-
Notifications
You must be signed in to change notification settings - Fork 127
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'dev' into samtools_index_c
- Loading branch information
Showing
7 changed files
with
290 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,41 @@ | ||
| /* | ||
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | ||
| Nextflow config file for running minimal tests | ||
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | ||
| Defines input files and everything required to run a fast and simple pipeline test. | ||
| Use as follows: | ||
| nextflow run nf-core/smrnaseq -profile test_contamination,<docker/singularity> --outdir <OUTDIR> | ||
| ---------------------------------------------------------------------------------------- | ||
| */ | ||
|
|
||
| params { | ||
| config_profile_name = 'Test profile' | ||
| config_profile_description = 'Minimal test dataset to check pipeline function with contamination filter' | ||
|
|
||
| // Limit resources so that this can run on GitHub Actions | ||
| max_cpus = 2 | ||
| max_memory = '6.GB' | ||
| max_time = '6.h' | ||
|
|
||
| // Input data | ||
|
|
||
| input = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/samplesheet/v2.0/samplesheet.csv' | ||
| fasta = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/genome.fa' | ||
|
|
||
| mirtrace_species = 'hsa' | ||
| skip_mirdeep = true | ||
| save_merged = false | ||
| save_aligned_mirna_quant = false | ||
|
|
||
|
|
||
| filter_contamination = true | ||
| cdna = "https://huggingface.co/datasets/nf-core/smrnaseq/resolve/main/GRCh37/Homo_sapiens.GRCh37.cdna.all.fa" | ||
| ncrna = "https://huggingface.co/datasets/nf-core/smrnaseq/resolve/main/GRCh37/Homo_sapiens.GRCh37.ncrna.fa" | ||
| trna = "https://huggingface.co/datasets/nf-core/smrnaseq/resolve/main/GRCh37/hg19-tRNAs.fa" | ||
| } | ||
|
|
||
| // Include illumina config to run test without additional profiles | ||
|
|
||
| includeConfig 'protocol_illumina.config' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| process BLAT_MIRNA { | ||
| tag "$fasta" | ||
| label 'process_medium' | ||
|
|
||
| conda 'bioconda::blat=36' | ||
| container 'community.wave.seqera.io/library/ucsc-blat:445--32730933d3c2c916' | ||
|
|
||
| input: | ||
| val db_type | ||
| path mirna | ||
| path contaminants | ||
|
|
||
|
|
||
| output: | ||
| path 'filtered.fa' , emit: filtered_set | ||
| path "versions.yml" , emit: versions | ||
|
|
||
| when: | ||
| task.ext.when == null || task.ext.when | ||
|
|
||
| script: | ||
| if ( db_type == "cdna" ) | ||
| """ | ||
| echo $db_type | ||
| awk '/^>/ { x=index(\$6, "transcript_biotype:miRNA") } { if(!x) print }' $contaminants > subset.fa | ||
| blat -out=blast8 $mirna subset.fa /dev/stdout | awk 'BEGIN{FS="\t"}{if(\$11 < 1e-5)print \$1;}' | uniq > mirnahit.txt | ||
| awk 'BEGIN { while((getline<"mirnahit.txt")>0) l[">"\$1]=1 } /^>/ {x = l[\$1]} {if(!x) print }' subset.fa > filtered.fa | ||
| cat <<-END_VERSIONS > versions.yml | ||
| "${task.process}": | ||
| blat: \$(echo \$(blat) | grep Standalone | awk '{ if (match(\$0,/[0-9]*[0-9]/,m)) print m[0] }') | ||
| END_VERSIONS | ||
| """ | ||
|
|
||
