Mercurial > repos > iuc > links

comparison links.xml @ 0:4b05cff7013b 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/links commit f15e5bb67b7a212ecd8c98e816c80e22d3b7a0cb"
author iuc
date Wed, 23 Feb 2022 08:25:19 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:4b05cff7013b
1 <tool id="links" name="LINKS" version="@TOOL_VERSION@+galaxy+@VERSION_SUFFIX@" python_template_version="3.5" profile="20.09">
2 <description> - scaffold genome assemblies with long reads</description>
3 <xrefs>
4 <xref type="bio.tools">links</xref>
5 </xrefs>
6 <macros>
7 <token name="@TOOL_VERSION@">2.0.1</token>
8 <token name="@VERSION_SUFFIX@">1</token>
9 </macros>
10 <requirements>
11 <requirement type="package" version="@TOOL_VERSION@">links</requirement>
12 </requirements>
13 <version_command><![CDATA[
14 LINKS | grep "LINKS v" | cut -d' ' -f4
15 ]]></version_command>
16 <command detect_errors="exit_code"><![CDATA[
17
18 ## set up file paths
19
20 #set sequences_fn = 'sequences.' + $f.ext
21 ln -s '$f' '$sequences_fn'
22 &&
23 #for $n, $read in enumerate($reads):
24 #set read_fn = 'reads' + str($n) + '.' + $read.ext
25 ln -s '$read' '$read_fn'
26 &&
27 printf '%s\n' '$read_fn' >> reads.fof
28 &&
29 #end for
30
31 ## RUN LINKS
32
33 LINKS
34 -f '$sequences_fn'
35 -s reads.fof
36 -b links_output
37
38 #if str($scaffolding.k):
39 -k '$scaffolding.k'
40 #end if
41
42 #if str($scaffolding.d):
43 -d '$scaffolding.d'
44 #end if
45
46 #if str($scaffolding.t):
47 -t '$scaffolding.t'
48 #end if
49
50 #if str($advanced.a):
51 -a '$advanced.a'
52 #end if
53
54 #if str($advanced.e):
55 -e '$advanced.e'
56 #end if
57
58 #if str($advanced.o):
59 -o '$advanced.o'
60 #end if
61
62 #if str($advanced.l):
63 -l '$advanced.l'
64 #end if
65
66 #if str($advanced.z):
67 -z '$advanced.z'
68 #end if
69
70 #if str($advanced.p):
71 -p '$advanced.p'
72 #end if
73
74 ]]></command>
75 <inputs>
76 <param argument="-f" type="data" format="fasta,fasta.gz" label="Contigs" help="Sequences to scaffold" />
77 <param name="reads" type="data" format="fasta,fasta.gz,fastq,fastq.gz" label="Reads" help="Long sequence reads for scaffolding" multiple="true" />
78 <section name="scaffolding" title="Scaffolding options" expanded="False">
79 <param argument="-k" type="integer" value="15" optional="true" label="k-mer length" />
80 <param argument="-d" type="text" value="4000" optional="true" label="Distance" help="Distance between k-mer pairs. Multiple distances are separated by comma, e.g. 500,1000,2000,3000"/>
81 <param argument="-t" type="text" value="2" optional="true" label="Step" help="Step of sliding window when extracting k-mer pairs from long reads. Multiple steps are separated by comma, e.g. 10,5" />
82 </section>
83 <section name="advanced" title="Advanced options" expanded="False">
84 <param argument="-a" type="float" value="0.3" optional="true" label="Maximum link ratio" help="Maximum link ratio between two best contig pairs. Higher values lead to least accurate scaffolding" />
85 <param argument="-e" type="float" value="0.1" optional="true" label="Error" help="Error (%) allowed on -d distance"/>
86 <param argument="-l" type="integer" value="5" optional="true" label="Number of links" help="Minimum number of links (k-mer pairs) to compute
87 scaffold"/>
88 <param argument="-o" type="integer" value="0" optional="true" label="Offset" help="Offset position for extracting k-mer pairs"/>
89 <param argument="-p" type="float" value="0.001" optional="true" label="Bloom filter false positive rate" help="Increase to prevent memory allocation errors"/>
90 <param argument="-z" type="integer" value="500" optional="true" label="Minimum contig length" help="Minimum contig length to consider for scaffolding"/>
91 </section>
92 </inputs>
93 <outputs>
94 <data name="scaffolds" format="fasta" from_work_dir="links_output.scaffolds.fa" label="${tool.name} on ${on_string} (scaffolds)" />
95 <data name="correspondence" format="tabular" from_work_dir="links_output.assembly_correspondence.tsv" label="${tool.name} on ${on_string} (Correspondence file)" />
