Mercurial > repos > iuc > idba_ud

comparison idba_ud.xml @ 0:fdaf2375d405 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/idba_ud commit 6901a5d3feb96ea81d2e3b765b39e32cb94565eb
author iuc
date Fri, 21 Sep 2018 15:25:56 -0400
parents
children 2ed5c0795f99
comparison
equal deleted inserted replaced
-1:000000000000 0:fdaf2375d405
1 <tool id="idba_ud" name="IDBA-UD" version="1.1.3">
2 <description>
3 Iterative de Bruijn Graph Assembler <!--for sequencing data with highly uneven depth-->
4 </description>
5 <macros>
6 <import>macros.xml</import>
7 </macros>
8 <expand macro="requirements"/>
9 <command><![CDATA[
10
11 idba_ud
12
13 --read '$read'
14 #if $read_level_2:
15 --read_level_2 '$read_level_2'
16 #end if
17 #if $read_level_3:
18 --read_level_3 '$read_level_3'
19 #end if
20 #if $read_level_4:
21 --read_level_4 '$read_level_4'
22 #end if
23 #if $read_level_5:
24 --read_level_5 '$read_level_5'
25 #end if
26 #if $long_read:
27 --long_read '$long_read'
28 #end if
29 --mink $mink
30 --maxk $maxk
31 --step $step
32 --inner_mink $inner_mink
33 --inner_step $inner_step
34 --prefix $prefix
35 --min_count $min_count
36 --min_support $min_support
37 --num_threads \${GALAXY_SLOTS:-1}
38 --seed_kmer $seed_kmer
39 --min_contig $min_contig
40 --similar $similar
41 --max_mismatch $max_mismatch
42 --min_pairs $min_pairs
43 #if $other:
44 ${" ".join(str($other).split(","))}
45 #end if
46 ]]></command>
47
48 <inputs>
49 <param argument="--read" type="data" format="fasta" label="Fasta read file. Lower or equal to 600b"/>
50 <param argument="--long_read" type="data" format="fasta" optional="true" label="Fasta long read file. More than 600b"/>
51
52 <param argument="--read_level_2" type="data" format="fasta" optional="true" label="Fasta Paired-end reads for second level scaffolds"/>
53 <param argument="--read_level_3" type="data" format="fasta" optional="true" label="Fasta Paired-end reads for third level scaffolds"/>
54 <param argument="--read_level_4" type="data" format="fasta" optional="true" label="Fasta Paired-end reads for fourth level scaffolds"/>
55 <param argument="--read_level_5" type="data" format="fasta" optional="true" label="Fasta Paired-end reads for fifth level scaffolds"/>
56
57 <param argument="--mink" type="integer" value="20" max="312" label="Minimum k value. Lower or equal to 312"/>
58 <param argument="--maxk" type="integer" value="100" max="312" label="Maximum k value. Lower or equal to 312"/>
59 <param argument="--step" type="integer" value="20" label="Increment of k-mer of each iteration"/>
60 <param argument="--inner_mink" type="integer" value="10" label="Inner minimum k value"/>
61 <param argument="--inner_step" type="integer" value="5" label="Inner increment of k-mer"/>
62 <param argument="--prefix" type="integer" value="3" label="Prefix length used to build sub k-mer table"/>
63 <param argument="--min_count" type="integer" value="2" label="Minimum multiplicity for filtering k-mer when building the graph"/>
64 <param argument="--min_support" type="integer" value="1" label="Minimum supoort in each iteration"/>
65 <param argument="--seed_kmer" type="integer" value="30" label="Seed kmer size for alignment"/>
66 <param argument="--min_contig" type="integer" value="200" label="Minimum size of contig"/>
67 <param argument="--similar" type="float" value="0.95" label="Similarity for alignment"/>
68 <param argument="--max_mismatch" type="integer" value="3" label="Max mismatch of error correction"/>
69 <param argument="--min_pairs" type="integer" value="3" label="Minimum number of pairs"/>
70
71 <param name="other" type="select" display="checkboxes" multiple="true" label="Other options">
72 <option value="--no_bubble">Do not merge bubble (--no_bubble)</option>
73 <option value="--no_local">Do not use local assembly (--no_local)</option>
74 <option value="--no_coverage">Do not iterate on coverage (--no_coverage)</option>
75 <option value="--no_correct">Do not do correction (--no_correct)</option>
76 <option value="--pre_correction">Perform pre-correction before assembly (--pre_correction)</option>
77 </param>
78 </inputs>
79 <outputs>
80 <data name="output" from_work_dir="out/scaffold.fa" format="fasta"/>
81 </outputs>
82 <tests>
83 <test>
84 <param name="read" value="merged.fa" ftype="fasta"/>
85 <output name="output" file="out/scaffold.fa" ftype="fasta"/>
86 </test>
87 </tests>
88 <help><![CDATA[
89 IDBA-UD is a iterative De Bruijn Graph De Novo Assembler for Short Reads Sequencing data with Highly Uneven Sequencing Depth. It is an extension of IDBA algorithm. IDBA-UD also iterates from small k to a large k. In each iteration, short and low-depth contigs are removed iteratively with cutoff threshold from low to high to reduce the errors in low-depth and high-depth regions. Paired-end reads are aligned to contigs and assembled locally to generate some missing k-mers in low-depth regions. With these technologies, IDBA-UD can iterate k value of de Bruijn graph to a very large value with less gaps and less branches to form long contigs in both low-depth and high-depth regions.
90
91
92 Input: IDBA-UD takes interleaved paired end data in the FASTA format as input,
93 i.e. paired-end reads need to be stored in the same FASTA file suc h that a pair
94 of reads should be in two consecutive lines.
95 In Galaxy paired reads in separate FASTQ files can be converted into interleaved
96 FASTA using the tools:
97
98 * `FASTQ interlacer on paired end read <https://toolshed.g2.bx.psu.edu/view/devteam/fastq_paired_end_interlacer>`_
99 * `Samtools extract FASTA or FASTQ from a SAM file <https://toolshed.g2.bx.psu.edu/view/devteam/fastq_to_fasta>`_
100
101 Note that, IDBA-UD assumes that the paired-end reads are in order (->,<-).
102 If your data is in reverse order (<-,->), please convert it by yourself.
103 ]]></help>
104 <citations>
105 <citation type="doi">10.1093/bioinformatics/bts174</citation>
106 </citations>
107 </tool>