Mercurial > repos > greg > meme_fimo

comparison fimo.xml @ 0:09098f34f445 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Wed, 23 Mar 2016 13:58:55 -0400
parents
children 1f221102ac4d
comparison
equal deleted inserted replaced
-1:000000000000 0:09098f34f445
1 <tool id="meme_fimo" name="FIMO" version="4.11.0.3">
2 <description>- Scan a set of sequences for motifs.</description>
3 <requirements>
4 <requirement type="package" version="6.9.3">imagemagick</requirement>
5 <requirement type="package" version="4.11.0">meme</requirement>
6 </requirements>
7 <command>
8 <![CDATA[
9 mkdir -p output &&
10 python $__tool_directory__/fimo_wrapper.py
11 --input_motifs "${input_motifs}"
12 #if str($fasta_type.fasta_type_selector) == 'history':
13 --input_fasta "${fasta_type.input_database}"
14 #else:
15 --input_fasta "${fasta_type.input_database.fields.path}"
16 #end if
17 --options_type $options_type.options_type_selector
18 #if str($options_type.options_type_selector) == 'advanced':
19 --alpha "${options_type.alpha}"
20 #if str($options_type.bgfile_type.bgfile_type_selector) == 'motif_file':
21 --bgfile "motif-file"
22 #elif str($options_type.bgfile_type.bgfile_type_selector) == 'bgfile':
23 --bgfile "${options_type.bgfile_type.bgfile}"
24 #end if
25 ${options_type.max_strand}
26 --max_stored_scores "${options_type.max_stored_scores}"
27 #if str($options_type.motifs_cond.motifs_selector) == 'no':
28 #for $motif in $options_type.motifs:
29 --motif "${motif.motif}"
30 #end for
31 #end if
32 --output_separate_motifs ${options_type.output_separate_motifs}
33 --motif_pseudo "${options_type.motif_pseudo}"
34 ${options_type.no_qvalue}
35 ${options_type.norc}
36 ${options_type.parse_genomic_coord_cond.parse_genomic_coord}
37 #if str($options_type.parse_genomic_coord_cond.parse_genomic_coord) == '--parse_genomic_coord':
38 --remove_duplicate_coords ${options_type.parse_genomic_coord_cond.remove_duplicate_coords}
39 #end if
40 #if str($options_type.psp_cond.psp_selector) == 'yes':
41 --input_psp "${input_psp}"
42 #end if
43 #if str($options_type.prior_dist_cond.prior_dist_selector) == 'yes':
44 --input_prior_dist "${input_prior_dist}"
45 #end if
46 ${options_type.qv_thresh}
47 --thresh ${options_type.thresh}
48 #end if
49 --output_path '${html_outfile.files_path}'
50 --html_output "${html_outfile}"
51 --interval_output '${interval_outfile}'
52 --txt_output "${txt_outfile}"
53 --xml_output "${xml_outfile}"
54 --gff_output "${gff_outfile}"
55 ]]>
56 </command>
57 <inputs>
58 <param name="input_motifs" type="data" format="memexml" label="'MEME output' formatted file"/>
59 <conditional name="fasta_type">
60 <param name="fasta_type_selector" type="select" label="Source for sequence to search">
61 <option value="cached">Locally Cached sequences</option>
62 <option value="history" selected="true">Sequences from your history</option>
63 </param>
64 <when value="cached">
65 <param name="input_database" type="select" label="Genome to search">
66 <options from_data_table="all_fasta" />
67 </param>
68 </when>
69 <when value="history">
70 <param format="fasta" name="input_database" type="data" label="Sequences"/>
71 </when>
72 </conditional>
73 <conditional name="options_type">
74 <param name="options_type_selector" type="select" label="Options configuration">
75 <option value="basic" selected="true">Basic</option>
76 <option value="advanced">Advanced</option>
77 </param>
78 <when value="basic" />
79 <when value="advanced">
80 <param name="alpha" type="float" value="1.0" min="0" max="1.0" label="Alpha parameter for calculating position specific priors" help="Represents the fraction of all transcription factor binding sites that are binding sites for the TF of interest (must be between 0 and 1)."/>
81 <conditional name="bgfile_type">
82 <param name="bgfile_type_selector" type="select" label="Background file type">
83 <option value="default" selected="true">Use frequencies embedded in the application from the non-redundant database</option>
84 <option value="motif_file">Use frequencies from motif file</option>
85 <option value="bgfile">Use frequencies from background file</option>
86 </param>
87 <when value="motif_file" />
88 <when value="default" />
89 <when value="bgfile">
90 <param name="bgfile" type="data" format="txt" optional="True" label="Background Model" help="File must be in MEME background file format."/>
91 </when>
92 </conditional>
93 <param name="max_strand" label="If matches on both strands at a given position satisfy the output threshold, only report the match for the strand with the higher score" type="boolean" truevalue="--max_strand" falsevalue="" checked="False" help="If the scores are tied, the matching strand is chosen at random. Leave unchecked to report both matches."/>
94 <param name="max_stored_scores" type="integer" value="100000" label="Maximum number of scores that will be stored" />
95 <conditional name="motifs_cond">