| else if ( db_type == "ncrna" ) | ||
| """ | ||
| echo $db_type | ||
| awk '/^>/ { x=(index(\$6, "transcript_biotype:rRNA") || index(\$6, "transcript_biotype:miRNA")) } { if(!x) print }' $contaminants > subset.fa | ||
| blat -out=blast8 $mirna subset.fa /dev/stdout | awk 'BEGIN{FS="\t"}{if(\$11 < 1e-5)print \$1;}' | uniq > mirnahit.txt | ||
| awk 'BEGIN { while((getline<"mirnahit.txt")>0) l[">"\$1]=1 } /^>/ {x = l[\$1]} {if(!x) print }' subset.fa > filtered.fa | ||
| cat <<-END_VERSIONS > versions.yml | ||
| "${task.process}": | ||
| blat: \$(echo \$(blat) | grep Standalone | awk '{ if (match(\$0,/[0-9]*[0-9]/,m)) print m[0] }') | ||
| END_VERSIONS | ||
| """ | ||
|
|
||
| else | ||
| """ | ||
| echo $db_type | ||
| blat -out=blast8 $mirna $contaminants /dev/stdout | awk 'BEGIN{FS="\t"}{if(\$11 < 1e-5)print \$1;}' | uniq > mirnahit.txt | ||
| awk 'BEGIN { while((getline<"mirnahit.txt")>0) l[">"\$1]=1 } /^>/ {x = l[\$1]} {if(!x) print }' $contaminants > filtered.fa | ||
| cat <<-END_VERSIONS > versions.yml | ||
| "${task.process}": | ||
| blat: \$(echo \$(blat) | grep Standalone | awk '{ if (match(\$0,/[0-9]*[0-9]/,m)) print m[0] }') | ||
| END_VERSIONS | ||
| """ | ||
|
|
||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| nextflow_process { | ||
|
|
||
| name "Test Process BLAT_MIRNA" | ||
| script "../blat_mirna.nf" | ||
| process "BLAT_MIRNA" | ||
| tag "modules" | ||
| tag "modules_local" | ||
| tag "blat_mirna" | ||
|
|
||
| test("cDNA BLAT - Human") { | ||
|
|
||
| when { | ||
| params { | ||
| outdir = "${outputDir}" | ||
| } | ||
| process { | ||
| """ | ||
| input[0] = "cdna" | ||
| input[1] = [file("https://github.com/nf-core/test-datasets/raw/smrnaseq/miRBase/hairpin.fa", checkIfExists: true)] | ||
| input[2] = [file("https://huggingface.co/datasets/nf-core/smrnaseq/resolve/main/GRCh37/Homo_sapiens.GRCh37.cdna.all.fa", checkIfExists: true)] | ||
| """ | ||
| } | ||
| } | ||
|
|
||
| then { | ||
| assert process.success | ||
| assert snapshot(process.out).match() | ||
|
|
||
| with(process.out.filtered_set) { | ||
| with(get(0)) { | ||
| assert get(0).endsWith("filtered.fa") | ||
|
|
||
| // Check for AWK filtering of specific biotype | ||
| def lines = path(get(0)).readLines() | ||
| assert !lines.any { it.contains("transcript_biotype:miRNA") } | ||
|
|
||
| // Check for exclusion of miRNAs hits | ||
| assert !lines.any { it.contains("ENST00000564740.1") } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| } | ||
|
|
||
| test("ncRNA BLAT - Human") { | ||
|
|
||
| when { | ||
| params { | ||
| outdir = "${outputDir}" | ||
| } | ||
| process { | ||
| """ | ||
| input[0] = "ncRNA" | ||
| input[1] = [file("https://github.com/nf-core/test-datasets/raw/smrnaseq/miRBase/hairpin.fa", checkIfExists: true)] | ||
| input[2] = [file("https://huggingface.co/datasets/nf-core/smrnaseq/resolve/main/GRCh37/Homo_sapiens.GRCh37.ncrna.fa", checkIfExists: true)] | ||
| """ | ||
| } | ||
| } | ||
|
|
||
| then { | ||
| assert process.success | ||
| assert snapshot(process.out).match() | ||
|
|
||
| with(process.out.filtered_set) { | ||
| with(get(0)) { | ||
| assert get(0).endsWith("filtered.fa") | ||
|
|
||
| // Check for AWK filtering of specific biotype | ||
