comparison bsmap.xml @ 11:413c742682f7 draft

Uploaded
author eiriche
date Fri, 30 Nov 2012 09:14:33 -0500
parents
children
comparison
equal deleted inserted replaced
10:4f9b7eaecbd4 11:413c742682f7
1 <tool id="bsmap" name="BSMAP Mapper">
2 <requirements>
3 <requirement type='package'>
4 bsmap
5 </requirement>
6 </requirements>
7 <command interpreter="bash">
8 bsmap_wrapper.sh
9 ##Reference genome
10 ##ref="${reference.fields.path}"
11 #if $refGenomeSource.genomeSource == "history":
12 ref="${refGenomeSource.myFile}"
13 #else
14 ref="${refGenomeSource.builtinFile.fields.path}"
15 #end if
16 ##Output files (SAM output, BSMAP summary)
17 mapped=$mapped
18 ##Temp directory
19 tempdir=$mapped.files_path
20 summary=$summary
21 #if str($singlePaired.sPaired) == "single":
22 library="single"
23 mate1=$singlePaired.sInput1
24 #if str($singlePaired.sParams.sSettingsType) == "full":
25 fullparam=true
26 qual=$singlePaired.sParams.qual
27 threshold=$singlePaired.sParams.threshold
28 lowqual=$singlePaired.sParams.lowqual
29 adapter=$singlePaired.sParams.adapter
30 firstn=$singlePaired.sParams.firstn
31 repeat_reads=$singlePaired.sParams.repeat_reads
32 seed_size=$singlePaired.sParams.seed_size
33 mismatch=$singlePaired.sParams.mismatch
34 equal_best=$singlePaired.sParams.equal_best
35 start=$singlePaired.sParams.start
36 end=$singlePaired.sParams.end
37 index_interval=$singlePaired.sParams.index_interval
38 seed_random=$singlePaired.sParams.seed_random
39 rrbs=$singlePaired.sParams.rrbs
40 mode=$singlePaired.sParams.mode
41 align_info=$singlePaired.sParams.align_info
42 #end if
43 #else:
44 library="paired"
45 mate1=$singlePaired.pInput1
46 mate2=$singlePaired.pInput2
47 unpaired=$unpaired
48 #if str($singlePaired.pParams.pSettingsType) == "full":
49 fullparam=true
50 qual=$singlePaired.pParams.qual
51 threshold=$singlePaired.pParams.threshold
52 lowqual=$singlePaired.pParams.lowqual
53 adapter=$singlePaired.pParams.adapter
54 firstn=$singlePaired.pParams.firstn
55 repeat_reads=$singlePaired.pParams.repeat_reads
56 seed_size=$singlePaired.pParams.seed_size
57 mismatch=$singlePaired.pParams.mismatch
58 equal_best=$singlePaired.pParams.equal_best
59 start=$singlePaired.pParams.start
60 end=$singlePaired.pParams.end
61 index_interval=$singlePaired.pParams.index_interval
62 seed_random=$singlePaired.pParams.seed_random
63 rrbs=$singlePaired.pParams.rrbs
64 mode=$singlePaired.pParams.mode
65 align_info=$singlePaired.pParams.align_info
66 maxinsert=$singlePaired.pParams.maxinsert
67 mininsert=$singlePaired.pParams.mininsert
68 #end if
69 #end if
70 </command>
71 <inputs>
72
73 <conditional name="refGenomeSource">
74 <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in reference?">
75 <option value="builtin">Use a built-in reference</option>
76 <option value="history">Use one from the history</option>
77 </param>
78 <when value="builtin">
79 <param name="builtinFile" type="select" label="Select the reference genome">
80 <options from_data_table="bsmap_fasta">
81 <filter type="sort_by" column="2" />
82 <validator type="no_options" message="No reference genomes are available" />
83 </options>
84 </param>
85 </when>
86 <when value="history">
87 <param name="myFile" type="data" format="fasta" label="Select the reference genome" />
88 </when>
89 </conditional>
90
91 <conditional name="singlePaired">
92 <param name="sPaired" type="select" label="Is this library mate-paired?">
93 <option value="single">Single-end</option>
94 <option value="paired">Paired-end</option>
95 </param>
96 <when value="single">
97 <param name="sInput1" type="data" format="fastq,fasta" label="FASTQ file" help="Must have ASCII encoded quality scores"/>
98 <conditional name="sParams">
99 <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">
100 <option value="preSet">Commonly used</option>
101 <option value="full">Full parameter list</option>
102 </param>
103 <when value="preSet" />
104 <when value="full">
105 <param name="qual" type="select" label="Select the type of FastQ qualities">
106 <option value="33">phred33-quals</option>
107 <option value="64">phred64-quals</option>
108 </param>
109 <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" />
110 <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" />
111 <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" />
112 <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" />
113
114 <param name="repeat_reads" type="select" label="How to report repeat hits">
115 <option value="0">none(unique hit only)</option>
116 <option value="1">random one</option>
117 </param>
118
119 <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" />
120 <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" />
