4
|
1 <tool id="methyation_extractor_tool" name="Methylation Extractor" version="0.7.6">
|
|
2 <description>: extracts the methylation information for individual cytosine</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 methylation_extractor_wrapper.pl
|
|
11
|
|
12
|
|
13 "GENOME::${genome.fields.path}"
|
|
14
|
|
15
|
|
16 #if str($no_overlap) == "ON":
|
|
17 "OPTION::--no_overlap"
|
|
18 #end if
|
|
19
|
|
20 #if str($ending) == "single":
|
|
21 "ENDING::-s"
|
|
22 #else
|
|
23 "ENDING::-p"
|
|
24 #end if
|
|
25
|
|
26 #if str($report) == "ON":
|
|
27 "OPTION::--report"
|
|
28 #end if
|
|
29
|
|
30 "OPTION::--bedGraph"
|
|
31
|
|
32 "OPTION::--counts"
|
|
33
|
|
34
|
|
35 "OUTPUT::$output"
|
|
36 "SUMMARY::$summary"
|
|
37
|
|
38 "BAMFILE::$bamfile"
|
|
39
|
|
40
|
|
41 </command>
|
|
42 <inputs>
|
|
43
|
|
44 <param name="genome" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
|
|
45 <options from_data_table="bismark_indexes">
|
|
46 <filter type="sort_by" column="2"/>
|
|
47 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
|
|
48 </options>
|
|
49 </param>
|
|
50
|
|
51 <param name="bamfile" type="data" format="bam" label="Bam file: bismark output" />
|
|
52
|
|
53 <param name="ending" type="select" label="ending" help="" optional="true">
|
|
54 <option value="single" >single-end</option>
|
|
55 <option value="paired" selected="true">paired-end</option>
|
|
56 </param>
|
|
57
|
|
58 <param name="no_overlap" type="select" label="no-overlap" help="" optional="true">
|
|
59 <option value="ON" selected="true">ON</option>
|
|
60 <option value="OFF">OFF</option>
|
|
61 </param>
|
|
62
|
|
63 <param name="report" type="select" label="Report" help="" optional="true">
|
|
64 <option value="ON" selected="true">ON</option>
|
|
65 <option value="OFF">OFF</option>
|
|
66 </param>
|
|
67
|
|
68 </inputs>
|
|
69 <outputs>
|
|
70 <data format="bedgraph" name="output" label="${tool.name} on ${on_string}">
|
|
71 <actions>
|
|
72 <action type="metadata" name="dbkey">
|
|
73 <option type="from_data_table" name="bismark_indexes" column="1" offset="0">
|
|
74 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
|
|
75 <filter type="param_value" ref="genome" column="0"/>
|
|
76 </option>
|
|
77 </action>
|
|
78 </actions>
|
|
79 </data>
|
|
80 <data name="summary" format="txt" label="${tool.name} summary" />
|
|
81 </outputs>
|
|
82 <help>
|
|
83 |
|
|
84
|
|
85 **Reference**
|
|
86
|
|
87 http://www.bioinformatics.babraham.ac.uk/projects/bismark/
|
|
88
|
|
89 -----
|
|
90
|
|
91 **What it does**
|
|
92
|
|
93
|
|
94
|
|
95 The script reads in a bisulfite read alignment results file
|
|
96 produced by the Bismark bisulfite mapper (BAM file) and extracts the methylation
|
|
97 informationfor individual cytosines. This information is found in the methylation
|
|
98 call field which can contain the following characters:
|
|
99
|
|
100 ::
|
|
101
|
|
102 ~~~ X for methylated C in CHG context (was protected) ~~~
|
|
103
|
|
104 ~~~ x for not methylated C CHG (was converted) ~~~
|
|
105
|
|
106 ~~~ H for methylated C in CHH context (was protected) ~~~
|
|
107
|
|
108 ~~~ h for not methylated C in CHH context (was converted) ~~~
|
|
109
|
|
110 ~~~ Z for methylated C in CpG context (was protected) ~~~
|
|
111
|
|
112 ~~~ z for not methylated C in CpG context (was converted) ~~~
|
|
113
|
|
114 ~~~ . for any bases not involving cytosines ~~~
|
|
115
|
|
116
|
|
117
|
|
118 -----
|
|
119
|
|
120 **Required Parameters**
|
|
121
|
|
122 ::
|
|
123
|
|
124 -s/--single-end Input file(s) are Bismark result file(s) generated from single-end
|
|
125 read data. Specifying either --single-end or --paired-end is
|
|
126 mandatory.
|
|
127
|
|
128 -p/--paired-end Input file(s) are Bismark result file(s) generated from paired-end
|
|
129 read data. Specifying either --paired-end or --single-end is
|
|
130 mandatory.
|
|
131
|
|
132 --no_overlap For paired-end reads it is theoretically possible that read_1 and
|
|
133 read_2 overlap. This option avoids scoring overlapping methylation
|
|
134 calls twice (only methylation calls of read 1 are used for in the process
|
|
135 since read 1 has historically higher quality basecalls than read 2).
|
|
136 Whilst this option removes a bias towards more methylation calls
|
|
137 in the center of sequenced fragments it may de facto remove a sizable
|
|
138 proportion of the data. This option is highly recommended for paired-end
|
|
139 data.
|
|
140
|
|
141 --report Prints out a short methylation summary as well as the paramaters used to run
|
|
142 this script.
|
|
143
|
|
144
|
|
145 -----
|
|
146
|
|
147 **Default Parameters**
|
|
148
|
|
149 ::
|
|
150
|
|
151 --bedGraph After finishing the methylation extraction, the methylation output is written into a
|
|
152 sorted bedGraph file that reports the position of a given cytosine and its methylation
|
|
153 state (in %, seem details below). The methylation extractor output is temporarily split up into
|
|
154 temporary files, one per chromosome (written into the current directory or folder
|
|
155 specified with -o/--output); these temp files are then used for sorting and deleted
|
|
156 afterwards. By default, only cytosines in CpG context will be sorted. The option
|
|
157 '--CX_context' may be used to report all cyosines irrespective of sequence context
|
|
158 (this will take MUCH longer!).
|
|
159
|
|
160
|
|
161
|
|
162 </help>
|
|
163 </tool>
|
|
164
|
|
165
|