annotate oases_optimiser.xml @ 2:ab37eb09b4ca draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
author artbio
date Mon, 12 Feb 2024 23:55:39 +0000
parents c9b5ec6c45e8
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
1 <tool id="oasesoptimiserv" name="Oases_optimiser" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
2 <description>Auto optimise de novo RNA-seq Oases/Velvet assembly</description>
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
3 <macros>
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
4 <token name="@TOOL_VERSION@">1.4.0</token>
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
5 <token name="@VERSION_SUFFIX@">0</token>
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
6 <token name="@PROFILE@">23.0</token>
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
7 </macros>
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
8 <requirements>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
9 <requirement type="package" version="0.2.09">oases</requirement>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
10 <requirement type="package" version="1.2.10">velvet</requirement>
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
11 <requirement type="package" version="3.12.1">python</requirement>
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
12 </requirements>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
13 <command><![CDATA[
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
14 python '$__tool_directory__/oases_optimiser.py' '$start_hash_length' '$end_hash_length'
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
15 #for $i in $inputs
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
16 '${i.input}'
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
17 #end for
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
18 '$transcripts'
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
19 ]]></command>
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
20 <inputs>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
21 <param label="Start Hash Length" name="start_hash_length" type="select" help="k-mer length in base pairs of the words being hashed. Shorter hash lengths (i.e. less than 31) may cause out-of-memory problems.">
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
22 <option value="11" selected="yes">11</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
23 <option value="13">13</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
24 <option value="15">15</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
25 <option value="17">17</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
26 <option value="19">19</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
27 <option value="21">21</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
28 <option value="23">23</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
29 <option value="25">25</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
30 <option value="35">35</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
31 <option value="45">45</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
32 <option value="55">55</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
33 <option value="65">65</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
34 </param>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
35 <param label="End Hash Length" name="end_hash_length" type="select" help="k-mer length in base pairs of the words being hashed. Value has to be higher than the Start Hash Length value">
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
36 <option value="25">25</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
37 <option value="27">27</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
38 <option value="29">29</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
39 <option value="31">31</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
40 <option value="33">33</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
41 <option value="35">35</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
42 <option value="45">45</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
43 <option value="55">55</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
44 <option value="63">63</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
45 <option value="69">69</option>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
46 </param>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
47 <repeat name="inputs" title="Input Files">
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
48 <param name="input" type="data" format="fasta" label="Dataset: short reads, fasta format"/>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
49 </repeat>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
50 </inputs>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
51 <outputs>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
52 <data format="fasta" name="transcripts" label="${tool.name} on ${on_string}: Denovo assembled transcripts"/>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
53 </outputs>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
54 <tests>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
55 <test>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
56 <param name="input" value="input.fa" ftype="fasta"/>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
57 <param name="start_hash_length" value="15" />
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
58 <param name="end_hash_length" value="35" />
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
59 <output name="transcripts">
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
60 <assert_contents>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
61 <has_line_matching expression=">Locus_1_Transcript_1/1_Confidence_.+" />
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
62 <has_line_matching expression=">Locus_25_Transcript_1/1_Confidence_.+" />
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
63 </assert_contents>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
64 </output>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
65 </test>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
66 </tests>
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
67 <help>
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
68 **Oases Optimiser Overview**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
69
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
70 Oases_ is a de novo transcriptome assembler specially designed to work with short reads. It is an extension of Velvet developed by Daniel Zerbino and Ewan Birney at the European Bioinformatics Institute (EMBL-EBI), near Cambridge, in the United Kingdom.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
71
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
72 Provide all the information about insert lengths and their standard deviation as
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
73 possible (identical to Velvet). In the advanced oases options you should set the -ins_length flag when using paired-end reads (e.g. -ins_length 200 -ins_length_sd 100). If you do not do this, then paired-end information will not be used by Oases!
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
74
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
75 ----------------------------------------------------------------------------------
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
76
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
77 Oases produces a number of output files, which correspond to the different algorithms
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
78 being run succesively on the data. In the above example, you would find:
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
79
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
80 transcripts.fa
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
81 A FASTA file containing the transcripts imputed directly from trivial
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
82 clusters of contigs (loci with less than two transcripts and Confidence Values = 1)
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
83 and the highly expressed transcripts imputed by dynamic
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
84 programming (loci with more than 2 transcripts and Confidence Values less than 1).
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
85
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
86 splicing_events.txt
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
87 A hybrid file which describes the contigs contained in each locus in FASTA
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
88 format, interlaced with one line descriptions of splicing events using the
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
89 AStalavista nomenclature*.
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
90
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
91 Read the Oases `documentation`__ for details on using the Oases Assembler.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
92
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
93 .. _Oases: https://github.com/dzerbino/oases
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
94
2
ab37eb09b4ca planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/oases commit d5a2de4b4c556e028fc5ef7ffcc7c2d0cf31c5ec
artbio
parents: 1
diff changeset
95 .. __: https://bioweb.pasteur.fr/docs/modules/oases/0.2.08/OasesManual.pdf
0
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
96
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
97 ------
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
98
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
99 **Other outputs (as per Velvet)**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
100
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
101
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
102 **Contigs**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
103
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
104 The *contigs.fa* file.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
105 This fasta file contains the sequences of the contigs longer than 2k, where k is the word-length used in velveth. If you have specified a min contig lgth threshold, then the contigs shorter than that value are omitted.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
106 Note that the length and coverage information provided in the header of each contig should therefore be understood in k-mers and in k-mer coverage (cf. 5.1) respectively.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
107 The N's in the sequence correspond to gaps between scaffolded contigs. The number of N's corresponds to the estimated length of the gap. For reasons of compatibility with the archives, any gap shorter than 10bp is represented by a sequence of 10 N's.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
108
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
109 **Stats**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
110
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
111 The *stats.txt* file.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
112 This file is a simple tabbed-delimited description of the nodes. The column names are pretty much self-explanatory. Note however that node lengths are given in k-mers. To obtain the length in nucleotides of each node you simply need to add k - 1, where k is the word-length used in velveth.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
113 The in and out columns correspond to the number of arcs on the 5' and 3' ends of the contig respectively.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
