|
0
|
1 <tool id="velveth" name="velveth" version="1.0.1">
|
|
|
2 <description>Prepare a dataset for the Velvet velvetg Assembler</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="1.2.10">velvet</requirement>
|
|
|
5 </requirements>
|
|
|
6 <macros>
|
|
|
7 <macro name="categories">
|
|
|
8 <param name="category" type="select" label="">
|
|
|
9 <option value="" selected="true"></option>
|
|
|
10 <option value="2">2</option>
|
|
|
11 <option value="3">3</option>
|
|
|
12 <option value="4">4</option>
|
|
|
13 </param>
|
|
|
14 </macro>
|
|
|
15 <macro name="paired_reads">
|
|
|
16 <conditional name="files">
|
|
|
17 <param name="separate" type="boolean" checked="false" truevalue="separate" falsevalue="interleaved" label="Are the reads paired and in two different files?" help="Tick this box if this is a paired library with forward and reverse read files.."/>
|
|
|
18 <when value="interleaved">
|
|
|
19 <param name="forwards_file" type="data" format="fasta,fastq,raw,sam,bam" label="Read dataset"/>
|
|
|
20 </when>
|
|
|
21 <when value="separate">
|
|
|
22 <param name="forwards_file" type="data" format="fasta,fastq,raw,sam,bam" label="Read dataset for direction 1"/>
|
|
|
23 <param name="reverse_file" type="data" format="fasta,fastq,raw,sam,bam" label="Read dataset for direction 2"/>
|
|
|
24 </when>
|
|
|
25 </conditional>
|
|
|
26 </macro>
|
|
|
27 </macros>
|
|
|
28 <command interpreter="python">
|
|
|
29 velveth_wrapper.py '$out_file1' '$out_file1.files_path' $hash_length $strand_specific
|
|
|
30 #for i in $inputs:
|
|
|
31 #if $i.reads.readtype == 'short':
|
|
|
32 -short${i.reads.category}
|
|
|
33 -#if str($i.reads.forwards_file.ext).startswith('fast') then $i.reads.forwards_file.ext[:5] else $i.reads.forwards_file.ext#
|
|
|
34 $i.reads.forwards_file.file_name
|
|
|
35 #elif $i.reads.readtype == 'shortPaired':
|
|
|
36 -shortPaired${i.reads.category}
|
|
|
37 -#if str($i.reads.files.forwards_file.ext).startswith('fast') then $i.reads.files.forwards_file.ext[:5] else $i.reads.files.forwards_file.ext#
|
|
|
38 #if $i.reads.files.separate:
|
|
|
39 -separate
|
|
|
40 $i.reads.files.forwards_file.__str__
|
|
|
41 $i.reads.files.reverse_file.__str__
|
|
|
42 #else
|
|
|
43 $i.reads.files.forwards_file.__str__
|
|
|
44 #end if
|
|
|
45 #elif $i.reads.readtype == 'long':
|
|
|
46 -long
|
|
|
47 -#if str($i.reads.forwards_file.ext).startswith('fast') then $i.reads.forwards_file.ext[:5] else $i.reads.forwards_file.ext#
|
|
|
48 $i.reads.forwards_file.__str__
|
|
|
49 #elif $i.reads.readtype == 'longPaired':
|
|
|
50 -longPaired
|
|
|
51 -#if str($i.reads.files.forwards_file.ext).startswith('fast') then $i.reads.files.forwards_file.ext[:5] else $i.reads.files.forwards_file.ext#
|
|
|
52 #if $i.reads.files.separate:
|
|
|
53 -separate
|
|
|
54 $i.reads.files.forwards_file.__str__
|
|
|
55 $i.reads.files.reverse_file.__str__
|
|
|
56 #else
|
|
|
57 $i.reads.files.forwards_file.__str__
|
|
|
58 #end if
|
|
|
59 #elif $i.reads.readtype == 'reference':
|
|
|
60 -reference
|
|
|
61 -#if str($i.reads.forwards_file.ext).startswith('fast') then $i.reads.forwards_file.ext[:5] else $i.reads.forwards_file.ext#
|
|
|
62 $i.reads.forwards_file.__str__
|
|
|
63 #end if
|
|
|
64 #end for
|
|
|
65 </command>
|
|
|
66 <inputs>
|
|
|
67 <param name="hash_length" type="integer" value="19" label="Hash Length" help="k-mer length in base pairs of the words being hashed.">
|
|
|
68 <validator type="in_range" min="7" max="191"/>
|
|
|
69 <validator type="expression" message="Must be an odd number">(int(value) % 2 == 1)</validator>
|
|
|
70 </param>
|
|
|
71
|
|
|
72 <param name="strand_specific" type="boolean" checked="false" truevalue="-strand_specific" falsevalue="" label="Use strand specific transcriptome sequencing" help="If you are using a strand specific transcriptome sequencing protocol, you may wish to use this option for better results."/>
|
|
|
73
|
|
|
74 ##Read files section. No need for zipped or auto format options as the data is already sucked in in a legible format...
