Mercurial > repos > iuc > salsa
changeset 4:9a22227bb6d0 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/salsa2 commit 41b8952cd0739db0b5eb62d5dd9ccc7bc0f1925f
| author | iuc |
|---|---|
| date | Thu, 19 May 2022 14:17:24 +0000 |
| parents | f77f7a7f3b83 |
| children | |
| files | salsa2.xml |
| diffstat | 1 files changed, 28 insertions(+), 19 deletions(-) [+] |
line wrap: on
line diff
--- a/salsa2.xml Thu Nov 11 15:03:17 2021 +0000 +++ b/salsa2.xml Thu May 19 14:17:24 2022 +0000 @@ -1,12 +1,12 @@ <tool id="salsa" name="SALSA" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01"> <description>scaffold long read assemblies with Hi-C</description> + <macros> + <token name="@TOOL_VERSION@">2.3</token> + <token name="@VERSION_SUFFIX@">3</token> + </macros> <xrefs> <xref type="bio.tools">SALSA</xref> </xrefs> - <macros> - <token name="@TOOL_VERSION@">2.3</token> - <token name="@VERSION_SUFFIX@">2</token> - </macros> <requirements> <requirement type="package" version="@TOOL_VERSION@">salsa2</requirement> <requirement type="package" version="1.11">samtools</requirement> @@ -39,20 +39,24 @@ #if $iter: -i '$iter' #end if +#if $gensize: + -s '$gensize' +#end if +-m '$clean' -o ./out ]]></command> <inputs> <param name="fasta_in" type="data" format="fasta" label="Initial assembly file" help="Headers must not contain ':'."/> - <param name="bed_file" type="data" format="bed" label="Bed alignment" help="To start scaffolding with SALSA, reads need to be mapped to the assembly. - BWA or BOWTIE2 are recommended. SALSA requires a bed file as the input. The alignment bam file can be converted using the bamToBed command from + <param name="bed_file" type="data" format="bed" label="Bed alignment" help="To start scaffolding with SALSA, reads need to be mapped to the assembly. + BWA or BOWTIE2 are recommended. SALSA requires a bed file as the input. The alignment bam file can be converted using the bamToBed command from the Bedtools package."/> <param name="cutoff" argument="-c" type="integer" min="1" label="Cutoff" optional="true" help="Minimum contig length to scaffold"/> - <param name="gfa_file" argument="-g" type="data" format="gfa1,gfa2" optional="true" label="Sequence graphs" + <param name="gfa_file" argument="-g" type="data" format="gfa1,gfa2" optional="true" label="Sequence graphs" help="An assembly graph can be optionally provided to guide the scaffolding, potentially reducing the scaffolding errors"/> <conditional name="enzyme_conditional"> <param name="enzyme_options" type="select" label="Enzyme selection" help="Hi-C experiments can use different restriction enzymes. - The enzyme frequency in contigs is used to normalize the Hi-C interaction frequency. Note that you need to specify the actual - sequence of the cutting site for a restriction enzyme and not the enzyme name. You can also specify DNASE as an enzyme if you + The enzyme frequency in contigs is used to normalize the Hi-C interaction frequency. Note that you need to specify the actual + sequence of the cutting site for a restriction enzyme and not the enzyme name. You can also specify DNASE as an enzyme if you use an enzyme-free prep, e.g. Omin-C."> <option value="preconfigured">Preconfigured restriction enzymes</option> <option value="specific">Enter a specific sequence</option> @@ -71,9 +75,11 @@ </param> </when> </conditional> - <param name="iter" argument="-i" type="integer" min="0" max="20" label="Iterations" optional="true" - help="SALSA will scaffold through sequential iterations. The default number of iterations is 3. Increasing the number of iterations will + <param name="iter" argument="-i" type="integer" min="0" max="20" label="Iterations" optional="true" + help="SALSA will scaffold through sequential iterations. The default number of iterations is 3. Increasing the number of iterations will potentially increase the number of joins, however it could also introduce additional misjoins"/> + <param