Skip to content

Commit

Permalink
Merge pull request #83 from nf-core/caching
Browse files Browse the repository at this point in the history
Fix caching problems
  • Loading branch information
nictru committed Jan 30, 2024
2 parents 6268eb5 + cf629ae commit 9999e23
Show file tree
Hide file tree
Showing 26 changed files with 80 additions and 140 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -67,4 +67,4 @@ jobs:
- name: Run pipeline with test data
run: |
nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets
nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets
2 changes: 2 additions & 0 deletions bin/circRNA_counts_matrix.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
#!/usr/bin/env python

import sys, glob
from collections import defaultdict

Expand Down
2 changes: 1 addition & 1 deletion bin/reformat_count_matrix.R
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
## License: MIT

library(dplyr)
mat <- read.table("circRNA_matrix.txt", sep="\t", header=T, stringsAsFactors=F)
mat <- read.table("circRNA_matrix.txt", sep="\t", header=T, stringsAsFactors=F, check.names=F)
mat$ID <- with(mat, paste0(Chr, sep=":", Start, sep="-", Stop, sep=":", Strand))
mat <- mat[,-c(1:4)]
mat1 <- mat %>% select(ID, everything())
Expand Down
20 changes: 10 additions & 10 deletions conf/test.config
Original file line number Diff line number Diff line change
Expand Up @@ -19,16 +19,16 @@ params {
max_memory = 6.GB
max_time = 6.h

// Input data for test data
input = 'https://raw.githubusercontent.com/nf-core/test-datasets/circrna/samples.csv'
fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/circrna/reference/chrI.fa'
gtf = 'https://raw.githubusercontent.com/nf-core/test-datasets/circrna/reference/chrI.gtf'
mature = 'https://raw.githubusercontent.com/nf-core/test-datasets/circrna/reference/mature.fa'
species = 'cel'
tool = 'circexplorer2'
phenotype = 'https://raw.githubusercontent.com/nf-core/test-datasets/circrna/phenotype.csv'
// Test input data
input = "${params.test_data_base}/samples.csv"
fasta = "${params.test_data_base}/reference/chrI.fa"
gtf = "${params.test_data_base}/reference/chrI.gtf"
mature = "${params.test_data_base}/reference/mature.fa"
tool = "circexplorer2"
phenotype = "${params.test_data_base}/phenotype.csv"
skip_trimming = false
module = 'circrna_discovery,mirna_prediction,differential_expression'
outdir = 'results/'
module = "circrna_discovery,mirna_prediction,differential_expression"
outdir = "results/"
bsj_reads = 2
species = "cel"
}
34 changes: 0 additions & 34 deletions conf/test_cache.config

This file was deleted.

