|
4
|
1 <tool id="bismark_tool" name="Bismark" version="0.7.6">
|
|
|
2 <description>: A bisulfite read mapper and methylation caller</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="0.1.16">samtools</requirement>
|
|
|
5 <requirement type="package" version="0.12.7">bowtie2</requirement>
|
|
|
6 <requirement type="package" version="0.7.6">bismark</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command interpreter="perl">
|
|
|
9
|
|
|
10 bismark_wrapper.pl
|
|
|
11
|
|
|
12
|
|
|
13 "GENOME::${genome.fields.path}"
|
|
|
14
|
|
|
15
|
|
|
16
|
|
|
17 #if str($option_input.input_option) == "mates":
|
|
|
18 "MATES::$option_input.file_mate1::$option_input.file_mate2"
|
|
|
19 #else
|
|
|
20 "SINGLES::$option_input.file_single"
|
|
|
21 #end if
|
|
|
22
|
|
|
23 #if str($format_option) == "fasta":
|
|
|
24 "FORMAT::--fasta"
|
|
|
25 #else
|
|
|
26 "FORMAT::--fastq"
|
|
|
27 #end if
|
|
|
28
|
|
|
29 #if str($non_directional) == "ON":
|
|
|
30 "DIRECTIONAL::--non_directional"
|
|
|
31 #end if
|
|
|
32
|
|
|
33 "OUTPUT::$output"
|
|
|
34 "SUMMARY::$summary"
|
|
|
35
|
|
|
36 </command>
|
|
|
37 <inputs>
|
|
|
38
|
|
|
39 <param name="genome" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
|
|
|
40 <options from_data_table="bismark_indexes">
|
|
|
41 <filter type="sort_by" column="2"/>
|
|
|
42 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
|
|
|
43 </options>
|
|
|
44 </param>
|
|
|
45
|
|
|
46 <param name="format_option" type="select" label="sample format">
|
|
|
47 <option value="fastq" selected="true">fastq</option>
|
|
|
48 <option value="fasta">fasta</option>
|
|
|
49 </param>
|
|
|
50
|
|
|
51
|
|
|
52 <conditional name="option_input">
|
|
|
53 <param name="input_option" type="select" label="Input files">
|
|
|
54 <option value="mates" selected="true">mates</option>
|
|
|
55 <option value="singles">singles</option>
|
|
|
56 </param>
|
|
|
57 <when value="mates">
|
|
|
58 <param format="fasta, fastq" name="file_mate1" type="data" label="Mate 1" help=""/>
|
|
|
59 <param format="fasta, fastq" name="file_mate2" type="data" label="Mate 2" help=""/>
|
|
|
60 </when>
|
|
|
61 <when value="singles">
|
|
|
62 <param format="fasta, fastq" name="file_single" type="data" label="Single" help=""/>
|
|
|
63 </when>
|
|
|
64 </conditional>
|
|
|
65
|
|
|
66 <param name="non_directional" type="select" label="non-directional" help="" optional="true">
|
|
|
67 <option value="ON" selected="true">ON</option>
|
|
|
68 <option value="OFF">OFF</option>
|
|
|
69 </param>
|
|
|
70
|
|
|
71 </inputs>
|
|
|
72 <outputs>
|
|
|
73 <data name="summary" format="txt" label="Bismark Sumary" />
|
|
|
74 <data format="bam" name="output" label="${tool.name} on ${on_string}">
|
|
|
75 <actions>
|
|
|
76 <action type="metadata" name="dbkey">
|
|
|
77 <option type="from_data_table" name="bismark_indexes" column="1" offset="0">
|
|
|
78 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
|
|
|
79 <filter type="param_value" ref="genome" column="0"/>
|
|
|
80 </option>
|
|
|
81 </action>
|
|
|
82 </actions>
|
|
|
83 </data>
|
|
|
84 </outputs>
|
|
|
85 <help>
|
|
|
86 |
|
|
|
87
|
|
|
88
|
|
|
89 **Reference**
|
|
|
90
|
|
|
91 http://www.bioinformatics.babraham.ac.uk/projects/bismark/
|
|
|
92
|
|
|
93 -----
|
|
|
94
|
|
|
95 **What it does**
|
|
|
96
|
|
|
97 Bismark takes in FastA or FastQ files and aligns the reads to a specified bisulfite genome.
|
|
|
98 Sequence reads are transformed into a bisulfite converted forward strand version (C->T conversion)
|
|
|
99 or into a bisulfite treated reverse strand (G->A conversion of the forward strand).
|
|
|
100 Each of these reads are then aligned to bisulfite treated forward strand index of a reference genome
|
|
|
101 (C->T converted) and a bisulfite treated reverse strand index of the genome (G->A conversion of the
|
|
|
102 forward strand, by doing this alignments will produce the same positions). These 4 instances of
|
|
|
103 Bowtie (1 or 2) are run in parallel. The sequence file(s) are then read in again sequence by sequence
|
|
|
104 to pull out the original sequence from the genome and determine if there were any protected C's present or not.
