Mercurial > repos > iuc > salsa

comparison salsa2.xml @ 5:58a870ef434c draft default tip

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 270d2e701478bcf3f7cd1db8e188eb2cd69f5db5
author iuc
date Thu, 01 Aug 2024 11:41:30 +0000
parents 9a22227bb6d0
children
comparison
equal deleted inserted replaced
4:9a22227bb6d0 5:58a870ef434c
1 <tool id="salsa" name="SALSA" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01"> 1 <tool id="salsa" name="SALSA" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01">
2 <description>scaffold long read assemblies with Hi-C</description> 2 <description>scaffold long read assemblies with Hi-C</description>
3 <macros> 3 <macros>
4 <token name="@TOOL_VERSION@">2.3</token> 4 <token name="@TOOL_VERSION@">2.3</token>
5 <token name="@VERSION_SUFFIX@">3</token> 5 <token name="@VERSION_SUFFIX@">5</token>
6 </macros> 6 </macros>
7 <xrefs> 7 <xrefs>
8 <xref type="bio.tools">SALSA</xref> 8 <xref type="bio.tools">SALSA</xref>
9 </xrefs> 9 </xrefs>
10 <requirements> 10 <requirements>
21 #if $enzyme_conditional.enzyme_options == 'preconfigured': 21 #if $enzyme_conditional.enzyme_options == 'preconfigured':
22 #if $enzyme_conditional.preconfigured_enzymes == 'dovetail' 22 #if $enzyme_conditional.preconfigured_enzymes == 'dovetail'
23 -e 'GATC' 23 -e 'GATC'
24 #else if $enzyme_conditional.preconfigured_enzymes == 'arima1' 24 #else if $enzyme_conditional.preconfigured_enzymes == 'arima1'
25 -e 'GATC,GANTC' 25 -e 'GATC,GANTC'
26 #else 26 #else if $enzyme_conditional.preconfigured_enzymes == 'arima2'
27 -e 'GATC,GANTC,CTNAG,TTAA' 27 -e 'GATC,GANTC,CTNAG,TTAA'
28 #else if $enzyme_conditional.preconfigured_enzymes == 'omnic'
29 -e 'DNASE'
28 #end if 30 #end if
29 #else: 31 #else:
30 -e '${enzyme_conditional.manual_enzyme}' 32 -e '${enzyme_conditional.manual_enzyme}'
31 #end if 33 #end if
32 -b '$bed_file' 34 -b '$bed_file'
42 #if $gensize: 44 #if $gensize:
43 -s '$gensize' 45 -s '$gensize'
44 #end if 46 #end if
45 -m '$clean' 47 -m '$clean'
46 -o ./out 48 -o ./out
49
50 &&
51
52 ## The tool seems to generate malformed AGP. Print exactly
53 ## 9 tab-delimited columns, adding blank columns or
54 ## removing columns if necessary.
55 awk -F'\t'
56 '{while(NF<9)\$0=\$0 FS""; if(NF>9)\$9=\$9 FS \$(NF--); print \$1,\$2,\$3,\$4,\$5,\$6,\$7,\$8,\$9}'
57 OFS='\t' out/scaffolds_FINAL.agp
58 | cut -f1-9
59 > out/scaffolds_FINAL.fixed.agp
60
47 ]]></command> 61 ]]></command>
48 <inputs> 62 <inputs>
49 <param name="fasta_in" type="data" format="fasta" label="Initial assembly file" help="Headers must not contain ':'."/> 63 <param name="fasta_in" type="data" format="fasta" label="Initial assembly file" help="Headers must not contain ':'."/>
50 <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. 64 <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."/>
51 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
52 the Bedtools package."/>
53 <param name="cutoff" argument="-c" type="integer" min="1" label="Cutoff" optional="true" help="Minimum contig length to scaffold"/> 65 <param name="cutoff" argument="-c" type="integer" min="1" label="Cutoff" optional="true" help="Minimum contig length to scaffold"/>
54 <param name="gfa_file" argument="-g" type="data" format="gfa1,gfa2" optional="true" label="Sequence graphs" 66 <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"/>
55 help="An assembly graph can be optionally provided to guide the scaffolding, potentially reducing the scaffolding errors"/>
56 <conditional name="enzyme_conditional"> 67 <conditional name="enzyme_conditional">
57 <param name="enzyme_options" type="select" label="Enzyme selection" help="Hi-C experiments can use different restriction enzymes. 68 <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 use an enzyme-free prep, e.g. Omni-C.">
58 The enzyme frequency in contigs is used to normalize the Hi-C interaction frequency. Note that you need to specify the actual
59 sequence of the cutting site for a restriction enzyme and not the enzyme name. You can also specify DNASE as an enzyme if you
60 use an enzyme-free prep, e.g. Omin-C.">
61 <option value="preconfigured">Preconfigured restriction enzymes</option> 69 <option value="preconfigured">Preconfigured restriction enzymes</option>
62 <option value="specific">Enter a specific sequence</option> 70 <option value="specific">Enter a specific sequence</option>
63 </param> 71 </param>
64 <when value="preconfigured"> 72 <when value="preconfigured">
65 <param name="preconfigured_enzymes" type="select" multiple="true" label="Preconfigured enzymes"> 73 <param name="preconfigured_enzymes" type="select" multiple="true" label="Preconfigured enzymes">
66 <option value="dovetail">Dovetail Chicago, Dovetail Hi-C or Phase: GATC</option> 74 <option value="dovetail">Dovetail Chicago, Dovetail Hi-C or Phase: GATC</option>
67 <option value="arima1">Arima Hi-C 1.0: GATC, GANTC</option> 75 <option value="arima1">Arima Hi-C 1.0: GATC, GANTC</option>
68 <option value="arima2">Arima Hi-C 2.0: GATC, GANTC, CTNAG, TTAA</option> 76 <option value="arima2">Arima Hi-C 2.0: GATC, GANTC, CTNAG, TTAA</option>
77 <option value="omnic">Dovetail Omni-C: enzyme-free prep</option>
69 </param> 78 </param>
70 </when> 79 </when>
71 <when value="specific"> 80 <when value="specific">
72 <param name="manual_enzyme" argument="-e" type="text" label="Restriction enzyme sequence(s)" 81 <param name="manual_enzyme" argument="-e" type="text" label="Restriction enzyme sequence(s)" help="Restriction enzyme sequence. If multiple were used, include all as a comma separated list without spaces (ex. 'GATC,AAGCTT').">
73 help="Restriction enzyme sequence. If multiple were used, include all as a comma separated list without spaces (ex. 'GATC,AAGCTT').">
74 <validator type="expression" message="Only alphabetical letters and the comma can be used in to define restriction enzym sequences.">value.replace(',', '').isalpha()</validator> 82 <validator type="expression" message="Only alphabetical letters and the comma can be used in to define restriction enzym sequences.">value.replace(',', '').isalpha()</validator>
75 </param> 83 </param>
76 </when> 84 </when>
77 </conditional> 85 </conditional>
78 <param name="iter" argument="-i" type="integer" min="0" max="20" label="Iterations" optional="true" 86 <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"/>
79 help="SALSA will scaffold through sequential iterations. The default number of iterations is 3. Increasing the number of iterations will 87 <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"/>
80 potentially increase the number of joins, however it could also introduce additional misjoins"/> 88 <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."/>
81 <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" />
82 <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." />
83 </inputs> 89 </inputs>
84 <outputs> 90 <outputs>
85 <data name="scaffolds_fasta" format="fasta" from_work_dir="out/scaffolds_FINAL.fasta" label="${tool.name} on ${on_string}: FASTA assembly"/> 91 <data name="scaffolds_fasta" format="fasta" from_work_dir="out/scaffolds_FINAL.fasta" label="${tool.name} on ${on_string}: FASTA assembly"/>
86 <data name="scaffolds_agp" format="tabular" from_work_dir="out/scaffolds_FINAL.agp" label="${tool.name} on ${on_string}: agp output"/> 92 <data name="scaffolds_agp" format="agp" from_work_dir="out/scaffolds_FINAL.fixed.agp" label="${tool.name} on ${on_string}: agp output"/>
87 </outputs> 93 </outputs>
88 <tests> 94 <tests>
89 <test>
90 <param name="fasta_in" value="test.fasta"/>
91 <param name="length" value="test.fai"/>
92 <param name="bed_file" value="test.bed"/>
93 <param name="gfa_file" value="test.gfa1"/>
94 <conditional name="enzyme_conditional">
95 <param name="enzyme_options" value="specific"/>
96 <param name="manual_enzyme" value="GATC,GANTC"/>
97 </conditional>
98 <param name="enzyme" value="GATC,GANTC"/>
99 <param name="cutoff" value="1000"/>
100 <param name="iter" value="3"/>
101 <param name="clean" value="yes"/>
102 <output name="scaffolds_fasta" file="out.fasta"/>
103 <output name="scaffolds_agp" file="out.agp"/>
104 </test>
105 <!--Test manual enzyme-->
106 <test> 95 <test>
107 <param name="fasta_in" value="test.fasta"/> 96 <param name="fasta_in" value="test.fasta"/>
108 <param name="bed_file" value="test.bed"/> 97 <param name="bed_file" value="test.bed"/>
109 <param name="gfa_file" value="test.gfa1"/> 98 <param name="gfa_file" value="test.gfa1"/>
110 <conditional name="enzyme_conditional"> 99 <conditional name="enzyme_conditional">
127 <param name="preconfigured_enzymes" value="arima1"/> 116 <param name="preconfigured_enzymes" value="arima1"/>
128 </conditional> 117 </conditional>
129 <param name="cutoff" value="1000"/> 118 <param name="cutoff" value="1000"/>
130 <param name="iter" value="3"/> 119 <param name="iter" value="3"/>
131 <param name="clean" value="yes"/> 120 <param name="clean" value="yes"/>
132 <output name="scaffolds_fasta" file="out.fasta"/> 121 <output name="scaffolds_fasta" file="arima1.fasta"/>
133 <output name="scaffolds_agp" file="out.agp"/> 122 <output name="scaffolds_agp" file="arima1.agp"/>
123 </test>
124 <!--Test omnic-->
125 <test>
126 <param name="fasta_in" value="test.fasta"/>
127 <param name="bed_file" value="test.bed"/>
128 <param name="gfa_file" value="test.gfa1"/>
129 <conditional name="enzyme_conditional">
130 <param name="enzyme_options" value="preconfigured"/>
131 <param name="preconfigured_enzymes" value="arima1"/>
132 </conditional>
133 <param name="cutoff" value="1000"/>
134 <param name="iter" value="3"/>
135 <param name="clean" value="yes"/>
136 <output name="scaffolds_fasta" file="omnic.fasta"/>
137 <output name="scaffolds_agp" file="omnic.agp"/>
134 </test> 138 </test>
135 </tests> 139 </tests>
136 <help><![CDATA[ 140 <help><![CDATA[
137 .. class:: infomark 141 .. class:: infomark
138 142