2 changes: 1 addition & 1 deletion modules/local/annotation/full_annotation/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ process ANNOTATION {
annotate_outputs.sh $exon_boundary &> ${prefix}.log
mv master_bed12.bed ${prefix}.bed.tmp
awk -v FS="\t" '{print \$11}' ${prefix}.bed.tmp > mature_len.tmp
awk -v FS="\\t" '{print \$11}' ${prefix}.bed.tmp > mature_len.tmp
awk -v FS="," '{for(i=t=0;i<NF;) t+=\$++i; \$0=t}1' mature_len.tmp > mature_length
paste ${prefix}.bed.tmp mature_length > ${prefix}.bed
Expand Down
4 changes: 2 additions & 2 deletions modules/local/annotation/parent_gene/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -35,14 +35,14 @@ process PARENT_GENE {
start=\$(echo \$line | cut -d- -f1 | cut -d: -f2)
stop=\$(echo \$line | cut -d- -f2 | cut -d: -f1)
sign=\$(echo \$line | cut -d: -f3)
echo -e "\$chr\t\$start\t\$stop\t\$name\t0\t\$sign" >> \${name}.bed
echo -e "\$chr\\t\$start\\t\$stop\\t\$name\\t0\\t\$sign" >> \${name}.bed
done < IDs.txt
cat *.bed > merged.txt && rm IDs.txt && rm *.bed && mv merged.txt circs.bed
# Re-use annotation script to identify the host gene.
annotate_outputs.sh $exon_boundary &> annotation.log
awk -v OFS="\t" '{print \$4, \$14}' master_bed12.bed > circrna_host-gene.txt
awk -v OFS="\\t" '{print \$4, \$14}' master_bed12.bed > circrna_host-gene.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
4 changes: 2 additions & 2 deletions modules/local/circexplorer2/filter/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -24,9 +24,9 @@ process CIRCEXPLORER2_FILTER {
prefix = task.ext.prefix ?: "${meta.id}"
def VERSION = '1.3.4'
"""
awk '{if(\$13 >= ${bsj_reads}) print \$0}' ${prefix}.txt | awk -v OFS="\t" '{print \$1,\$2,\$3,\$6,\$13}' > ${prefix}_${meta.tool}.bed
awk '{if(\$13 >= ${bsj_reads}) print \$0}' ${prefix}.txt | awk -v OFS="\\t" '{print \$1,\$2,\$3,\$6,\$13}' > ${prefix}_${meta.tool}.bed
awk -v OFS="\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_${meta.tool}.bed > ${prefix}_${meta.tool}_circs.bed
awk -v OFS="\\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_${meta.tool}.bed > ${prefix}_${meta.tool}_circs.bed
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
2 changes: 1 addition & 1 deletion modules/local/circexplorer2/reference/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ process CIRCEXPLORER2_REFERENCE {
$gtf \
${prefix}.genepred
awk -v OFS="\t" '{print \$12, \$1, \$2, \$3, \$4, \$5, \$6, \$7, \$8, \$9, \$10}' ${prefix}.genepred > ${prefix}.txt
awk -v OFS="\\t" '{print \$12, \$1, \$2, \$3, \$4, \$5, \$6, \$7, \$8, \$9, \$10}' ${prefix}.genepred > ${prefix}.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
4 changes: 2 additions & 2 deletions modules/local/circrna_finder/filter/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -29,9 +29,9 @@ process CIRCRNA_FINDER_FILTER {
mkdir -p star_dir && mv *.tab *.junction *.sam star_dir
postProcessStarAlignment.pl --starDir star_dir/ --outDir ./
awk '{if(\$5 >= ${bsj_reads}) print \$0}' ${prefix}.filteredJunctions.bed | awk -v OFS="\t" -F"\t" '{print \$1,\$2,\$3,\$6,\$5}' > ${prefix}_circrna_finder.bed
awk '{if(\$5 >= ${bsj_reads}) print \$0}' ${prefix}.filteredJunctions.bed | awk -v OFS="\\t" -F"\\t" '{print \$1,\$2,\$3,\$6,\$5}' > ${prefix}_circrna_finder.bed
awk -v OFS="\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_circrna_finder.bed > ${prefix}_circrna_finder_circs.bed
awk -v OFS="\\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_circrna_finder.bed > ${prefix}_circrna_finder_circs.bed
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
6 changes: 3 additions & 3 deletions modules/local/ciriquant/filter/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -24,16 +24,16 @@ process CIRIQUANT_FILTER {
def VERSION = '1.3.4'
"""
grep -v "#" ${prefix}.gtf | awk '{print \$14}' | cut -d '.' -f1 > counts
grep -v "#" ${prefix}.gtf | awk -v OFS="\t" '{print \$1,\$4,\$5,\$7}' > ${prefix}.tmp
grep -v "#" ${prefix}.gtf | awk -v OFS="\\t" '{print \$1,\$4,\$5,\$7}' > ${prefix}.tmp
paste ${prefix}.tmp counts > ${prefix}_unfilt.bed
awk '{if(\$5 >= ${bsj_reads}) print \$0}' ${prefix}_unfilt.bed > ${prefix}_filt.bed
grep -v '^\$' ${prefix}_filt.bed > ${prefix}_ciriquant
awk -v OFS="\t" '{\$2-=1;print}' ${prefix}_ciriquant > ${prefix}_ciriquant.bed
awk -v OFS="\\t" '{\$2-=1;print}' ${prefix}_ciriquant > ${prefix}_ciriquant.bed
rm ${prefix}.gtf
awk -v OFS="\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_ciriquant.bed > ${prefix}_ciriquant_circs.bed
awk -v OFS="\\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_ciriquant.bed > ${prefix}_ciriquant_circs.bed