| def lines = path(get(0)).readLines() | ||
| // Lines contain transcript_biotype:rRNA or miRNA, so AWK assertions do not work: | ||
| //assert !lines.any { it.contains("transcript_biotype:rRNA") } | ||
| //assert !lines.any { it.contains("transcript_biotype:miRNA") } | ||
|
|
||
| // Check for exclusion of miRNAs hits | ||
| assert !lines.any { it.contains("ENST00000564740.1") } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| } | ||
|
|
||
| test("tRNA BLAT - Human") { | ||
|
|
||
| when { | ||
| params { | ||
| outdir = "${outputDir}" | ||
| } | ||
| process { | ||
| """ | ||
| input[0] = "tRNA" | ||
| input[1] = [file("https://github.com/nf-core/test-datasets/raw/smrnaseq/miRBase/hairpin.fa", checkIfExists: true)] | ||
| input[2] = [file("https://huggingface.co/datasets/nf-core/smrnaseq/resolve/main/GRCh37/hg19-tRNAs.fa", checkIfExists: true)] | ||
| """ | ||
| } | ||
| } | ||
|
|
||
| then { | ||
| assert process.success | ||
| assert snapshot(process.out).match() | ||
|
|
||
| with(process.out.filtered_set) { | ||
| with(get(0)) { | ||
| assert get(0).endsWith("filtered.fa") | ||
|
|
||
| // Check for exclusion of miRNAs hits | ||
| def lines = path(get(0)).readLines() | ||
| assert !lines.any { it.contains("ENST00000564740.1") } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| } | ||
|
|
||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,71 @@ | ||
| { | ||
| "ncRNA BLAT - Human": { | ||
| "content": [ | ||
| { | ||
| "0": [ | ||
| "filtered.fa:md5,6bc8a430400e2e78cf7f474981230811" | ||
| ], | ||
| "1": [ | ||
| "versions.yml:md5,e2957df2cc8f0410101564c8e65d1761" | ||
| ], | ||
| "filtered_set": [ | ||
| "filtered.fa:md5,6bc8a430400e2e78cf7f474981230811" | ||
| ], | ||
| "versions": [ | ||
| "versions.yml:md5,e2957df2cc8f0410101564c8e65d1761" | ||
| ] | ||
| } | ||
| ], | ||
| "meta": { | ||
| "nf-test": "0.8.4", | ||
| "nextflow": "24.04.4" | ||
| }, | ||
| "timestamp": "2024-08-23T17:53:35.313580289" | ||
| }, | ||
| "tRNA BLAT - Human": { | ||
| "content": [ | ||
| { | ||
| "0": [ | ||
| "filtered.fa:md5,6b54e95ca5418d7d9c4d331ca3b2c96f" | ||
| ], | ||
| "1": [ | ||
| "versions.yml:md5,e2957df2cc8f0410101564c8e65d1761" | ||
| ], | ||
| "filtered_set": [ | ||
| "filtered.fa:md5,6b54e95ca5418d7d9c4d331ca3b2c96f" | ||
| ], | ||
| "versions": [ | ||
| "versions.yml:md5,e2957df2cc8f0410101564c8e65d1761" | ||
| ] | ||
| } | ||
| ], | ||
| "meta": { | ||
| "nf-test": "0.8.4", | ||
| "nextflow": "24.04.4" | ||
| }, | ||
| "timestamp": "2024-08-23T17:57:58.238216453" | ||
| }, | ||
| "cDNA BLAT - Human": { | ||
| "content": [ | ||
| { | ||
| "0": [ | ||
| "filtered.fa:md5,8fd42894e815999b4278b08297720aae" | ||
| ], | ||
| "1": [ | ||
| "versions.yml:md5,e2957df2cc8f0410101564c8e65d1761" | ||
| ], | ||
| "filtered_set": [ | ||
| "filtered.fa:md5,8fd42894e815999b4278b08297720aae" | ||
| ], | ||
| "versions": [ | ||
| "versions.yml:md5,e2957df2cc8f0410101564c8e65d1761" | ||
| ] | ||
| } | ||
| ], | ||
| "meta": { | ||
| "nf-test": "0.8.4", | ||
| "nextflow": "24.04.4" | ||
| }, | ||
| "timestamp": "2024-08-23T17:53:16.735132971" | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters