assert workflow.success },
{ assert snapshot(UTILS.removeNextflowVersion("$outputDir")).match("software_versions") },
{ assert workflow.trace.succeeded().size() == 64 },
{ assert workflow.trace.succeeded().size() == 66 },

{ assert snapshot(
path("$outputDir/mirna_quant/mirtop/joined_samples_mirtop.tsv").exists(),
Expand Down
8 changes: 4 additions & 4 deletions tests/test_skipfastp.nf.test.snap
Original file line number Diff line number Diff line change
Expand Up @@ -41,13 +41,13 @@
},
"software_versions": {
"content": [
"{BOWTIE_MAP_GENOME={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, CSVTK_JOIN={csvtk=0.30.0}, DATATABLE_MERGE={r-base=3.6.2}, FASTQC_RAW={fastqc=0.12.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, MIRTRACE_QC={mirtrace=1.0.1}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, Workflow={nf-core/smrnaseq=v2.4.0}}"
"{BOWTIE_MAP_GENOME={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_HAIRPIN={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_MATURE={bowtie=1.3.0, samtools=1.16.1}, BOWTIE_MAP_SEQCLUSTER={bowtie=1.3.0, samtools=1.16.1}, DATATABLE_MERGE={r-base=3.6.2}, FASTQC_RAW={fastqc=0.12.1}, FORMAT_HAIRPIN={fastx_toolkit=0.0.14}, FORMAT_MATURE={fastx_toolkit=0.0.14}, INDEX_HAIRPIN={bowtie=1.3.0}, INDEX_MATURE={bowtie=1.3.0}, MIRTOP_COUNTS={mirtop=0.4.28}, MIRTOP_EXPORT={mirtop=0.4.28}, MIRTOP_GFF={mirtop=0.4.28}, MIRTOP_STATS={mirtop=0.4.28}, MIRTRACE_QC={mirtrace=1.0.1}, PARSE_HAIRPIN={seqkit=2.6.1}, PARSE_MATURE={seqkit=2.6.1}, PIVOT_LONGER={r-base=4.4.2, tidyr=1.3.1, optparse=1.7.5}, PIVOT_WIDER={r-base=4.4.2, tidyr=1.3.1, dplyr=1.1.4, optparse=1.7.5, vroom=1.6.5}, SAMTOOLS_FLAGSTAT={samtools=1.21}, SAMTOOLS_IDXSTATS={samtools=1.21}, SAMTOOLS_INDEX={samtools=1.21}, SAMTOOLS_SORT={samtools=1.21}, SAMTOOLS_STATS={samtools=1.21}, SEQCLUSTER_COLLAPSE={seqcluster=1.2.9}, Workflow={nf-core/smrnaseq=v2.4.0}}"
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.04.4"
"nextflow": "24.10.2"
},
"timestamp": "2024-10-08T23:28:49.241105443"
"timestamp": "2024-12-10T00:40:10.829696529"
},
"mirna_quant_bam": {
"content": [
Expand Down Expand Up @@ -142,4 +142,4 @@
},
"timestamp": "2024-10-01T20:19:25.557700049"
}
}
}
Loading
Loading