Mercurial > repos > iuc > megahit
changeset 8:e1475fcac99c draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/megahit commit acac4f9e3f82cc7248177b97d1cbabbf58d24cf6
| author | iuc |
|---|---|
| date | Thu, 13 Feb 2025 19:36:06 +0000 |
| parents | d27f770bf397 |
| children | |
| files | megahit_wrapper.xml |
| diffstat | 1 files changed, 40 insertions(+), 24 deletions(-) [+] |
line wrap: on
line diff
--- a/megahit_wrapper.xml Sun Jan 09 16:57:18 2022 +0000 +++ b/megahit_wrapper.xml Thu Feb 13 19:36:06 2025 +0000 @@ -1,17 +1,20 @@ -<?xml version='1.0' encoding='utf-8'?> -<tool id="megahit" name="MEGAHIT" version="@TOOL_VERSION@+galaxy0"> +<tool id="megahit" name="MEGAHIT" version="@TOOL_VERSION@+galaxy2"> <description>for metagenomics assembly</description> + <macros> + <token name="@TOOL_VERSION@">1.2.9</token> + </macros> <xrefs> <xref type="bio.tools">megahit</xref> </xrefs> - <macros> - <token name="@TOOL_VERSION@">1.2.9</token> - </macros> <requirements> <requirement type="package" version="@TOOL_VERSION@">megahit</requirement> </requirements> <version_command>megahit --version</version_command> <command detect_errors="exit_code"><![CDATA[ +if [[ -n "\$GALAXY_MEMORY_MB" ]]; then + MEMORY="-m \$((GALAXY_MEMORY_MB * 1024))"; +fi; + megahit --num-cpu-threads \${GALAXY_SLOTS:-4} #if $input_option.choice == 'paired' @@ -52,7 +55,7 @@ ${advanced_section.nolocal} ${advanced_section.kmin1pass} --min-contig-len '${output_section.min_contig_len}' -&& cat megahit_out/log + \$MEMORY ]]></command> <inputs> <conditional name="input_option"> @@ -88,37 +91,38 @@ </when> </conditional> <section name="basic_section" title="Basic assembly options" expanded="True"> - <param name="min_count" argument="--min-count" type="integer" value="2" label="minimum multiplicity for filtering (k_min+1)-mers" help="(kmin+1)-mer with multiplicity lower than d (default 2, specified by --min-count option) will be discarded. You should be cautious to set d less than 2, which will lead to a much larger and noisy graph. We recommend using the default value 2 for metagenomics assembly. If you want to use MEGAHIT to do generic assemblies, please change this value according to the sequencing depth. (recommend --min-count 3 for >40x)."/> + <param argument="--min-count" type="integer" value="2" label="minimum multiplicity for filtering (k_min+1)-mers" help="(kmin+1)-mer with multiplicity lower than d (default 2, specified by --min-count option) will be discarded. You should be cautious to set d less than 2, which will lead to a much larger and noisy graph. We recommend using the default value 2 for metagenomics assembly. If you want to use MEGAHIT to do generic assemblies, please change this value according to the sequencing depth. (recommend --min-count 3 for >40x)."/> <conditional name="k_mer"> <param name="k_mer_method" type="select" label="K-mer specification method"> <option value="klist_method">Specify list</option> <option value="klim_method">Specify min, max, and step values</option> </param> <when value="klist_method"> - <param name="k_list" argument="--k-list" type="text" value="21,29,39,59,79,99,119,141" label="Comma-separated list of kmer size" help="all must be odd, in the range 15-255, and with increments <= 28"/> + <param argument="--k-list" type="text" value="21,29,39,59,79,99,119,141" label="Comma-separated list of kmer size" help="all must be odd, in the range 15-255, and with increments <= 28"/> </when> <when value="klim_method"> - <param name="k_min" argument="--k-min" type="integer" value="21" label="Minimum kmer size" max="255" help="Must be odd number. For ultra complex metagenomics data such as soil, a larger kmin, say 27, is recommended to reduce the complexity of the de Bruijn graph. Quality trimming is also recommended. For high-depth generic data, large --k-min (25 to 31) is recommended. Smaller --k-step, say 10, is more friendly to low-coverage datasets."/> - <param name="k_max" argument="--k-max" type="integer" value="141" label="Maximum kmer size" max="255" help="must be odd number"/> - <param name="k_step" argument="--k-step" type="integer" value="12" label="Increment of kmer size of each iteration" max="28" help="must be even number"/> + <param argument="--k-min" type="integer" value="21" label="Minimum kmer size" max="255" help="Must be odd number. For ultra complex metagenomics data such as soil, a larger kmin, say 27, is recommended to reduce the complexity of the de Bruijn graph. Quality trimming is also recommended. For high-depth generic data, large --k-min (25 to 31) is recommended. Smaller --k-step, say 10, is more friendly to low-coverage datasets."