|
|
|
75 <repeat name="inputs" min="1" title="Input read libraries">
|
|
|
76 <conditional name="reads">
|
|
|
77 <param name="readtype" type="select" label="Read type">
|
|
|
78 <option value="short" selected="yes">short</option>
|
|
|
79 <option value="shortPaired">shortPaired</option>
|
|
|
80 <option value="long">long</option>
|
|
|
81 <option value="longPaired">longPaired</option>
|
|
|
82 <option value="reference">reference</option>
|
|
|
83 </param>
|
|
|
84 <when value="short">
|
|
|
85 <expand macro="categories" />
|
|
|
86 <param name="forwards_file" type="data" format="fasta,fastq,raw,sam,bam" label="Read dataset"/>
|
|
|
87 </when>
|
|
|
88 <when value="shortPaired">
|
|
|
89 <expand macro="categories" />
|
|
|
90 <expand macro="paired_reads" />
|
|
|
91 </when>
|
|
|
92 <when value="long">
|
|
|
93 <param name="forwards_file" type="data" format="fasta,fastq,raw,sam,bam" label="Read dataset"/>
|
|
|
94 </when>
|
|
|
95 <when value="longPaired">
|
|
|
96 <expand macro="paired_reads" />
|
|
|
97 </when>
|
|
|
98 <when value="reference">
|
|
|
99 </when>
|
|
|
100 </conditional>
|
|
|
101 </repeat>
|
|
|
102 </inputs>
|
|
|
103 <outputs>
|
|
|
104 <data format="velvet" name="out_file1" />
|
|
|
105 </outputs>
|
|
|
106 <tests>
|
|
|
107 <test>
|
|
|
108 <param name="hash_length" value="21" />
|
|
|
109 <param name="read_type" value="-shortPaired" />
|
|
|
110 <!-- <repeat name="inputs"> -->
|
|
|
111 <param name="file_format" value="fasta" />
|
|
|
112 <param name="read_type" value="shortPaired reads" />
|
|
|
113 <param name="input" value="velvet_test_reads.fa" ftype="fasta" />
|
|
|
114 <!-- </repeat> -->
|
|
|
115 <param name="strand_specific" value="" />
|
|
|
116 <output name="out_file1" file="velveth_test1/output.html" lines_diff="4">
|
|
|
117 <extra_files type="file" name='Sequences' value="velveth_test1/Sequences" compare="diff" />
|
|
|
118 <extra_files type="file" name='Roadmaps' value="velveth_test1/Roadmaps" compare="diff" />
|
|
|
119 </output>
|
|
|
120 </test>
|
|
|
121 </tests>
|
|
|
122 <help>
|
|
|
123 **Velvet Overview**
|
|
|
124
|
|
|
125 Velvet_ is a de novo genomic assembler specially designed for short read sequencing technologies, such as Solexa or 454, developed by Daniel Zerbino and Ewan Birney at the European Bioinformatics Institute (EMBL-EBI), near Cambridge, in the United Kingdom.
|
|
|
126
|
|
|
127 Velvet currently takes in short read sequences, removes errors then produces high quality unique contigs. It then uses paired-end read and long read information, when available, to retrieve the repeated areas between contigs.
|
|
|
128
|
|
|
129 Read the Velvet `documentation`__ for details on using the Velvet Assembler.
|
|
|
130
|
|
|
131 .. _Velvet: http://www.ebi.ac.uk/~zerbino/velvet/
|
|
|
132
|
|
|
133 .. __: http://www.ebi.ac.uk/~zerbino/velvet/Manual.pdf
|
|
|
134
|
|
|
135 ------
|
|
|
136
|
|
|
137 **Velveth**
|
|
|
138
|
|
|
139 Velveth takes in a number of sequence files, produces a hashtable, then outputs two files in an output directory (creating it if necessary), Sequences and Roadmaps, which are necessary to velvetg.
|
|
|
140
|
|
|
141 ------
|
|
|
142
|
|
|
143 **Hash Length**
|
|
|
144
|
|
|
145 The hash length, also known as k-mer length, corresponds to the length, in base pairs, of the words being hashed.
|
|
|
146
|
|
|
147 The hash length is the length of the k-mers being entered in the hash table. Firstly, you must observe three technical constraints::
|
|
|
148
|
|
|
149 # it must be an odd number, to avoid palindromes. If you put in an even number, Velvet will just decrement it and proceed.
|
|
|
150 # it must be below or equal to MAXKMERHASH length (cf. 2.3.3, by default 31bp), because it is stored on 64 bits
|
|
|
151 # it must be strictly inferior to read length, otherwise you simply will not observe any overlaps between reads, for obvious reasons.
|
|
|
152
|
|
|
153 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.
|
|
|
154 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.
|
|
|
155 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!
|
|
|
156
|
|
|
157 **Input Files**
|
|
|
158
|
|
|
159 Velvet works mainly with fasta and fastq formats. For paired-end reads, the assumption is that each read is next to its mate
|
|
|
160 read. In other words, if the reads are indexed from 0, then reads 0 and 1 are paired, 2 and 3, 4 and 5, etc.
|
|
|
161
|
|
|
162 Supported file formats are::
|
|
|
163
|
|
|
164 fasta
|
|
|
165 fastq
|
|
|
166 fasta.gz
|
|
|
167 fastq.gz
|
|
|
168 eland
|
|
|
169 gerald
|
|
|
170
|
|
|
171 Read categories are::
|
|
|
172
|
|
|
173 short (default)
|
|
|
174 shortPaired
|
|
|
175 short2 (same as short, but for a separate insert-size library)
|
|
|
176 shortPaired2 (see above)
|
|
|
177 long (for Sanger, 454 or even reference sequences)
|
|
|
178 longPaired
|
|
|
179
|
|
|
180 </help>
|
|
|
181 </tool>
|