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
8 changes: 3 additions & 5 deletions modules/local/count_matrix/combined/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -20,20 +20,18 @@ process COUNTS_COMBINED {
script:
def args = task.ext.args ?: ''
"""
python ${workflow.projectDir}/bin/circRNA_counts_matrix.py > matrix.txt
circRNA_counts_matrix.py > matrix.txt
## handle non-canon chromosomes here (https://stackoverflow.com/questions/71479919/joining-columns-based-on-number-of-fields)
n_samps=\$(ls *.bed | wc -l)
canon=\$(awk -v a="\$n_samps" 'BEGIN {print a + 4}')
awk -v n="\$canon" '{ for (i = 2; i <= NF - n + 1; ++i) { \$1 = \$1"-"\$i; \$i=""; } } 1' matrix.txt | awk -v OFS="\t" '\$1=\$1' > circRNA_matrix.txt
Rscript ${workflow.projectDir}/bin/reformat_count_matrix.R
awk -v n="\$canon" '{ for (i = 2; i <= NF - n + 1; ++i) { \$1 = \$1"-"\$i; \$i=""; } } 1' matrix.txt | awk -v OFS="\\t" '\$1=\$1' > circRNA_matrix.txt
reformat_count_matrix.R
cat <<-END_VERSIONS > versions.yml
"${task.process}":
awk: \$(awk --version | head -n 1 | cut -d' ' -f3 | sed 's/,//g')
r-base: \$(echo \$(R --version 2>&1) | sed 's/^.*R version //; s/ .*\$//')
argparser: \$(Rscript -e "library(arparser); cat(as.character(packageVersion('argparser')))")
dplyr: \$(Rscript -e "library(dplyr); cat(as.character(packageVersion('dplyr')))")
python: \$(python --version | sed -e 's/Python //g')
END_VERSIONS
"""
}
2 changes: 1 addition & 1 deletion modules/local/count_matrix/merge_tools/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ process MERGE_TOOLS {
## Use intersection of "n" (params.tool_filter) circRNAs called by tools
## remove duplicate IDs, keep highest count.
Rscript ${workflow.projectDir}/bin/consolidate_algorithms_intersection.R samples.csv $tool_filter $duplicates_fun
consolidate_algorithms_intersection.R samples.csv $tool_filter $duplicates_fun
mv combined_counts.bed ${prefix}.bed
cat <<-END_VERSIONS > versions.yml
Expand Down
2 changes: 1 addition & 1 deletion modules/local/count_matrix/single/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ process COUNTS_SINGLE {
## handle non-canon chromosomes here (https://stackoverflow.com/questions/71479919/joining-columns-based-on-number-of-fields)
n_samps=\$(ls *.bed | wc -l)
canon=\$(awk -v a="\$n_samps" 'BEGIN {print a + 4}')
awk -v n="\$canon" '{ for (i = 2; i <= NF - n + 1; ++i) { \$1 = \$1"-"\$i; \$i=""; } } 1' matrix.txt | awk -v OFS="\t" '\$1=\$1' > circRNA_matrix.txt
awk -v n="\$canon" '{ for (i = 2; i <= NF - n + 1; ++i) { \$1 = \$1"-"\$i; \$i=""; } } 1' matrix.txt | awk -v OFS="\\t" '\$1=\$1' > circRNA_matrix.txt
Rscript ${workflow.projectDir}/bin/reformat_count_matrix.R
cat <<-END_VERSIONS > versions.yml
Expand Down
4 changes: 2 additions & 2 deletions modules/local/dcc/dcc/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ process DCC {
DCC @samplesheet -D -an $gtf -Pi -ss -F -M -Nr 1 1 -fg -A $fasta -N -T ${task.cpus}
awk '{print \$6}' CircCoordinates >> strand
paste CircRNACount strand | tail -n +2 | awk -v OFS="\t" '{print \$1,\$2,\$3,\$5,\$4}' >> ${prefix}.txt
paste CircRNACount strand | tail -n +2 | awk -v OFS="\\t" '{print \$1,\$2,\$3,\$5,\$4}' >> ${prefix}.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand All @@ -49,7 +49,7 @@ process DCC {
DCC @samplesheet -mt1 @mate1file -mt2 @mate2file -D -an $gtf -Pi -ss -F -M -Nr 1 1 -fg -A $fasta -N -T ${task.cpus}
awk '{print \$6}' CircCoordinates >> strand
paste CircRNACount strand | tail -n +2 | awk -v OFS="\t" '{print \$1,\$2,\$3,\$5,\$4}' >> ${prefix}.txt
paste CircRNACount strand | tail -n +2 | awk -v OFS="\\t" '{print \$1,\$2,\$3,\$5,\$4}' >> ${prefix}.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
4 changes: 2 additions & 2 deletions modules/local/dcc/filter/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,8 @@ process DCC_FILTER {
def VERSION = '1.3.4'
"""
awk '{if(\$5 >= ${bsj_reads}) print \$0}' ${prefix}.txt > ${prefix}_dcc.filtered
awk -v OFS="\t" '{\$2-=1;print}' ${prefix}_dcc.filtered > ${prefix}_dcc.bed
awk -v OFS="\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_dcc.bed > ${prefix}_dcc_circs.bed
awk -v OFS="\\t" '{\$2-=1;print}' ${prefix}_dcc.filtered > ${prefix}_dcc.bed
awk -v OFS="\\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_dcc.bed > ${prefix}_dcc_circs.bed
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
7 changes: 3 additions & 4 deletions modules/local/fasta/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ process FASTA {