/> + <param argument="--k-max" type="integer" value="141" label="Maximum kmer size" max="255" help="must be odd number"/> + <param argument="--k-step" type="integer" value="12" label="Increment of kmer size of each iteration" max="28" help="must be even number"/> </when> </conditional> </section> <section name="advanced_section" title="Advanced assembly options" expanded="False"> <param name="nomercy" type="boolean" checked="false" truevalue="--no-mercy" falsevalue="" label="Do not add mercy kmers" help="Mercy kmers are specially designed for metagenomics assembly to recover low coverage sequences. For generic dataset >= 30x, MEGAHIT may generate better results with no mercy kmers." /> - <param name="bubble_level" argument="--bubble-level" type="integer" value="2" min="0" max="2" label="Intensity of bubble merging (0-2), 0 to disable" /> - <param name="merge_level" argument="--merge-level" type="text" value="20,0.95" label="Merge complex bubbles of length" /> - <param name="prune_level" argument="--prune-level" type="integer" value="2" min="0" max="3" label="Strength of low depth pruning" /> - <param name="prune_depth" argument="--prune-depth" type="integer" value="2" min="0" label="Remove unitigs with avg kmer depth less than this value" /> - <param name="disconnect_ratio" argument="--disconnect-ratio" type="float" value="0.1" label="Disconnect unitigs if its depth is less than this ratio times the total depth of itself and its siblings" /> - <param name="low_local_ratio" argument="--low-local-ratio" type="float" value="0.2" label="Remove unitigs if its depth is less than this ratio times the average depth of the neighborhoods" /> - <param name="cleaning_rounds" argument="--cleaning-rounds" type="integer" value="5" label="Number of rounds for graph cleanning" /> + <param argument="--bubble-level" type="integer" value="2" min="0" max="2" label="Intensity of bubble merging (0-2), 0 to disable" /> + <param argument="--merge-level" type="text" value="20,0.95" label="Merge complex bubbles of length" /> + <param argument="--prune-level" type="integer" value="2" min="0" max="3" label="Strength of low depth pruning" /> + <param argument="--prune-depth" type="integer" value="2" min="0" label="Remove unitigs with avg kmer depth less than this value" /> + <param argument="--disconnect-ratio" type="float" value="0.1" label="Disconnect unitigs if its depth is less than this ratio times the total depth of itself and its siblings" /> + <param argument="--low-local-ratio" type="float" value="0.2" label="Remove unitigs if its depth is less than this ratio times the average depth of the neighborhoods" /> + <param argument="--cleaning-rounds" type="integer" value="5" label="Number of rounds for graph cleanning" /> <param name="nolocal" type="boolean" checked="false" truevalue="--no-local" falsevalue="" label="Disable local assembly" /> <param name="kmin1pass" type="boolean" checked="false" truevalue="--kmin-1pass" falsevalue="" label="Use 1pass mode to build SdBG of k_min" /> </section> <section name="output_section" title="Output options" expanded="True"> - <param name="min_contig_len" argument="--min-contig-len" type="integer" value="200" label="Minimum length of contigs to output" /> + <param argument="--min-contig-len" type="integer" value="200" label="Minimum length of contigs to output" /> <param name="show_intermediate_contigs" type="boolean" checked="false" label="Return intermediate contigs?"/> + <param name="log_file" type="boolean" label="Generate a log file" help="Generates a log file, which can be used as MultiQC input"/> </section> </inputs> <outputs> @@ -127,27 +131,39 @@ <filter>output_section['show_intermediate_contigs']</filter> <discover_datasets pattern="(?P<designation>.*\d)\.contigs\.fa$" ext="fasta" directory="megahit_out/intermediate_contigs" /> </collection> + <data name="log_output" format="txt" label="${tool.name} on ${on_string} (Log file)" from_work_dir="megahit_out/log"> + <filter>output_section['log_file']</filter> + </data> </outputs> <tests> - <test> + <test expect_num_outputs="2"> <conditional name="input_option"> <param name="choice" value="single"/> <param name="single_files" value="refExample.fa" ftype="fasta"/> </conditional> + <param name="log_file" value="true"/> <output name="output"> <assert_contents> - <has_line_matching expression=">k21_0 flag=3 multi=1.0486 len=576" /> + <has_line_matching expression=">k21_0 flag=3 multi=1.0505 len=576" /> </assert_contents> </output> + <output name="log_output"> + <assert_contents> + <has_text text="- MEGAHIT v"/> + <has_text text="- Build graph for k = 21"/> + <has_text text="- Assemble contigs from SdBG for k = 21"/> + <has_text text="- Local assembly for k = 21"/> + </assert_contents> + </output> </test> - <test> + <test expect_num_outputs="1"> <conditional name="input_option"> <param name="choice" value="interleaved"/> <param name="interleaved_file" value="interleaved-fq.fa"/> </conditional> <output name="output" file="interleaved_result.fa"/> </test> - <test> + <test expect_num_outputs="1"> <conditional name="input_option"> <param name="choice" value="paired"/> <param name="fastq_input1" value="paired-fq1.fa"/> @@ -155,7 +171,7 @@ </conditional> <output name="output" file="paired_result.fa"/> </test> - <test> + <test expect_num_outputs="1"> <conditional name="input_option"> <param name="choice" value="paired_collection"/> <conditional name="batchmode">