Mercurial > repos > eiriche > bsmap
comparison bsmap.xml @ 0:b35020882aad draft
Uploaded
author | eiriche |
---|---|
date | Thu, 29 Nov 2012 10:09:10 -0500 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:b35020882aad |
---|---|
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="${reference.fields.path}" | |
11 ##Output files (SAM output, BSMAP summary) | |
12 mapped=$mapped | |
13 ##Temp directory | |
14 tempdir=$mapped.files_path | |
15 summary=$summary | |
16 #if str($singlePaired.sPaired) == "single": | |
17 library="single" | |
18 mate1=$singlePaired.sInput1 | |
19 #if str($singlePaired.sParams.sSettingsType) == "full": | |
20 fullparam=true | |
21 qual=$singlePaired.sParams.qual | |
22 threshold=$singlePaired.sParams.threshold | |
23 lowqual=$singlePaired.sParams.lowqual | |
24 adapter=$singlePaired.sParams.adapter | |
25 firstn=$singlePaired.sParams.firstn | |
26 repeat_reads=$singlePaired.sParams.repeat_reads | |
27 seed_size=$singlePaired.sParams.seed_size | |
28 mismatch=$singlePaired.sParams.mismatch | |
29 equal_best=$singlePaired.sParams.equal_best | |
30 start=$singlePaired.sParams.start | |
31 end=$singlePaired.sParams.end | |
32 index_interval=$singlePaired.sParams.index_interval | |
33 seed_random=$singlePaired.sParams.seed_random | |
34 rrbs=$singlePaired.sParams.rrbs | |
35 mode=$singlePaired.sParams.mode | |
36 align_info=$singlePaired.sParams.align_info | |
37 #end if | |
38 #else: | |
39 library="paired" | |
40 mate1=$singlePaired.pInput1 | |
41 mate2=$singlePaired.pInput2 | |
42 unpaired=$unpaired | |
43 #if str($singlePaired.pParams.pSettingsType) == "full": | |
44 fullparam=true | |
45 qual=$singlePaired.pParams.qual | |
46 threshold=$singlePaired.pParams.threshold | |
47 lowqual=$singlePaired.pParams.lowqual | |
48 adapter=$singlePaired.pParams.adapter | |
49 firstn=$singlePaired.pParams.firstn | |
50 repeat_reads=$singlePaired.pParams.repeat_reads | |
51 seed_size=$singlePaired.pParams.seed_size | |
52 mismatch=$singlePaired.pParams.mismatch | |
53 equal_best=$singlePaired.pParams.equal_best | |
54 start=$singlePaired.pParams.start | |
55 end=$singlePaired.pParams.end | |
56 index_interval=$singlePaired.pParams.index_interval | |
57 seed_random=$singlePaired.pParams.seed_random | |
58 rrbs=$singlePaired.pParams.rrbs | |
59 mode=$singlePaired.pParams.mode | |
60 align_info=$singlePaired.pParams.align_info | |
61 maxinsert=$singlePaired.pParams.maxinsert | |
62 mininsert=$singlePaired.pParams.mininsert | |
63 #end if | |
64 #end if | |
65 </command> | |
66 <inputs> | |
67 <param name="reference" type="select" label="Select a reference genome"> | |
68 <options from_data_table="all_fasta"> | |
69 <filter type="sort_by" column="2" /> | |
70 <validator type="no_options" message="No reference genomes are available" /> | |
71 </options> | |
72 </param> | |
73 | |
74 <conditional name="singlePaired"> | |
75 <param name="sPaired" type="select" label="Is this library mate-paired?"> | |
76 <option value="single">Single-end</option> | |
77 <option value="paired">Paired-end</option> | |
78 </param> | |
79 <when value="single"> | |
80 <param name="sInput1" type="data" format="fastq,fasta" label="FASTQ file" help="Must have ASCII encoded quality scores"/> | |
81 <conditional name="sParams"> | |
82 <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"> | |
83 <option value="preSet">Commonly used</option> | |
84 <option value="full">Full parameter list</option> | |
85 </param> | |
86 <when value="preSet" /> | |
87 <when value="full"> | |
88 <param name="qual" type="select" label="Select the type of FastQ qualities"> | |
89 <option value="33">phred33-quals</option> | |
90 <option value="64">phred64-quals</option> | |
91 </param> | |
92 <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" /> | |
93 <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" /> | |
94 <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" /> | |
95 <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" /> | |
96 | |
97 <param name="repeat_reads" type="select" label="How to report repeat hits"> | |
98 <option value="0">none(unique hit only)</option> | |
99 <option value="1">random one</option> | |
100 </param> | |
101 | |
102 <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" /> | |
103 <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" /> | |
104 <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" /> | |
105 <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" /> | |
106 <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" /> | |
107 <param name="index_interval" type="integer" value="4" label="Index interval" /> | |
108 <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" /> | |
109 <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)" /> | |
110 <param name="mode" type="select" label="Set mapping strand information"> | |
111 <option value="0">only map to 2 forward strands</option> | |
112 <option value="1">map SE or PE reads to all 4 strands</option> | |
113 </param> | |
114 <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." /> | |
115 </when> <!-- full --> | |
116 </conditional> <!-- sParams --> | |