96 <param name="motifs_selector" type="select" label="Use all motifs in input?">
97 <option value="yes" selected="true">Yes</option>
98 <option value="no">No</option>
99 </param>
100 <when value="yes"/>
101 <when value="no">
102 <repeat name="motifs" title="Limit to specified motif">
103 <param name="motif" type="text" value="" label="Specify motif by id" />
104 </repeat>
105 </when>
106 </conditional>
107 <param name="output_separate_motifs" type="select" label="Output a dataset per motif?" help="Output a collection consisting of a separate dataset for each motif in the input">
108 <option value="no" selected="true">No</option>
109 <option value="yes">Yes</option>
110 </param>
111 <param name="motif_pseudo" type="float" value="0.1" label="Pseudocount to add to counts in motif matrix" help="A pseudocount to be added to each count in the motif matrix, after first multiplying by the corresponding background frequency"/>
112 <param name="no_qvalue" label="Do not compute a q-value for each p-value" type="boolean" truevalue="--no_qvalue" falsevalue="" checked="True" help="The q-value calculation is that of Benjamini and Hochberg (1995)."/>
113 <param name="norc" label="Do not score the reverse complement DNA strand" type="boolean" truevalue="--norc" falsevalue="" checked="False" />
114 <conditional name="parse_genomic_coord_cond">
115 <param name="parse_genomic_coord" label="Check each sequence header for UCSC style genomic coordinates" type="boolean" truevalue="--parse_genomic_coord" falsevalue="" checked="False" />
116 <when value="--parse_genomic_coord">
117 <param name="remove_duplicate_coords" type="select" label="Remove duplicate entries in unique GFF coordinates?" help="Remove duplicate entries as defined by the unique GFF coordinates">
118 <option value="no" selected="true">No</option>
119 <option value="yes">Yes</option>
120 </param>
121 </when>
122 <when value=""/>
123 </conditional>
124 <conditional name="psp_cond">
125 <param name="psp_selector" type="select" label="Use position-specific priors?">
126 <option value="no" selected="true">No</option>
127 <option value="yes">Yes</option>
128 </param>
129 <when value="no"/>
130 <when value="yes">
131 <param name="input_psp" type="data" format="txt" label="Select dataset containing position specific priors" help="Format must be meme psp or wiggle."/>
132 </when>
133 </conditional>
134 <conditional name="prior_dist_cond">
135 <param name="prior_dist_selector" type="select" label="Use binned distribution of priors?">
136 <option value="no" selected="true">No</option>
137 <option value="yes">Yes</option>
138 </param>
139 <when value="no"/>
140 <when value="yes">
141 <param name="input_prior_dist" type="data" format="txt" label="Select dataset containing binned distribution of priors"/>
142 </when>
143 </conditional>
144 <param name="qv_thresh" label="Use q-values for the output threshold" type="boolean" truevalue="--qv_thresh" falsevalue="" checked="False" help="Leave unchecked to use p-values for the output threshold."/>
145 <param name="thresh" type="float" value="1e-4" label="Output threshold for displaying search results" help="Only search results with a p-value less than the threshold will be output. The threshold can be set to use q-values rather than p-values via the option above."/>
146 </when>
147 </conditional>
148 <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False">
149 <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
150 </param>
151 </inputs>
152 <outputs>
153 <data format="html" name="html_outfile" label="${tool.name} on ${on_string} (html)">
154 <actions>
155 <conditional name="fasta_type.fasta_type_selector">
156 <when value="cached">
157 <action type="metadata" name="dbkey">
158 <option type="from_data_table" name="all_fasta" column="1" offset="0">
159 <filter type="param_value" column="0" value="seq" keep="True"/>
160 <filter type="param_value" ref="fasta_type.input_database" column="1"/>
161 </option>
162 </action>
163 </when>
164 </conditional>
165 </actions>
166 </data>
167 <data format="tabular" name="txt_outfile" label="${tool.name} on ${on_string} (text)">
168 <actions>
169 <conditional name="fasta_type.fasta_type_selector">
170 <when value="cached">
171 <action type="metadata" name="dbkey">
172 <option type="from_data_table" name="all_fasta" column="1" offset="0">
173 <filter type="param_value" ref="fasta_type.input_database" column="0"/>
174 </option>
175 </action>
176 </when>
177 </conditional>
178 </actions>
179 </data>
180 <data format="tabular" name="gff_outfile" label="${tool.name} on ${on_string} (almost-gff)">
181 <filter>options_type['output_separate_motifs'] == 'no'</filter>
182 <actions>
183 <conditional name="fasta_type.fasta_type_selector">
184 <when value="cached">
185 <action type="metadata" name="dbkey">
186 <option type="from_data_table" name="all_fasta" column="1" offset="0">
187 <filter type="param_value" ref="fasta_type.input_database" column="0"/>
188 </option>
189 </action>