input:
tuple val(meta), path(bed)
path fasta
path(fasta, stageAs: 'fasta.input') // TODO: Remove input renaming, currently necessary to prevent problems with the backsplice_gen.sh script

output:
tuple val(meta), path("${prefix}.fa"), emit: analysis_fasta
Expand All @@ -24,15 +24,14 @@ process FASTA {
prefix = task.ext.prefix ?: "${meta.id}"
"""
## FASTA sequences (bedtools does not like the extra annotation info - split will not work properly)
cut -d\$'\t' -f1-12 ${prefix}.bed > bed12.tmp
cut -d\$'\\t' -f1-12 $bed > bed12.tmp
bedtools getfasta -fi $fasta -bed bed12.tmp -s -split -name > circ_seq.tmp
## clean fasta header
grep -A 1 '>' circ_seq.tmp | cut -d: -f1,2,3 > ${prefix}.fa && rm circ_seq.tmp
## add backsplice sequence for miRanda Targetscan, publish canonical FASTA to results.
rm $fasta
bash ${workflow.projectDir}/bin/backsplice_gen.sh ${prefix}.fa
backsplice_gen.sh ${prefix}.fa
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
4 changes: 2 additions & 2 deletions modules/local/find_circ/filter/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -30,9 +30,9 @@ process FIND_CIRC_FILTER {
maxlength.py 100000 \
> ${prefix}.txt
tail -n +2 ${prefix}.txt | awk -v OFS="\t" '{print \$1,\$2,\$3,\$6,\$5}' > ${prefix}_find_circ.bed
tail -n +2 ${prefix}.txt | awk -v OFS="\\t" '{print \$1,\$2,\$3,\$6,\$5}' > ${prefix}_find_circ.bed
awk -v OFS="\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_find_circ.bed > ${prefix}_find_circ_circs.bed
awk -v OFS="\\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_find_circ.bed > ${prefix}_find_circ_circs.bed
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
8 changes: 4 additions & 4 deletions modules/local/mirna_targets/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,8 @@ process MIRNA_TARGETS {
prefix = task.ext.prefix ?: "${meta.id}"
"""
## reformat and sort miRanda, TargetScan outputs, convert to BED for overlaps.
tail -n +2 $targetscan | sort -k1,1 -k4n | awk -v OFS="\t" '{print \$1, \$2, \$4, \$5, \$9}' | awk -v OFS="\t" '{print \$2, \$3, \$4, \$1, "0", \$5}' > targetscan.bed
tail -n +2 $miranda | sort -k2,2 -k7n | awk -v OFS="\t" '{print \$2, \$1, \$3, \$4, \$7, \$8}' | awk -v OFS="\t" '{print \$2, \$5, \$6, \$1, \$3, \$4}' | sed 's/^[^-]*-//g' > miranda.bed
tail -n +2 $targetscan | sort -k1,1 -k4n | awk -v OFS="\\t" '{print \$1, \$2, \$4, \$5, \$9}' | awk -v OFS="\t" '{print \$2, \$3, \$4, \$1, "0", \$5}' > targetscan.bed
tail -n +2 $miranda | sort -k2,2 -k7n | awk -v OFS="\\t" '{print \$2, \$1, \$3, \$4, \$7, \$8}' | awk -v OFS="\t" '{print \$2, \$5, \$6, \$1, \$3, \$4}' | sed 's/^[^-]*-//g' > miranda.bed
## intersect, consolidate miRanda, TargetScan information about miRs.
## -wa to output miRanda hits - targetscan makes it difficult to resolve duplicate miRNAs at MRE sites.
Expand All @@ -32,8 +32,8 @@ process MIRNA_TARGETS {
## remove duplicate miRNA entries at MRE sites.
## strategy: sory by circs, sort by start position, sort by site type - the goal is to take the best site type (i.e rank site type found at MRE site).
paste ${prefix}.mirnas.tmp mirna_type | sort -k3,3 -k2n -k7r | awk -v OFS="\t" '{print \$4,\$1,\$2,\$3,\$5,\$6,\$7}' | awk -F "\t" '{if (!seen[\$1,\$2,\$3,\$4,\$5,\$6]++)print}' | sort -k1,1 -k3n > ${prefix}.mirna_targets.tmp
echo -e "circRNA\tmiRNA\tStart\tEnd\tScore\tEnergy_KcalMol\tSite_type" | cat - ${prefix}.mirna_targets.tmp > ${prefix}.mirna_targets.txt
paste ${prefix}.mirnas.tmp mirna_type | sort -k3,3 -k2n -k7r | awk -v OFS="\\t" '{print \$4,\$1,\$2,\$3,\$5,\$6,\$7}' | awk -F "\\t" '{if (!seen[\$1,\$2,\$3,\$4,\$5,\$6]++)print}' | sort -k1,1 -k3n > ${prefix}.mirna_targets.tmp
echo -e "circRNA\\tmiRNA\\tStart\\tEnd\\tScore\\tEnergy_KcalMol\\tSite_type" | cat - ${prefix}.mirna_targets.tmp > ${prefix}.mirna_targets.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
6 changes: 3 additions & 3 deletions modules/local/segemehl/filter/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,11 @@ process SEGEMEHL_FILTER {
prefix = task.ext.prefix ?: "${meta.id}"
def VERSION = '1.3.4'
"""
grep ';C;' ${prefix}.sngl.bed | awk -v OFS="\t" '{print \$1,\$2,\$3,\$6}' | sort | uniq -c | awk -v OFS="\t" '{print \$2,\$3,\$4,\$5,\$1}' > ${prefix}_collapsed.bed
grep ';C;' ${prefix}.sngl.bed | awk -v OFS="\\t" '{print \$1,\$2,\$3,\$6}' | sort | uniq -c | awk -v OFS="\\t" '{print \$2,\$3,\$4,\$5,\$1}' > ${prefix}_collapsed.bed
awk -v OFS="\t" -v BSJ=${bsj_reads} '{if(\$5>=BSJ) print \$0}' ${prefix}_collapsed.bed > ${prefix}_segemehl.bed
awk -v OFS="\\t" -v BSJ=${bsj_reads} '{if(\$5>=BSJ) print \$0}' ${prefix}_collapsed.bed > ${prefix}_segemehl.bed
awk -v OFS="\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_segemehl.bed > ${prefix}_segemehl_circs.bed
awk -v OFS="\\t" '{print \$1, \$2, \$3, \$1":"\$2"-"\$3":"\$4, \$5, \$4}' ${prefix}_segemehl.bed > ${prefix}_segemehl_circs.bed
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
2 changes: 1 addition & 1 deletion modules/local/stringtie/prepde/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ process STRINGTIE_PREPDE {