117 </when> <!-- single --> | |
118 | |
119 <when value="paired"> | |
120 <param name="pInput1" type="data" format="fastq,fasta" label="Forward FASTQ file" /> | |
121 <param name="pInput2" type="data" format="fastq,fasta" label="Reverse FASTQ file" /> | |
122 | |
123 <conditional name="pParams"> | |
124 <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"> | |
125 <option value="preSet">Commonly used</option> | |
126 <option value="full">Full parameter list</option> | |
127 </param> | |
128 <when value="preSet" /> | |
129 <when value="full"> | |
130 <param name="qual" type="select" label="Select the type of FastQ qualities"> | |
131 <option value="33">phred33-quals</option> | |
132 <option value="64">phred64-quals</option> | |
133 </param> | |
134 | |
135 <param name="mininsert" type="integer" value="28" label="Minimal insert size allowed" /> | |
136 <param name="maxinsert" type="integer" value="500" label="Maximal insert size allowed" /> | |
137 | |
138 <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" /> | |
139 <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" /> | |
140 <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" /> | |
141 <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" /> | |
142 | |
143 <param name="repeat_reads" type="select" label="How to report repeat hits"> | |
144 <option value="0">none(unique hit only)</option> | |
145 <option value="1">random one</option> | |
146 </param> | |
147 | |
148 <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" /> | |
149 <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" /> | |
150 <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" /> | |
151 <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" /> | |
152 <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" /> | |
153 <param name="index_interval" type="integer" value="4" label="Index interval" /> | |
154 <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" /> | |
155 <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)" /> | |
156 <param name="mode" type="select" label="Set mapping strand information"> | |
157 <option value="0">only map to 2 forward strands</option> | |
158 <option value="1">map SE or PE reads to all 4 strands</option> | |
159 </param> | |
160 <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." /> | |
161 | |
162 | |
163 </when> <!-- full --> | |
164 </conditional> <!-- pParams --> | |
165 </when> <!-- paired --> | |
166 </conditional> <!-- singlePaired --> | |
167 | |
168 | |
169 </inputs> | |
170 <outputs> | |
171 <data name="mapped" format="sam" label="BSMAP Mapped Reads"> | |
172 <actions> | |
173 <action type="metadata" name="dbkey"> | |
174 <option type="from_data_table" name="bsmap_fasta" column="1" offset="0"> | |
175 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> | |
176 <filter type="param_value" ref="reference" column="0"/> | |
177 </option> | |
178 </action> | |
179 </actions> | |
180 </data> | |
181 <data name="summary" format="txt" label="BSMAP Mapping Summary" /> | |
182 <data name="unpaired" format ="sam" label="BSMAP Unpaired Hits"> | |
183 <filter>(singlePaired['sPaired'] == 'paired')</filter> | |
184 </data> | |
185 | |
186 </outputs> | |
187 <help> | |
188 **What it does** | |
189 | |
190 BSMAP is a short reads mapping software for bisulfite sequencing reads. It has the following features: | |
191 | |
192 - read length up to 144 nt, allow up to 15 mismatches, gap size up to 3 bp. | |
193 | |
194 - support single end and pair end mapping. support multi-thread mapping. | |
195 | |
196 - support both "Lister protocol" (sequence 2 forward strands only) and "Cokus protocol" (sequence all 4 bisulfite converted strands) | |
197 | |
198 - reads are directly mapped to original reference genome sequence, no need to preprocess the reads and reference genome to convert C to T. | |
199 | |
200 - 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. | |
201 | |
202 - allow trimming adapter sequences and low quality nucleotides from the 3'end of reads | |
203 | |
204 - 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. | |
205 | |
206 - allow alignment for other nucleotide transitions, for example, can be set to detect the A=>I(G) transition in RNA editing. | |
207 | |
208 .. _BSMAP: http://code.google.com/p/bsmap/ | |
209 | |
210 **Input formats** | |
211 | |
212 BSMAP accepts files in FASTA/FASTQ format. | |
213 | |
214 **Outputs** | |
215 | |
216 The output contains the following files: | |
217 | |
218 - mapped reads in SAM format | |
219 | |
220 - mapping summary | |
221 | |
222 - unpaired hits (only for paired-end mapping) | |
223 | |
224 </help> | |
225 | |
226 <tests> | |
227 <test> | |
228 <param name="sPaired" value="single" /> | |
229 <param name="indices" value="bismark" /> | |
230 <param name="sInput1" ftype="fastq" value="bismark_test_single.fastq" /> | |
231 <param name="sParams" value="preSet" /> | |
232 <output name="mapped" ftype="SAM" file="bismark_result_single_1.SAM" /> | |
233 <ouput name="summary" ftype="txt" file="bismark_result_single_2.txt" /> | |
234 </test> | |
235 </tests> | |
236 </tool> | |
237 |