Mercurial > repos > drosofff > msp_oases
annotate oases_optimiser.xml @ 5:58bf34f98232 draft default tip
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
author | drosofff |
---|---|
date | Fri, 29 Apr 2016 03:14:58 -0400 |
parents | 42fad5f9c78e |
children |
rev | line source |
---|---|
5
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
1 <tool id="oasesoptimiserv" name="Oases_optimiser" version="1.1.5"> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
2 <description>Auto optimise de novo RNA-seq Oases/Velvet assembly</description> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
3 <requirements> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
4 <requirement type="package" version="0.2.08_7a32460a60929b510037952ae815bb6e29b68123">oases</requirement> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
5 </requirements> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
6 <command><![CDATA[ |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
7 python "$__tool_directory__"/oases_optimiser.py "$start_hash_length" "$end_hash_length" |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
8 #for $i in $inputs |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
9 "${i.input}" |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
10 #end for |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
11 "$transcripts" |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
12 ]]></command> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
13 <inputs> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
14 <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."> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
15 <option value="11" selected="yes">11</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
16 <option value="13">13</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
17 <option value="15">15</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
18 <option value="17">17</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
19 <option value="19">19</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
20 <option value="21">21</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
21 <option value="23">23</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
22 <option value="25">25</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
23 <option value="35">35</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
24 <option value="45">45</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
25 <option value="55">55</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
26 <option value="65">65</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
27 </param> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
28 <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"> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
29 <option value="25">25</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
30 <option value="27">27</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
31 <option value="29">29</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
32 <option value="31">31</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
33 <option value="33">33</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
34 <option value="35">35</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
35 <option value="45">45</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
36 <option value="55">55</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
37 <option value="63">63</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
38 <option value="69">69</option> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
39 </param> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
40 <repeat name="inputs" title="Input Files"> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
41 <param name="input" type="data" format="fasta" label="Dataset: short reads, fasta format"/> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
42 </repeat> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
43 </inputs> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
44 <outputs> |
0
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
45 <data format="fasta" name="transcripts" label="${tool.name} on ${on_string}: Denovo assembled transcripts"/> |
5
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
46 </outputs> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
47 <tests> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
48 <test> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
49 <param name="input" value="input.fa" ftype="fasta"/> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
50 <param name="start_hash_length" value="15" /> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
51 <param name="end_hash_length" value="35" /> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
52 <output name="transcripts" file="output.fa"/> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
53 </test> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
54 </tests> |
0
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
55 <help> |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
56 **Oases Optimiser Overview** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
57 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
58 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
59 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
60 Provide all the information about insert lengths and their standard deviation as |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
61 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! |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
62 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
63 ---------------------------------------------------------------------------------- |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
64 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
65 Oases produces a number of output files, which correspond to the different algorithms |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
66 being run succesively on the data. In the above example, you would find: |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
67 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
68 transcripts.fa |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
69 A FASTA file containing the transcripts imputed directly from trivial |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
70 clusters of contigs (loci with less than two transcripts and Confidence Values = 1) |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
71 and the highly expressed transcripts imputed by dynamic |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
72 programming (loci with more than 2 transcripts and Confidence Values less than 1). |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
73 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
74 splicing_events.txt |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
75 A hybrid file which describes the contigs contained in each locus in FASTA |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
76 format, interlaced with one line descriptions of splicing events using the |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
77 AStalavista nomenclature*. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
78 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
79 Read the Oases `documentation`__ for details on using the Oases Assembler. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
80 |
5
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
81 .. _Oases: http://www.ebi.ac.uk/~zerbino/oases/ |
0
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
82 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
83 .. __: http://www.ebi.ac.uk/~zerbino/oases/Manual.txt |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
84 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
85 ------ |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
86 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
87 **Other outputs (as per Velvet)** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
88 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
89 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
90 **Contigs** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
91 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
92 The *contigs.fa* file. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
93 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
94 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
95 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
96 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
97 **Stats** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
98 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
99 The *stats.txt* file. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
100 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
101 The in and out columns correspond to the number of arcs on the 5' and 3' ends of the contig respectively. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
102 The coverages in columns short1 cov, short1 Ocov, short2 cov, and short2 Ocov are provided in k-mer coverage (5.1). |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
103 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
104 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
105 **LastGraph** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
106 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
107 The *LastGraph* file. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
108 This file describes in its entirety the graph produced by Velvet. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
109 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
110 **AMOS.afg** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
111 The *velvet_asm.afg* file. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
112 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
113 The file describes all the contigs contained in the contigs.fa file (cf 4.2.1). |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
114 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
115 **Advanced options** |
5
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
116 -ins_length integer: expected distance between two paired-end reads in the first short-read dataset (default: no read pairing) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
117 -ins_length2 integer: expected distance between two paired-end reads in the second short-read dataset (default: no read pairing) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
118 -ins_length_long integer: expected distance between two long paired-end reads (default: no read pairing) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
119 -ins_length_sd integer: est. standard deviation of respective dataset (default: 10% of corresponding length) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
120 -scaffolding yes|no: scaffolding of contigs used paired end information (default: on) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
121 -max_branch_length integer: maximum length in base pair of bubble (default: 100) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
122 -max_divergence floating-point: maximum divergence rate between two branches in a bubble (default: 0.2) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
123 -max_gap_count integer: maximum number of gaps allowed in the alignment of the two branches of a bubble (default: 3) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
124 -min_pair_count integer: minimum number of paired end connections to justify the scaffolding of two long contigs (default: 10) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
125 -max_coverage floating point: removal of high coverage nodes AFTER tour bus (default: no removal) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
126 -long_mult_cutoff int: minimum number of long reads required to merge contigs (default: 2) |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
127 -min_trans_length: simple threshold on output transcript length |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
128 -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] |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
129 -min_pair_cov: minimum number of times two contigs must be connected by reads or read pairs to be clustered together [default=4] |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
130 -paired_cutoff: minimum ratio between the numbers of observed and expected connecting read pairs between two contigs [default=0.1] |
0
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
131 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
132 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
133 **Hash Length** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
134 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
135 The hash length, also known as k-mer length, corresponds to the length, in base pairs, of the words being hashed. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
136 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
137 The hash length is the length of the k-mers being entered in the hash table. Firstly, you must observe three technical constraints:: |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
138 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
139 # it must be an odd number, to avoid palindromes. If you put in an even number, Velvet will just decrement it and proceed. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
140 # it must be below or equal to MAXKMERHASH length (cf. 2.3.3, by default 31bp), because it is stored on 64 bits |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
141 # it must be strictly inferior to read length, otherwise you simply will not observe any overlaps between reads, for obvious reasons. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
142 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
143 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
144 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. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
145 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. |
5
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
146 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. |
0
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
147 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
148 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
149 **Velvetg options** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
150 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
151 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
152 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
153 **Input Files** |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
154 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
155 This Velvet wrapper works only with fasta format, non-paired-end reads. |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
156 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
157 Supported file formats are:: |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
158 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
159 fasta |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
160 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
161 Read categories are:: |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
162 |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
163 short (default) |
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
164 |
5
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
165 </help> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
166 <citations> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
167 <citation type="doi">10.1093/bioinformatics/bts094</citation> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
168 <citation type="doi">10.1101/gr.074492.107</citation> |
58bf34f98232
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_oases commit 3d96056b65a38e7642cfeef4ed274dc76b88472a
drosofff
parents:
4
diff
changeset
|
169 </citations> |
0
435711ba68e3
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
drosofff
parents:
diff
changeset
|
170 </tool> |