|
|
|
105
|
|
|
106 As of version 0.7.0 Bismark will only run 2 alignment threads for OT and OB in parallel, the 4 strand mode can be
|
|
|
107 re-enabled by using --non_directional.
|
|
|
108
|
|
|
109 The final output of Bismark is in SAM format by default. But for storage restrictions the output is compressed (BAM).
|
|
|
110
|
|
|
111
|
|
|
112 -----
|
|
|
113
|
|
|
114 **Required Parameters**
|
|
|
115
|
|
|
116 ::
|
|
|
117
|
|
|
118 -q/--fastq The query input files (specified as mate1,mate2 or singles are FASTQ
|
|
|
119 files (usually having extension .fg or .fastq). This is the default. See also
|
|
|
120 --solexa-quals.
|
|
|
121
|
|
|
122 -f/--fasta The query input files (specified as mate1,mate2 or singles are FASTA
|
|
|
123 files (usually havin extension .fa, .mfa, .fna or similar). All quality values
|
|
|
124 are assumed to be 40 on the Phred scale.
|
|
|
125
|
|
|
126 -1 mates1 List of files containing the #1 mates (filename usually includes
|
|
|
127 "_1"), e.g. flyA_1.fq,flyB_1.fq). Sequences specified with this option must
|
|
|
128 correspond file-for-file and read-for-read with those specified in mates2.
|
|
|
129 Reads may be a mix of different lengths. Bismark will produce one mapping result
|
|
|
130 and one report file per paired-end input file pair.
|
|
|
131
|
|
|
132 -2 mates2 List of files containing the #2 mates (filename usually includes
|
|
|
133 "_2"), e.g. flyA_1.fq,flyB_1.fq). Sequences specified with this option must
|
|
|
134 correspond file-for-file and read-for-read with those specified in mates1.
|
|
|
135 Reads may be a mix of different lengths.
|
|
|
136
|
|
|
137 singles List of files containing the reads to be aligned (e.g.
|
|
|
138 lane1.fq,lane2.fq lane3.fq). Reads may be a mix of different lengths. Bismark will
|
|
|
139 produce one mapping result and one report file per input file.
|
|
|
140
|
|
|
141 --non_directional The sequencing library was constructed in a non strand-specific manner, alignments to all four
|
|
|
142 bisulfite strands will be reported. Default: ON.
|
|
|
143
|
|
|
144 (The current Illumina protocol for BS-Seq is directional, in which case the strands complementary
|
|
|
145 to the original strands are merely theoretical and should not exist in reality. Specifying directional
|
|
|
146 alignments (which is the default) will only run 2 alignment threads to the original top (OT)
|
|
|
147 or bottom (OB) strands in parallel and report these alignments. This is the recommended option
|
|
|
148 for sprand-specific libraries).
|
|
|
149
|
|
|
150 -----
|
|
|
151
|
|
|
152 **Default Parameters**
|
|
|
153
|
|
|
154 ::
|
|
|
155
|
|
|
156 --bowtie2 Uses Bowtie 2 instead of Bowtie 1. Bismark limits Bowtie 2 to only perform end-to-end
|
|
|
157 alignments, i.e. searches for alignments involving all read characters (also called
|
|
|
158 untrimmed or unclipped alignments). Bismark assumes that raw sequence data is adapter
|
|
|
159 and/or quality trimmed where appropriate. Default: on.
|
|
|
160
|
|
|
161
|
|
|
162
|
|
|
163
|
|
|
164 -p NTHREADS Launch NTHREADS parallel search threads (default: 4). Threads will run on separate processors/cores
|
|
|
165 and synchronize when parsing reads and outputting alignments. Searching for alignments is highly
|
|
|
166 parallel, and speedup is close to linear. Increasing -p increases Bowtie 2's memory footprint.
|
|
|
167 E.g. when aligning to a human genome index, increasing -p from 1 to 8 increases the memory footprint
|
|
|
168 by a few hundred megabytes. This option is only available if bowtie is linked with the pthreads
|
|
|
169 library (i.e. if BOWTIE_PTHREADS=0 is not specified at build time). In addition, this option will
|
|
|
170 automatically use the option '--reorder', which guarantees that output SAM records are printed in
|
|
|
171 an order corresponding to the order of the reads in the original input file, even when -p is set
|
|
|
172 greater than 1 (Bismark requires the Bowtie 2 output to be this way). Specifying --reorder and
|
|
|
173 setting -p greater than 1 causes Bowtie 2 to run somewhat slower and use somewhat more memory then
|
|
|
174 if --reorder were not specified. Has no effect if -p is set to 1, since output order will naturally
|
|
|
175 correspond to input order in that case.
|
|
|
176
|
|
|
177
|
|
|
178
|
|
|
179 </help>
|
|
|
180 </tool>
|
|
|
181
|
|
|
182
|
