Mercurial > repos > iuc > salsa

comparison salsa2.xml @ 3:5af503c47367 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/salsa2 commit 4904594e8df7cbd6eeee4be24023c6bd15e162de"
author iuc
date Thu, 11 Nov 2021 15:02:50 +0000
parents e15025381b3b
children 41c4e48b0617
comparison
equal deleted inserted replaced
2:e15025381b3b 3:5af503c47367
3 <xrefs> 3 <xrefs>
4 <xref type="bio.tools">SALSA</xref> 4 <xref type="bio.tools">SALSA</xref>
5 </xrefs> 5 </xrefs>
6 <macros> 6 <macros>
7 <token name="@TOOL_VERSION@">2.3</token> 7 <token name="@TOOL_VERSION@">2.3</token>
8 <token name="@VERSION_SUFFIX@">1</token> 8 <token name="@VERSION_SUFFIX@">2</token>
9 </macros> 9 </macros>
10 <requirements> 10 <requirements>
11 <requirement type="package" version="@TOOL_VERSION@">salsa2</requirement> 11 <requirement type="package" version="@TOOL_VERSION@">salsa2</requirement>
12 <requirement type="package" version="1.11">samtools</requirement> 12 <requirement type="package" version="1.11">samtools</requirement>
13 </requirements> 13 </requirements>
41 #end if 41 #end if
42 -o ./out 42 -o ./out
43 ]]></command> 43 ]]></command>
44 <inputs> 44 <inputs>
45 <param name="fasta_in" type="data" format="fasta" label="Initial assembly file" help="Headers must not contain ':'."/> 45 <param name="fasta_in" type="data" format="fasta" label="Initial assembly file" help="Headers must not contain ':'."/>
46 <param name="bed_file" type="data" format="bed" label="Bed alignment" help="Sorted by read names"/> 46 <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.
47 <param name="cutoff" argument="-c" type="integer" min="1" label="Cutoff" optional="true" help="Minimum contig length to scaffold."/> 47 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
48 <param name="gfa_file" argument="-g" type="data" format="gfa1,gfa2" optional="true" label="Sequence graphs" help="Sequence graphs encoded in GFA format."/> 48 the Bedtools package."/>
49 <param name="cutoff" argument="-c" type="integer" min="1" label="Cutoff" optional="true" help="Minimum contig length to scaffold"/>
50 <param name="gfa_file" argument="-g" type="data" format="gfa1,gfa2" optional="true" label="Sequence graphs"
51 help="An assembly graph can be optionally provided to guide the scaffolding, potentially reducing the scaffolding errors"/>
49 <conditional name="enzyme_conditional"> 52 <conditional name="enzyme_conditional">
50 <param name="enzyme_options" type="select" label="Enzyme selection" help="TODO"> 53 <param name="enzyme_options" type="select" label="Enzyme selection" help="Hi-C experiments can use different restriction enzymes.
54 The enzyme frequency in contigs is used to normalize the Hi-C interaction frequency. Note that you need to specify the actual
55 sequence of the cutting site for a restriction enzyme and not the enzyme name. You can also specify DNASE as an enzyme if you
56 use an enzyme-free prep, e.g. Omin-C.">
51 <option value="preconfigured">Preconfigured restriction enzymes</option> 57 <option value="preconfigured">Preconfigured restriction enzymes</option>
52 <option value="specific">Enter a specific sequence</option> 58 <option value="specific">Enter a specific sequence</option>
53 </param> 59 </param>
54 <when value="preconfigured"> 60 <when value="preconfigured">
55 <param name="preconfigured_enzymes" type="select" multiple="true" label="Preconfigured enzymes"> 61 <param name="preconfigured_enzymes" type="select" multiple="true" label="Preconfigured enzymes">
63 help="Restriction enzyme sequence. If multiple were used, include all as a comma separated list without spaces (ex. 'GATC,AAGCTT')."> 69 help="Restriction enzyme sequence. If multiple were used, include all as a comma separated list without spaces (ex. 'GATC,AAGCTT').">
64 <validator type="expression" message="Only alphabetical letters and the comma can be used in to define restriction enzym sequences.">value.replace(',', '').isalpha()</validator> 70 <validator type="expression" message="Only alphabetical letters and the comma can be used in to define restriction enzym sequences.">value.replace(',', '').isalpha()</validator>
65 </param> 71 </param>
66 </when> 72 </when>
67 </conditional> 73 </conditional>
68 <param name="iter" argument="-i" type="integer" min="0" label="Iterations" optional="true" help="Number of iterations to run"/> 74 <param name="iter" argument="-i" type="integer" min="0" max="20" label="Iterations" optional="true"
75 help="SALSA will scaffold through sequential iterations. The default number of iterations is 3. Increasing the number of iterations will
76 potentially increase the number of joins, however it could also introduce additional misjoins"/>
69 </inputs> 77 </inputs>
70 <outputs> 78 <outputs>
71 <data name="scaffolds_fasta" format="fasta" from_work_dir="out/scaffolds_FINAL.fasta" label="${tool.name} on ${on_string}: FASTA assembly"/> 79 <data name="scaffolds_fasta" format="fasta" from_work_dir="out/scaffolds_FINAL.fasta" label="${tool.name} on ${on_string}: FASTA assembly"/>
72 <data name="scaffolds_agp" format="tabular" from_work_dir="out/scaffolds_FINAL.agp" label="${tool.name} on ${on_string}: agp output"/> 80 <data name="scaffolds_agp" format="tabular" from_work_dir="out/scaffolds_FINAL.agp" label="${tool.name} on ${on_string}: agp output"/>
73 </outputs> 81 </outputs>
115 <output name="scaffolds_fasta" file="out.fasta"/> 123 <output name="scaffolds_fasta" file="out.fasta"/>
116 <output name="scaffolds_agp" file="out.agp"/> 124 <output name="scaffolds_agp" file="out.agp"/>
117 </test> 125 </test>
118 </tests> 126 </tests>
119 <help><![CDATA[ 127 <help><![CDATA[
120 **What is does** 128 .. class:: infomark
129
130 **Purpose**
121 131
122 SALSA (Simple AssembLy ScAffolder) is a scaffolding tool based on a computational method that exploits the genomic proximity 132 SALSA (Simple AssembLy ScAffolder) is a scaffolding tool based on a computational method that exploits the genomic proximity
123 information in Hi-C data sets for long range scaffolding of de novo genome assemblies. 133 information in Hi-C data sets for long range scaffolding of de novo genome assemblies.
134
135 ----
136
137 .. class:: infomark
138
139 **Mapping reads**
140
141 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>`_
142 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
143 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
144 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.
145
146 Since Hi-C reads and alignments contain experimental artifacts, the alignments needs some postprocessing. To align and postprocess
147 the alignments, you can use the pipeline released by Arima Genomics which can be found in the `GitHub repository <https://github.com/ArimaGenomics>`_.
148
149 Additional information on how to generate/filter the bam `here <https://github.com/marbl/SALSA#mapping-reads>`_.
124 150
125 ]]></help> 151 ]]></help>
126 <citations> 152 <citations>
127 <citation type="doi">10.1101/261149</citation> 153 <citation type="doi">10.1101/261149</citation>
128 <citation type="doi">10.1186/s12864-017-3879-z</citation> 154 <citation type="doi">10.1186/s12864-017-3879-z</citation>