Mercurial > repos > galaxytrakr > mitokmer
view mitokmer.xml @ 0:adc887a1a6de draft
planemo upload commit 927c4ee71df7d19ceb10446a04618af22c99d839
| author | galaxytrakr |
|---|---|
| date | Fri, 11 Sep 2026 21:58:43 +0000 |
| parents | |
| children | e6b5e7a0d7e7 |
line wrap: on
line source
<tool id="mitokmer" name="mitoKmer" version="2.0+galaxy0.1" python_template_version="3.5" profile="21.05"> <description>Identify metagenomic mitochondrial reads by k-mer database matching</description> <requirements> <container type="docker">quay.io/galaxytrakr/mitokmer2:latest</container> </requirements> <command detect_errors="exit_code"><![CDATA[ ## ── kmerread expects files at specific relative paths ───────────────── ## ./mitoch/mitoch_probes.txt.gz - probe database ## ./jobs1/jobs1.txt - jobs file listing sample reads ## It is invoked with no arguments: ./kmerread mkdir -p ./mitoch ./jobs1 ./reads && ## ── Link probe database to the path kmerread expects ───────────────── ln -sf '${probe_db.fields.path}' ./mitoch/mitoch_probes.txt.gz && ## ── Stage input reads ───────────────────────────────────────────────── #for read in $reads ln -sf '${read}' ./reads/${read.element_identifier.replace(' ', '_')} && #end for ## ── Write the jobs file in the format kmerread expects ─────────────── ## Line 1: <sample_name> <number_of_files> ## Lines 2+: absolute path to each read file, one per line #set sample_name = $reads[0].element_identifier.replace(' ', '_').split('_')[:-1] | join('_') echo "${sample_name} ${reads|length}" > ./jobs1/jobs1.txt && #for read in $reads echo "\$PWD/reads/${read.element_identifier.replace(' ', '_')}" >> ./jobs1/jobs1.txt && #end for ## ── Run kmerread (reads jobs1/jobs1.txt and mitoch/mitoch_probes.txt.gz ## by convention; no CLI arguments) ────────────────────────────────── kmerread && ## ── Summarise results into CSV ──────────────────────────────────────── python3 /opt/mitokmer2/kmer_read_m7.py -i ./jobs1 -o '${results_csv}' ]]></command> <inputs> <!-- Probe database selected from Galaxy data table --> <param name="probe_db" type="select" label="Mitochondrial k-mer probe database" help="Select a pre-installed mitochondrial k-mer probe database. Databases are managed by your Galaxy administrator via the mitokmer_probe_db data table."> <options from_data_table="mitokmer_probe_db"> <filter type="sort_by" column="1" /> <validator type="no_options" message="No mitochondrial k-mer probe databases are currently installed. Please contact your Galaxy administrator." /> </options> </param> <!-- One or more FASTQ/FASTA files for a single sample --> <param name="reads" type="data_collection" collection_type="list" format="fastq,fastq.gz,fasta,fasta.gz" label="Input reads (FASTQ or FASTA, gzipped or plain)" help="Provide one or more read files for a single sample as a Galaxy list collection. Paired-end files (R1 + R2) should both be included in the same collection. Light quality trimming of read ends is performed internally; pre-trimming is optional." /> </inputs> <outputs> <data name="results_csv" format="csv" label="mitoKmer results for ${on_string}" /> </outputs> <tests> <test> <param name="probe_db" value="mitoch_probes_sample" /> <param name="reads"> <collection type="list"> <element name="Plodia_R1" value="test/Plodia_R1.fastq.gz" /> <element name="Plodia_R2" value="test/Plodia_R2.fastq.gz" /> </collection> </param> <output name="results_csv"> <assert_contents> <has_text text="Plodia" /> </assert_contents> </output> </test> </tests> <help><![CDATA[ **mitoKmer** — Metagenomic Mitochondrial Read Identification by K-mer Database =============================================================================== Overview -------- mitoKmer identifies the taxonomic origin of short-read shotgun sequencing data by matching reads against a database of species-specific mitochondrial k-mer probes. It reports the relative abundance of taxa at multiple taxonomic ranks (e.g. order, species) along with the number of matching reads and supporting unique k-mers. Inputs ------ **Mitochondrial k-mer probe database** Select a pre-installed probe database from the dropdown. Databases are managed by your Galaxy administrator and registered in the ``mitokmer_probe_db`` data table. **Input reads** One or more FASTQ or FASTA files (gzipped or plain) for a single sample, supplied as a Galaxy list collection. Both paired-end files (R1 and R2) should be included in the same collection. * Pre-trimming is optional — the tool performs simple window-based quality trimming of read ends internally. Output ------ **Results CSV** A comma-separated file summarising the relative abundance of each taxon detected in the sample. Columns include taxon name, taxonomic rank, number of reads assigned, relative abundance (%), and the number of unique k-mers supporting the assignment. Example output for the "Plodia" test sample:: Rank Taxon Reads Rel_Abund(%) Unique_kmers Order Lepidoptera 10 0.1 329 Species Plodia interpunctella 462 99.9 466 Citation -------- Please cite the mitoKmer GitHub repository if you use this tool in published work. ]]></help> <citations> <citation type="bibtex"> @misc{githubmitokmer2, author = {Mammel, Mark}, title = {mitoKmer2}, year = {2024}, publisher = {GitHub}, journal = {GitHub repository}, url = {https://github.com/mmammel8/mitokmer2}, } </citation> </citations> </tool>
