GloSED database incorporation #1022
There are no files selected for viewing
This file contains hidden or 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 hidden or 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 hidden or 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 +1,94 @@ | ||
| #!/bin/sh | ||
|
|
||
| # Reformat GloSED references for assignTaxonomy and addSpecies. | ||
| # Inputs (in current directory by default): | ||
| # - GloSED__OTU_sequences.fasta.gz | ||
| # - GloSED__Taxonomy.tsv.zip | ||
| # Outputs: | ||
| # - assignTaxonomy.fna | ||
| # - addSpecies.fna | ||
|
|
||
| set -eu | ||
|
|
||
| stream_seq() { | ||
| case "$1" in | ||
| *.zip) unzip -p "$1" ;; | ||
| *) gzip -dc "$1" ;; | ||
| esac | ||
| } | ||
|
|
||
| SEQ_GZ="${1:-GloSED__OTU_sequences.fasta.gz}" | ||
| TAX_ZIP="${2:-GloSED__Taxonomy.tsv.zip}" | ||
|
|
||
| if [ -z "${1:-}" ] && [ -z "${2:-}" ] && [ ! -f "$SEQ_GZ" ] && [ ! -f "$TAX_ZIP" ] && [ -f "GloSED__OTU_sequences_first1k.fasta.zip" ] && [ -f "GloSED_Taxonomy_first1k.tsv.zip" ]; then | ||
| SEQ_GZ="GloSED__OTU_sequences_first1k.fasta.zip" | ||
| TAX_ZIP="GloSED_Taxonomy_first1k.tsv.zip" | ||
| fi | ||
|
|
||
| [ -f "$SEQ_GZ" ] || { echo "ERROR: missing $SEQ_GZ" >&2; exit 1; } | ||
| [ -f "$TAX_ZIP" ] || { echo "ERROR: missing $TAX_ZIP" >&2; exit 1; } | ||
|
|
||
| TMPDIR_LOCAL="$(mktemp -d glosed_reformat.XXXXXX)" | ||
| trap 'rm -rf "$TMPDIR_LOCAL"' EXIT INT TERM | ||
|
|
||
| TAX_TSV="${TMPDIR_LOCAL}/glosed_taxonomy.tsv" | ||
| META_TSV="${TMPDIR_LOCAL}/glosed_meta.tsv" | ||
|
|
||
| unzip -p "$TAX_ZIP" > "$TAX_TSV" | ||
|
|
||
| awk -F '\t' 'BEGIN { OFS="\t" } | ||
| NR==1 { | ||
| for (i = 1; i <= NF; i++) { | ||
| if ($i == "OTU") otu = i | ||
| else if ($i == "Kingdom") kingdom = i | ||
| else if ($i == "Phylum") phylum = i | ||
| else if ($i == "Class") classcol = i | ||
| else if ($i == "Order") ordercol = i | ||
| else if ($i == "Family") family = i | ||
| else if ($i == "Genus") genus = i | ||
| else if ($i == "Species") species = i | ||
| } | ||
| next | ||
| } | ||
| { | ||
| id = $otu | ||
| k = $kingdom; p = $phylum; c = $classcol; o = $ordercol; f = $family; g = $genus; s = $species | ||
| gsub(/ /, "_", k); gsub(/ /, "_", p); gsub(/ /, "_", c); gsub(/ /, "_", o); gsub(/ /, "_", f); gsub(/ /, "_", g); gsub(/ /, "_", s) | ||
|
|
||
| tax = "" | ||
| if (k != "." && k != "") { | ||
| tax = k ";" | ||
| if (p != "." && p != "") { | ||
| tax = tax p ";" | ||
| if (c != "." && c != "") { | ||
| tax = tax c ";" | ||
| if (o != "." && o != "") { | ||
| tax = tax o ";" | ||
| if (f != "." && f != "") { | ||
| tax = tax f ";" | ||
| if (g != "." && g != "") { | ||
| tax = tax g ";" | ||
| if (s != "." && s != "") { | ||
| tax = tax s ";" | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| print id, tax, g, s | ||
| } | ||
| ' "$TAX_TSV" > "$META_TSV" | ||
|
|
||
| stream_seq "$SEQ_GZ" | awk -F '\t' 'NR==FNR { tax[$1] = $2; next } | ||
| /^>/ { id = substr($0,2); if (id in tax && tax[id] != "") print ">" tax[id]; else print ">" id; next } | ||
| { print } | ||
| ' "$META_TSV" - > assignTaxonomy.fna | ||
|
|
||
| stream_seq "$SEQ_GZ" | awk -F '\t' 'NR==FNR { if ($3 != "." && $3 != "" && $3 != "NA" && $4 != "." && $4 != "" && $4 != "NA") addsp[$1] = $3 " " $4; next } | ||
| /^>/ { id = substr($0,2); keep = (id in addsp); if (keep) print ">" id " " addsp[id]; next } | ||
| { if (keep) print } | ||
| ' "$META_TSV" - > addSpecies.fna | ||
|
|
||
| echo "Created files: assignTaxonomy.fna addSpecies.fna" |
This file contains hidden or 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 hidden or 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 +1,34 @@ | ||
| /* | ||
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | ||
| nf-core/ampliseq Nextflow config file for the GloSED test profile | ||
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | ||
| Purpose: run the pipeline against a small GloSED reference subset hosted in | ||
| nf-core/test-datasets instead of the full Zenodo reference database. | ||
|
|
||
| Use as follows: | ||
| nextflow run nf-core/ampliseq -profile test_glosed,<docker/singularity> --outdir <OUTDIR> | ||
| ---------------------------------------------------------------------------------------- | ||
| */ | ||
|
|
||
|
d4straub marked this conversation as resolved.