121 <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" />
122 <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" />
123 <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" />
124 <param name="index_interval" type="integer" value="4" label="Index interval" />
125 <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" />
126 <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)" />
127 <param name="mode" type="select" label="Set mapping strand information">
128 <option value="0">only map to 2 forward strands</option>
129 <option value="1">map SE or PE reads to all 4 strands</option>
130 </param>
131 <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." />
132 </when> <!-- full -->
133 </conditional> <!-- sParams -->
134 </when> <!-- single -->
135
136 <when value="paired">
137 <param name="pInput1" type="data" format="fastq,fasta" label="Forward FASTQ file" />
138 <param name="pInput2" type="data" format="fastq,fasta" label="Reverse FASTQ file" />
139
140 <conditional name="pParams">
141 <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">
142 <option value="preSet">Commonly used</option>
143 <option value="full">Full parameter list</option>
144 </param>
145 <when value="preSet" />
146 <when value="full">
147 <param name="qual" type="select" label="Select the type of FastQ qualities">
148 <option value="33">phred33-quals</option>
149 <option value="64">phred64-quals</option>
150 </param>
151
152 <param name="mininsert" type="integer" value="28" label="Minimal insert size allowed" />
153 <param name="maxinsert" type="integer" value="500" label="Maximal insert size allowed" />
154
155 <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" />
156 <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" />
157 <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" />
158 <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" />
159
160 <param name="repeat_reads" type="select" label="How to report repeat hits">
161 <option value="0">none(unique hit only)</option>
162 <option value="1">random one</option>
163 </param>
164
165 <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" />
166 <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" />
167 <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" />
168 <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" />
169 <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" />
170 <param name="index_interval" type="integer" value="4" label="Index interval" />
171 <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" />
172 <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)" />
173 <param name="mode" type="select" label="Set mapping strand information">
174 <option value="0">only map to 2 forward strands</option>
175 <option value="1">map SE or PE reads to all 4 strands</option>
176 </param>
177 <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." />
178
179
180 </when> <!-- full -->
181 </conditional> <!-- pParams -->
182 </when> <!-- paired -->
183 </conditional> <!-- singlePaired -->
184
185
186 </inputs>
187 <outputs>
188 <data name="mapped" format="sam" label="BSMAP Mapped Reads" />
189 <data name="summary" format="txt" label="BSMAP Mapping Summary" />
190 <data name="unpaired" format ="sam" label="BSMAP Unpaired Hits">
191 <filter>(singlePaired['sPaired'] == 'paired')</filter>
192 </data>
193
194 </outputs>
195 <help>
196 **What it does**
197
198 BSMAP is a short reads mapping software for bisulfite sequencing reads. It has the following features:
199
200 - read length up to 144 nt, allow up to 15 mismatches, gap size up to 3 bp.
201
202 - support single end and pair end mapping. support multi-thread mapping.
203
204 - support both "Lister protocol" (sequence 2 forward strands only) and "Cokus protocol" (sequence all 4 bisulfite converted strands)
205
206 - reads are directly mapped to original reference genome sequence, no need to preprocess the reads and reference genome to convert C to T.
207
208 - 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.
209
210 - allow trimming adapter sequences and low quality nucleotides from the 3'end of reads
211
212 - 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.
213
214 - allow alignment for other nucleotide transitions, for example, can be set to detect the A=>I(G) transition in RNA editing.
215
216 .. _BSMAP: http://code.google.com/p/bsmap/
217
218 **Input formats**
219
220 BSMAP accepts files in FASTA/FASTQ format.
221
222 **Outputs**
223
224 The output contains the following files:
225
226 - mapped reads in SAM format
227
228 - mapping summary
229
230 - unpaired hits (only for paired-end mapping)
231
232 </help>
233
234 <tests>
235 </tests>
236 </tool>
237