Mercurial > repos > eiriche > bsmap

comparison bsmap.xml @ 18:765fe3947e2a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author eiriche
date Mon, 03 Dec 2012 02:38:16 -0500
parents
children
comparison
equal deleted inserted replaced
17:c5fc750e45ab 18:765fe3947e2a
1 <tool id="bsmap" name="BSMAP Mapper">
2 <requirements>
3 <requirement type='package' version="2.6">bsmap</requirement>
4 </requirements>
5 <command interpreter="bash">
6 bsmap_wrapper.sh
7 ##Reference genome
8 ##ref="${reference.fields.path}"
9 #if $refGenomeSource.genomeSource == "history":
10 ref="${refGenomeSource.myFile}"
11 #else
12 ref="${refGenomeSource.builtinFile.fields.path}"
13 #end if
14 ##Output files (SAM output, BSMAP summary)
15 mapped=$mapped
16 ##Temp directory
17 tempdir=$mapped.files_path
18 summary=$summary
19 #if str($singlePaired.sPaired) == "single":
20 library="single"
21 mate1=$singlePaired.sInput1
22 #if str($singlePaired.sParams.sSettingsType) == "full":
23 fullparam=true
24 qual=$singlePaired.sParams.qual
25 threshold=$singlePaired.sParams.threshold
26 lowqual=$singlePaired.sParams.lowqual
27 adapter=$singlePaired.sParams.adapter
28 firstn=$singlePaired.sParams.firstn
29 repeat_reads=$singlePaired.sParams.repeat_reads
30 seed_size=$singlePaired.sParams.seed_size
31 mismatch=$singlePaired.sParams.mismatch
32 equal_best=$singlePaired.sParams.equal_best
33 start=$singlePaired.sParams.start
34 end=$singlePaired.sParams.end
35 index_interval=$singlePaired.sParams.index_interval
36 seed_random=$singlePaired.sParams.seed_random
37 rrbs=$singlePaired.sParams.rrbs
38 mode=$singlePaired.sParams.mode
39 align_info=$singlePaired.sParams.align_info
40 #end if
41 #else:
42 library="paired"
43 mate1=$singlePaired.pInput1
44 mate2=$singlePaired.pInput2
45 unpaired=$unpaired
46 #if str($singlePaired.pParams.pSettingsType) == "full":
47 fullparam=true
48 qual=$singlePaired.pParams.qual
49 threshold=$singlePaired.pParams.threshold
50 lowqual=$singlePaired.pParams.lowqual
51 adapter=$singlePaired.pParams.adapter
52 firstn=$singlePaired.pParams.firstn
53 repeat_reads=$singlePaired.pParams.repeat_reads
54 seed_size=$singlePaired.pParams.seed_size
55 mismatch=$singlePaired.pParams.mismatch
56 equal_best=$singlePaired.pParams.equal_best
57 start=$singlePaired.pParams.start
58 end=$singlePaired.pParams.end
59 index_interval=$singlePaired.pParams.index_interval
60 seed_random=$singlePaired.pParams.seed_random
61 rrbs=$singlePaired.pParams.rrbs
62 mode=$singlePaired.pParams.mode
63 align_info=$singlePaired.pParams.align_info
64 maxinsert=$singlePaired.pParams.maxinsert
65 mininsert=$singlePaired.pParams.mininsert
66 #end if
67 #end if
68 </command>
69 <inputs>
70
71 <conditional name="refGenomeSource">
72 <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in reference?">
73 <option value="builtin">Use a built-in reference</option>
74 <option value="history">Use one from the history</option>
75 </param>
76 <when value="builtin">
77 <param name="builtinFile" type="select" label="Select the reference genome">
78 <options from_data_table="bsmap_fasta">
79 <filter type="sort_by" column="2" />
80 <validator type="no_options" message="No reference genomes are available" />
81 </options>
82 </param>
83 </when>
84 <when value="history">
85 <param name="myFile" type="data" format="fasta" label="Select the reference genome" />
86 </when>
87 </conditional>
88
89 <conditional name="singlePaired">
90 <param name="sPaired" type="select" label="Is this library mate-paired?">
91 <option value="single">Single-end</option>
92 <option value="paired">Paired-end</option>
93 </param>
94 <when value="single">
95 <param name="sInput1" type="data" format="fastq,fasta" label="FASTQ file" help="Must have ASCII encoded quality scores"/>
96 <conditional name="sParams">
97 <param name="sSettingsType" type="select" label="BSMAP settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list">
98 <option value="preSet">Commonly used</option>
99 <option value="full">Full parameter list</option>
100 </param>
101 <when value="preSet" />
102 <when value="full">
103 <param name="qual" type="select" label="Select the type of FastQ qualities">
104 <option value="33">phred33-quals</option>
105 <option value="64">phred64-quals</option>
106 </param>
107 <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" />
108 <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" />
109 <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" />
110 <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" />
111
112 <param name="repeat_reads" type="select" label="How to report repeat hits">
113 <option value="0">none(unique hit only)</option>
114 <option value="1">random one</option>
115 </param>
116
117 <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" />
118 <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" />
119 <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" />
120 <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" />
121 <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" />
122 <param name="index_interval" type="integer" value="4" label="Index interval" />
123 <param name="seed_random" type="integer" value="-1" label="Seed for random number generation used in selecting multiple hits" help="other seed values generate pseudo random number based on read index number, to allow reproducible mapping results" />
124 <param name="rrbs" type="text" value="none" label="Activating RRBS mapping mode and set restriction enzyme digestion sites" help="digestion position marked by '-', example: -D C-CGG for MspI digestion. default: none (whole genome shotgun bisulfite mapping mode)" />
125 <param name="mode" type="select" label="Set mapping strand information">