114 The coverages in columns short1 cov, short1 Ocov, short2 cov, and short2 Ocov are provided in k-mer coverage (5.1).
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
115 Also, the difference between # cov and # Ocov is the way these values are computed. In the first count, slightly divergent sequences are added to the coverage tally. However, in the second, stricter count, only the sequences which map perfectly onto the consensus sequence are taken into account.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
116
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
117 **LastGraph**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
118
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
119 The *LastGraph* file.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
120 This file describes in its entirety the graph produced by Velvet.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
121
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
122 **AMOS.afg**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
123 The *velvet_asm.afg* file.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
124 This file is mainly designed to be read by the open-source AMOS genome assembly package. Nonetheless, a number of programs are available to transform this kind of file into other assembly file formats (namely ACE, TIGR, Arachne and Celera). See http://amos.sourceforge.net/ for more information.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
125 The file describes all the contigs contained in the contigs.fa file (cf 4.2.1).
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
126
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
127 **Advanced options**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
128 -ins_length integer: expected distance between two paired-end reads in the first short-read dataset (default: no read pairing)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
129 -ins_length2 integer: expected distance between two paired-end reads in the second short-read dataset (default: no read pairing)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
130 -ins_length_long integer: expected distance between two long paired-end reads (default: no read pairing)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
131 -ins_length_sd integer: est. standard deviation of respective dataset (default: 10% of corresponding length)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
132 -scaffolding yes|no: scaffolding of contigs used paired end information (default: on)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
133 -max_branch_length integer: maximum length in base pair of bubble (default: 100)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
134 -max_divergence floating-point: maximum divergence rate between two branches in a bubble (default: 0.2)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
135 -max_gap_count integer: maximum number of gaps allowed in the alignment of the two branches of a bubble (default: 3)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
136 -min_pair_count integer: minimum number of paired end connections to justify the scaffolding of two long contigs (default: 10)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
137 -max_coverage floating point: removal of high coverage nodes AFTER tour bus (default: no removal)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
138 -long_mult_cutoff int: minimum number of long reads required to merge contigs (default: 2)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
139 -min_trans_length: simple threshold on output transcript length
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
140 -cov_cutoff: minimum number of times a k-mer has to be observed to be used in the assembly (just like in Velvet) [default=3]
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
141 -min_pair_cov: minimum number of times two contigs must be connected by reads or read pairs to be clustered together [default=4]
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
142 -paired_cutoff: minimum ratio between the numbers of observed and expected connecting read pairs between two contigs [default=0.1]
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
143
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
144
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
145 **Hash Length**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
146
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
147 The hash length, also known as k-mer length, corresponds to the length, in base pairs, of the words being hashed.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
148
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
149 The hash length is the length of the k-mers being entered in the hash table. Firstly, you must observe three technical constraints::
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
150
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
151 # it must be an odd number, to avoid palindromes. If you put in an even number, Velvet will just decrement it and proceed.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
152 # it must be below or equal to MAXKMERHASH length (cf. 2.3.3, by default 31bp), because it is stored on 64 bits
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
153 # it must be strictly inferior to read length, otherwise you simply will not observe any overlaps between reads, for obvious reasons.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
154
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
155 Now you still have quite a lot of possibilities. As is often the case, it's a trade- off between specificity and sensitivity. Longer kmers bring you more specificity (i.e. less spurious overlaps) but lowers coverage (cf. below). . . so there's a sweet spot to be found with time and experience.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
156 We like to think in terms of "k-mer coverage", i.e. how many times has a k-mer been seen among the reads. The relation between k-mer coverage Ck and standard (nucleotide-wise) coverage C is Ck = C # (L - k + 1)/L where k is your hash length, and L you read length.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
157 Experience shows that this kmer coverage should be above 10 to start getting decent results. If Ck is above 20, you might be "wasting" coverage. Experience also shows that empirical tests with different values for k are not that costly to run! VelvetOptimiser automates these tests for you.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
158 Occasionally oases crashes at specific k-mers, in that case this Galaxy wrapper will skip this k-mer and continue the analysis without this k-mer.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
159
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
160
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
161 **Velvetg options**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
162
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
163
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
164
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
165 **Input Files**
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
166
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
167 This Velvet wrapper works only with fasta format, non-paired-end reads.
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
168
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
169 Supported file formats are::
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
170
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
171 fasta
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
172
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
173 Read categories are::
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
174
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
175 short (default)
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
176
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
177 </help>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
178 <citations>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
179 <citation type="doi">10.1093/bioinformatics/bts094</citation>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
180 <citation type="doi">10.1101/gr.074492.107</citation>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
181 </citations>
f7dd852c8f4c planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/oases commit 48b8101fd53263212839ecb14d3029811a3278f4
artbio
parents:
diff changeset
182 </tool>