script:
"""
for file in \$(ls *.gtf); do sample_id=\${file%".transcripts.gtf"}; touch samples.txt; printf "\$sample_id\t\$file\\n" >> samples.txt ; done
for file in \$(ls *.gtf); do sample_id=\${file%".transcripts.gtf"}; touch samples.txt; printf "\$sample_id\\t\$file\\n" >> samples.txt ; done
prepDE.py -i samples.txt
Expand Down
2 changes: 1 addition & 1 deletion modules/local/targetscan/predict/main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ process TARGETSCAN {
##format for targetscan
cat $fasta | grep ">" | sed 's/>//g' > id
cat $fasta | grep -v ">" > seq
paste id seq | awk -v OFS="\t" '{print \$1, "0000", \$2}' > ${prefix}_ts.txt
paste id seq | awk -v OFS="\\t" '{print \$1, "0000", \$2}' > ${prefix}_ts.txt
# run targetscan
targetscan_70.pl mature.txt ${prefix}_ts.txt ${prefix}.txt
Expand Down
5 changes: 3 additions & 2 deletions nextflow.config
Original file line number Diff line number Diff line change
Expand Up @@ -94,10 +94,12 @@ params {
max_cpus = 50
max_time = '240.h'

test_data_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/circrna'

// Schema validation default options
validationFailUnrecognisedParams = false
validationLenientMode = false
validationSchemaIgnoreParams = 'genomes,igenomes_base'
validationSchemaIgnoreParams = 'genomes,igenomes_base,test_data_base'
validationShowHiddenParams = false
validate_params = true
}
Expand Down Expand Up @@ -211,7 +213,6 @@ profiles {
executor.memory = 8.GB
}
test { includeConfig 'conf/test.config' }
test_cache { includeConfig 'conf/test_cache.config' }
test_igenomes { includeConfig 'conf/test_igenomes.config' }
full { includeConfig 'conf/full.config' }
test_full { includeConfig 'conf/test_full.config' }
Expand Down

0 comments on commit 9999e23

Please sign in to comment.