126 <option value="0">only map to 2 forward strands</option>
127 <option value="1">map SE or PE reads to all 4 strands</option>
128 </param>
129 <param name="align_info" type="text" value="none" label="Set alignment information for the additional nucleotide transition" help="is in the form of two different nucleotides N1N2,indicating N1 in the reads could be mapped to N2 in the reference sequences. default: -M TC, corresponds to C=>U(T) transition in bisulfite conversion. example: -M GA could be used to detect A=>I(G) transition in RNA editing." />
130 </when> <!-- full -->
131 </conditional> <!-- sParams -->
132 </when> <!-- single -->
133
134 <when value="paired">
135 <param name="pInput1" type="data" format="fastq,fasta" label="Forward FASTQ file" />
136 <param name="pInput2" type="data" format="fastq,fasta" label="Reverse FASTQ file" />
137
138 <conditional name="pParams">
139 <param name="pSettingsType" type="select" label="BSMAP settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list">
140 <option value="preSet">Commonly used</option>
141 <option value="full">Full parameter list</option>
142 </param>
143 <when value="preSet" />
144 <when value="full">
145 <param name="qual" type="select" label="Select the type of FastQ qualities">
146 <option value="33">phred33-quals</option>
147 <option value="64">phred64-quals</option>
148 </param>
149
150 <param name="mininsert" type="integer" value="28" label="Minimal insert size allowed" />
151 <param name="maxinsert" type="integer" value="500" label="Maximal insert size allowed" />
152
153 <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" />
154 <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" />
155 <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" />
156 <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" />
157
158 <param name="repeat_reads" type="select" label="How to report repeat hits">
159 <option value="0">none(unique hit only)</option>
160 <option value="1">random one</option>
161 </param>
162
163 <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" />
164 <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" />
165 <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" />
166 <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" />
167 <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" />
168 <param name="index_interval" type="integer" value="4" label="Index interval" />
169 <param name="seed_random" type="integer" value="-1" label="Seed for random number generation used in selecting multiple hits" help="other seed values generate pseudo random number based on read index number, to allow reproducible mapping results" />
170 <param name="rrbs" type="text" value="none" label="Activating RRBS mapping mode and set restriction enzyme digestion sites" help="digestion position marked by '-', example: -D C-CGG for MspI digestion. default: none (whole genome shotgun bisulfite mapping mode)" />
171 <param name="mode" type="select" label="Set mapping strand information">
172 <option value="0">only map to 2 forward strands</option>
173 <option value="1">map SE or PE reads to all 4 strands</option>
174 </param>
175 <param name="align_info" type="text" value="none" label="Set alignment information for the additional nucleotide transition" help="is in the form of two different nucleotides N1N2,indicating N1 in the reads could be mapped to N2 in the reference sequences. default: -M TC, corresponds to C=>U(T) transition in bisulfite conversion. example: -M GA could be used to detect A=>I(G) transition in RNA editing." />
176
177
178 </when> <!-- full -->
179 </conditional> <!-- pParams -->
180 </when> <!-- paired -->
181 </conditional> <!-- singlePaired -->
182
183
184 </inputs>
185 <outputs>
186 <data name="mapped" format="sam" label="BSMAP Mapped Reads" />
187 <data name="summary" format="txt" label="BSMAP Mapping Summary" />
188 <data name="unpaired" format ="sam" label="BSMAP Unpaired Hits">
189 <filter>(singlePaired['sPaired'] == 'paired')</filter>
190 </data>
191
192 </outputs>
193 <help>
194 **What it does**
195
196 BSMAP is a short reads mapping software for bisulfite sequencing reads. It has the following features:
197
198 - read length up to 144 nt, allow up to 15 mismatches, gap size up to 3 bp.
199
200 - support single end and pair end mapping. support multi-thread mapping.
201
202 - support both "Lister protocol" (sequence 2 forward strands only) and "Cokus protocol" (sequence all 4 bisulfite converted strands)
203
204 - reads are directly mapped to original reference genome sequence, no need to preprocess the reads and reference genome to convert C to T.
205
206 - support both whole genome bisulfite sequencing (WGBS) mode and reduced representation bisulfite sequencing (RRBS) mode, allow changing the digestion site information to support different digestion enzymes for RRBS.
207
208 - allow trimming adapter sequences and low quality nucleotides from the 3'end of reads
209
210 - allow trade off between speed/memory usage/mapping sensitivity. For human genome, the RRBS mode uses ~3GB. In WGBS mode, the typical memory usage is ~9GB, but can be as low as 5GB.
211
212 - allow alignment for other nucleotide transitions, for example, can be set to detect the A=>I(G) transition in RNA editing.
213
214 .. _BSMAP: http://code.google.com/p/bsmap/
215
216 **Input formats**
217
218 BSMAP accepts files in FASTA/FASTQ format.
219
220 **Outputs**
221
222 The output contains the following files:
223
224 - mapped reads in SAM format
225
226 - mapping summary
227
228 - unpaired hits (only for paired-end mapping)
229
230 </help>
231
232 <tests>
233 </tests>
234 </tool>
235