190 </when>
191 </conditional>
192 </actions>
193 </data>
194 <collection name="motifs" type="list" label="Motifs: ${tool.name} on ${on_string}">
195 <discover_datasets pattern="(?P&lt;designation&gt;.*)" directory="output" ext="gff" visible="false" />
196 <filter>options_type['output_separate_motifs'] == 'yes'</filter>
197 </collection>
198 <data format="cisml" name="xml_outfile" label="${tool.name} on ${on_string} (xml)">
199 <actions>
200 <conditional name="fasta_type.fasta_type_selector">
201 <when value="cached">
202 <action type="metadata" name="dbkey">
203 <option type="from_data_table" name="all_fasta" column="1" offset="0">
204 <filter type="param_value" ref="fasta_type.input_database" column="0"/>
205 </option>
206 </action>
207 </when>
208 </conditional>
209 </actions>
210 </data>
211 <data format="interval" name="interval_outfile" label="${tool.name} on ${on_string} (interval)">
212 <actions>
213 <conditional name="fasta_type.fasta_type_selector">
214 <when value="cached">
215 <action type="metadata" name="dbkey">
216 <option type="from_data_table" name="all_fasta" column="1" offset="0">
217 <filter type="param_value" ref="fasta_type.input_database" column="0"/>
218 </option>
219 </action>
220 </when>
221 </conditional>
222 </actions>
223 </data>
224 </outputs>
225 <tests>
226 <test>
227 <param name="input_motifs" value="meme_output_xml_1.xml" ftype="memexml"/>
228 <param name="fasta_type_selector" value="history"/>
229 <param name="input_database" value="phiX.fasta" ftype="fasta"/>
230 <param name="options_type_selector" value="basic"/>
231 <param name="non_commercial_use" value="True"/>
232 <output name="html_outfile" file="fimo_output_html_1.html" compare="contains"/>
233 <output name="txt_outfile" file="fimo_output_txt_1.txt" compare="contains"/>
234 <output name="gff_outfile" file="fimo_output_almost-gff_1.txt" compare="contains"/>
235 <output name="xml_outfile" file="fimo_output_xml_1.xml" lines_diff="8"/>
236 <output name="interval_outfile" file="fimo_output_interval_1.txt" compare="contains"/>
237 </test>
238 <test>
239 <param name="input_motifs" value="meme_output_xml_1.xml" ftype="memexml"/>
240 <param name="fasta_type_selector" value="history"/>
241 <param name="input_database" value="phiX.fasta" ftype="fasta"/>
242 <param name="options_type_selector" value="advanced"/>
243 <param name="non_commercial_use" value="True"/>
244 <output name="html_outfile" file="fimo_output_html_2.html" compare="contains"/>
245 <output name="txt_outfile" file="fimo_output_txt_2.txt" compare="contains"/>
246 <output name="gff_outfile" file="fimo_output_almost-gff_2.txt" compare="contains"/>
247 <output name="xml_outfile" file="fimo_output_xml_2.xml" lines_diff="8"/>
248 <output name="interval_outfile" file="fimo_output_interval_2.txt" compare="contains"/>
249 </test>
250 <test>
251 <param name="input_motifs" value="meme_output_xml_1.xml" ftype="memexml"/>
252 <param name="fasta_type_selector" value="history"/>
253 <param name="input_database" value="phiX.fasta" ftype="fasta"/>
254 <param name="options_type_selector" value="advanced"/>
255 <param name="parse_genomic_coord" value="--parse_genomic_coord"/>
256 <param name="remove_duplicate_coords" value="yes"/>
257 <param name="output_separate_motifs" value="yes"/>
258 <param name="non_commercial_use" value="True"/>
259 <output name="html_outfile" file="fimo_output_html_2.html" compare="contains"/>
260 <output name="txt_outfile" file="fimo_output_txt_2.txt" compare="contains"/>
261 <output_collection name="motifs" type="list">
262 <element name="MOTIFS1.gff" file="fimo_output_almost-gff_2.txt" ftype="gff" compare="contains"/>
263 </output_collection>
264 <output name="xml_outfile" file="fimo_output_xml_2.xml" lines_diff="8"/>
265 <output name="interval_outfile" file="fimo_output_interval_2.txt" compare="contains"/>
266 </test>
267 </tests>
268 <help>
269
270 .. class:: warningmark
271
272 **WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted.
273 Before using, be sure to review, agree, and comply with the license.**
274
275 FIMO scans a sequence database for individual matches to each of the motifs you provide (sample output for motifs and sequences).
276 The name FIMO stands for 'Find Individual Motif Occurrences'. The program searches a database of sequences for occurrences of
277 known motifs, treating each motif independently. Motifs must be in MEME Motif Format. You can define the statistical threshold
278 (p-value) for motifs and whether FIMO scans just the given sequences or their reverse complements (where applicable).
279
280 .. class:: infomark
281
282 For detailed information on FIMO, click here_, or view the license_.
283
284 .. _here: http://meme-suite.org/doc/fimo.html?man_type=web
285 .. _license: http://meme-suite.org/doc/copyright.html?man_type=web
286
287 </help>
288 <citations>
289 <citation type="doi">10.1093/bioinformatics/btr064</citation>
290 </citations>
291 </tool>