|
||
| params { | ||
| config_profile_name = 'Test profile for GloSED database' | ||
| config_profile_description = 'Minimal test dataset to verify pipeline function with GloSED reference database' | ||
|
|
||
| FW_primer = "GTGYCAGCMGCCGCGGTAA" | ||
| RV_primer = "GGACTACNVGGGTWTCTAAT" | ||
| input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv" | ||
| dada_ref_taxonomy = "glosed" | ||
| skip_qiime = true | ||
|
|
||
| // IMPORTANT: override the actual database map used by the workflow | ||
| dada_ref_databases.glosed = [ | ||
| title:"GloSED - Global standardised Soil Eukaryome Dataset", | ||
| file:[ | ||
| "https://raw.githubusercontent.com/nf-core/test-datasets/ampliseq/testdata/GloSED__OTU_sequences_first1k.fasta.zip", | ||
| "https://raw.githubusercontent.com/nf-core/test-datasets/amplsieq/testdata/GloSED_Taxonomy_first1k.tsv.zip" | ||
|
Collaborator
There was a problem hiding this comment. Thats ok i think. An alternative could be to add an entry such as "glosed_1k" or such. Similar to ampliseq/conf/ref_databases.config Lines 881 to 889 in 2723d4c
d4straub marked this conversation as resolved.
Outdated
|
||
| ], | ||
| citation:"Sundh J, Larsson E, Nilsson RH, et al. GloSED fungal ITS database. Zenodo. https://zenodo.org/records/17827890", | ||
| fmtscript:"taxref_reformat_glosed.sh", | ||
| dbversion:"GloSED test subset (first1k)" | ||
| ] | ||
| } | ||
This file contains hidden or 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 hidden or 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 hidden or 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 hidden or 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 hidden or 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 +1,47 @@ | ||
| nextflow_pipeline { | ||
|
|
||
| name "Test pipeline with GloSED" | ||
| script "../main.nf" | ||
| tag "pipeline" | ||
| profile "test_glosed" | ||
|
|
||
| test("-profile test_glosed") { | ||
|
|
||
| when { | ||
| params { | ||
| outdir = "$outputDir" | ||
| } | ||
| } | ||
|
|
||
| then { | ||
| // stable_name: All files + folders in ${params.outdir}/ with a stable name | ||
| def stable_name = getAllFilesFromDir(params.outdir, relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}']) | ||
|
|
||
| assert workflow.success | ||
| assertAll( | ||
| { assert snapshot( | ||
| // pipeline versions.yml file for multiqc from which Nextflow version is removed because we test pipelines on multiple Nextflow versions | ||
| removeNextflowVersion("$outputDir/pipeline_info/software_versions.yml"), | ||
| // All stable path name, with a relative path | ||
| stable_name, | ||
| // Manually chosen files for content checks | ||
| path("$outputDir/overall_summary.tsv"), | ||
| path("$outputDir/barrnap/rrna.arc.gff"), | ||
| path("$outputDir/barrnap/rrna.bac.gff"), | ||
| path("$outputDir/barrnap/rrna.euk.gff"), | ||
| path("$outputDir/barrnap/rrna.mito.gff"), | ||
| path("$outputDir/cutadapt/cutadapt_summary.tsv"), | ||
| path("$outputDir/dada2/ASV_seqs.fasta"), | ||
| path("$outputDir/dada2/ASV_table.tsv"), | ||
| path("$outputDir/dada2/ref_taxonomy.glosed.txt"), | ||
| path("$outputDir/dada2/DADA2_stats.tsv"), | ||
| path("$outputDir/dada2/DADA2_table.tsv"), | ||
| path("$outputDir/input/Samplesheet.tsv"), | ||
| path("$outputDir/multiqc/multiqc_data/multiqc_fastqc.txt"), | ||
| path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"), | ||
| path("$outputDir/multiqc/multiqc_data/multiqc_cutadapt.txt") | ||
| ).match() } | ||
| ) | ||
| } | ||
| } | ||
| } |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.