96 <data name="gv" format="graph_dot" from_work_dir="links_output.gv" label="${tool.name} on ${on_string} (Graph)" />
97 </outputs>
98 <tests>
99 <!-- Basic test -->
100 <test>
101 <param name="f" value="used_contigs.fasta.gz"/>
102 <param name="reads" value="reads.fasta.gz"/>
103 <output name="scaffolds" ftype="fasta" file="single_readfile.scaffolds.fa"/>
104 <output name="correspondence" ftype="tabular" file="single_readfile.assembly_correspondence.tsv"/>
105 <output name="gv">
106 <assert_contents>
107 <has_text text="node [shape = circle]" />
108 </assert_contents>
109 </output>
110 </test>
111 <!-- Test multiple readfile input -->
112 <test>
113 <param name="f" value="used_contigs.fasta.gz"/>
114 <param name="reads" value="reads1.fasta.gz,reads2.fasta.gz"/>
115 <output name="scaffolds" ftype="fasta" file="multi_readfile.scaffolds.fa"/>
116 <output name="correspondence" ftype="tabular" file="multi_readfile.assembly_correspondence.tsv"/>
117 </test>
118 <!-- Test scaffolding parameters -->
119 <test>
120 <param name="f" value="used_contigs.fasta.gz"/>
121 <param name="reads" value="reads.fasta.gz"/>
122 <param name="k" value="19" />
123 <param name="d" value="500,1000,2000,3000" />
124 <param name="t" value="10,5" />
125 <output name="scaffolds" ftype="fasta" file="scaffolding.scaffolds.fa"/>
126 <output name="correspondence" ftype="tabular" file="scaffolding.assembly_correspondence.tsv"/>
127 </test>
128 <!-- Test advanced parameters -->
129 <test>
130 <param name="f" value="used_contigs.fasta.gz"/>
131 <param name="reads" value="reads.fasta.gz"/>
132 <output name="scaffolds" ftype="fasta" file="advanced.scaffolds.fa"/>
133 <param name="a" value="0.2" />
134 <param name="e" value="0.05" />
135 <param name="l" value="10" />
136 <param name="o" value="1" />
137 <param name="z" value="600" />
138 <output name="scaffolds" ftype="fasta" file="advanced.scaffolds.fa"/>
139 <output name="correspondence" ftype="tabular" file="advanced.assembly_correspondence.tsv"/>
140 </test>
141 </tests>
142 <help><![CDATA[
143
144 .. figure:: https://github.com/warrenlr/links/raw/master/links-logo.png
145 :alt: links-logo
146 :width: 200px
147
148 `LINKS <https://github.com/bcgsc/LINKS>`__ is a genomics application for
149 scaffolding genome assemblies with long reads, such as those produced by
150 Oxford Nanopore Technologies Ltd. It can be used to scaffold
151 high-quality draft genome assemblies with any long sequences (eg. ONT
152 reads, PacBio reads, other draft genomes, etc).
153
154 **Input**:
155
156 **LINKS does not use quality information in the Reads, so it is
157 recommended to filter the long reads first**.
158
159 Provide a ``fasta`` or ``fasta.gz`` dataset containing the Contigs, and
160 a ``fastq``, ``fastq.gz``, ``fasta`` or ``fasta.gz`` dataset of Reads to
161 be used for scaffolding.
162
163 **Use cases**:
164
165 - *Use long reads to scaffold a draft assembly* by providing the draft
166 assembly to the Contigs parameter and the long reads to the Reads
167 parameter.
168 - *Use a reference assembly to scaffold a draft assembly* by providing
169 the reference assembly to the Reads parameter. For example, you could
170 use a species’s reference genome to scaffold a genome that was
171 assembled for another individual.
172
173 **How it works**:
174
175 LINKS uses *k*-mer pairs from the Reads to identify candidate pairs of
176 Contigs, then uses the number of spanning *k*-mer pairs and the mean
177 distance between them to build scaffolds.
178
179 You can control the distance between *k*-mer pairs, the length of the
180 *k*-mers and the minimum number of *k*-mer pairs between contigs. See
181 the `LINKS readme on
182 GitHub <https://github.com/bcgsc/LINKS#how-it-works>`__ for information
183 on setting advanced parameters.
184
185
186
187 ]]></help>
188 <citations>
189 <citation type="doi">10.1186/s13742-015-0076-3</citation>
190 </citations>
191 </tool>