name="clean" argument="-m" type="boolean" label="Clean Assembly" checked="false" truevalue='yes' falsevalue="no" help="Set this option to 'yes' if you want to find misassemblies in input assembly" /> + <param name="gensize" argument="-s" type="integer" label="Expected Genome Size" optional="true" help="Expected Genome size of the assembled genome. If not set, Salsa will estimate genome size." /> </inputs> <outputs> <data name="scaffolds_fasta" format="fasta" from_work_dir="out/scaffolds_FINAL.fasta" label="${tool.name} on ${on_string}: FASTA assembly"/> @@ -87,11 +93,12 @@ <param name="gfa_file" value="test.gfa1"/> <conditional name="enzyme_conditional"> <param name="enzyme_options" value="specific"/> - <param name="manual_enzyme" value="GATC,GANTC"/> + <param name="manual_enzyme" value="GATC,GANTC"/> </conditional> - <param name="enzyme" value="GATC,GANTC"/> + <param name="enzyme" value="GATC,GANTC"/> <param name="cutoff" value="1000"/> <param name="iter" value="3"/> + <param name="clean" value="yes"/> <output name="scaffolds_fasta" file="out.fasta"/> <output name="scaffolds_agp" file="out.agp"/> </test> @@ -102,10 +109,11 @@ <param name="gfa_file" value="test.gfa1"/> <conditional name="enzyme_conditional"> <param name="enzyme_options" value="specific"/> - <param name="manual_enzyme" value="GATC,GANTC"/> + <param name="manual_enzyme" value="GATC,GANTC"/> </conditional> <param name="cutoff" value="1000"/> <param name="iter" value="3"/> + <param name="clean" value="yes"/> <output name="scaffolds_fasta" file="out.fasta"/> <output name="scaffolds_agp" file="out.agp"/> </test> @@ -116,10 +124,11 @@ <param name="gfa_file" value="test.gfa1"/> <conditional name="enzyme_conditional"> <param name="enzyme_options" value="preconfigured"/> - <param name="preconfigured_enzymes" value="arima1"/> + <param name="preconfigured_enzymes" value="arima1"/> </conditional> <param name="cutoff" value="1000"/> <param name="iter" value="3"/> + <param name="clean" value="yes"/> <output name="scaffolds_fasta" file="out.fasta"/> <output name="scaffolds_agp" file="out.agp"/> </test> @@ -138,12 +147,12 @@ **Mapping reads** -To start the scaffolding, first step is to map reads to the assembly. We recommend using `BWA <https://usegalaxy.eu/root?tool_id=toolshed.g2.bx.psu.edu/repos/devteam/bwa/bwa_mem/0.7.17.2>`_ -or `BOWTIE2 <https://usegalaxy.eu/root?tool_id=toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/bowtie2/2.4.2+galaxy0>`_ aligner to map reads. The read mapping generates a bam file. SALSA requires -BED file as the input. This can be done using the bamToBed command from the `Bedtools package <http://bedtools.readthedocs.io/en/latest/>`_. Also, SALSA requires BED files to be sorted by the +To start the scaffolding, first step is to map reads to the assembly. We recommend using `BWA <https://usegalaxy.eu/root?tool_id=toolshed.g2.bx.psu.edu/repos/devteam/bwa/bwa_mem/0.7.17.2>`_ +or `BOWTIE2 <https://usegalaxy.eu/root?tool_id=toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/bowtie2/2.4.2+galaxy0>`_ aligner to map reads. The read mapping generates a bam file. SALSA requires +BED file as the input. This can be done using the bamToBed command from the `Bedtools package <http://bedtools.readthedocs.io/en/latest/>`_. Also, SALSA requires BED files to be sorted by the read name, rather than the alignment coordinates. Once you have bam file, you can run following commands to get the bam file needed as an input to SALSA. -Since Hi-C reads and alignments contain experimental artifacts, the alignments needs some postprocessing. To align and postprocess +Since Hi-C reads and alignments contain experimental artifacts, the alignments needs some postprocessing. To align and postprocess the alignments, you can use the pipeline released by Arima Genomics which can be found in the `GitHub repository <https://github.com/ArimaGenomics>`_. Additional information on how to generate/filter the bam `here <https://github.com/marbl/SALSA#mapping-reads>`_.