|
0
|
1 <?xml version="1.0"?>
|
|
|
2 <tool id="cwpair2" name="CWPair2" version="@WRAPPER_VERSION@.0">
|
|
|
3 <description>find matched pairs and unmatched orphans</description>
|
|
|
4 <macros>
|
|
|
5 <import>cwpair2_macros.xml</import>
|
|
|
6 </macros>
|
|
|
7 <expand macro="requirements" />
|
|
|
8 <command>
|
|
|
9 <![CDATA[
|
|
|
10 python $__tool_directory__/cwpair2.py
|
|
|
11 #for $i in $input:
|
|
|
12 --input "${i}" "${i.hid}"
|
|
|
13 #end for
|
|
|
14 --method $method
|
|
|
15 --up_distance $up_distance
|
|
|
16 --down_distance $down_distance
|
|
|
17 --binsize $binsize
|
|
|
18 --threshold_format $threshold_format_cond.threshold_format
|
|
|
19 #if str($threshold_format_cond.threshold_format) == "absolute_threshold":
|
|
|
20 --absolute_threshold $threshold_format_cond.absolute_threshold
|
|
|
21 #elif str($threshold_format_cond.threshold_format) == "relative_threshold":
|
|
|
22 --relative_threshold $threshold_format_cond.relative_threshold
|
|
|
23 #end if
|
|
4
|
24 --output_files $output_files
|
|
0
|
25 --sort_chromosome $sort_chromosome
|
|
|
26 --sort_score $sort_score
|
|
|
27 --statistics_output "$statistics_output"
|
|
|
28 ]]>
|
|
|
29 </command>
|
|
|
30 <inputs>
|
|
|
31 <param name="input" type="data" format="gff" multiple="True" label="Find matched pairs on" />
|
|
|
32 <param name="method" type="select" label="Method of finding a match">
|
|
|
33 <option value="mode" selected="True">Mode</option>
|
|
|
34 <option value="closest">Closest</option>
|
|
|
35 <option value="largest">Largest</option>
|
|
|
36 <option value="all">All</option>
|
|
|
37 </param>
|
|
|
38 <param name="up_distance" type="integer" value="50" min="0" label="Distance upstream from a peak to allow a pair" />
|
|
|
39 <param name="down_distance" type="integer" value="100" min="0" label="Distance downstream from a peak to allow a pair" />
|
|
|
40 <param name="binsize" type="integer" value="1" min="0" label="Width of bins for frequency plots and mode calculation" help="Value 1 implies no bins" />
|
|
|
41 <conditional name="threshold_format_cond">
|
|
|
42 <param name="threshold_format" type="select" label="Filter using">
|
|
|
43 <option value="relative_threshold" selected="True">Relative threshold</option>
|
|
|
44 <option value="absolute_threshold">Absolute threshold</option>
|
|
|
45 </param>
|
|
|
46 <when value="relative_threshold">
|
|
|
47 <param name="relative_threshold" type="float" value="0.0" min="0.0" label="Percentage of the 95 percentile value to filter below" help="Value 0 results in no filtering" />
|
|
|
48 </when>
|
|
|
49 <when value="absolute_threshold">
|
|
|
50 <param name="absolute_threshold" type="float" value="0.0" min="0.0" label="Absolute value to filter below" />
|
|
|
51 </when>
|
|
|
52 </conditional>
|
|
4
|
53 <param name="output_files" type="select" label="Restrict output to" help="Statistics will always be generated." >
|
|
|
54 <option value="simple" selected="True">matched pairs only (S)</option>
|
|
|
55 <option value="simple_orphan">matched pairs and orphans only (O,S)</option>
|
|
|
56 <option value="simple_orphan_detail">matched pairs, orphans and details only (D,O,S)</option>
|
|
|
57 <option value="all">no restrictions (output everything: C,D,F,O,P,S)</option>
|
|
|
58 </param>
|
|
0
|
59 <param name="sort_chromosome" type="select" label="Sort output by chromosomes in" help="Chromosome strings that are not numeric will not be sorted" >
|
|
|
60 <option value="asc" selected="True">ascending order</option>
|
|
|
61 <option value="desc">descending order</option>
|
|
|
62 </param>
|
|
|
63 <param name="sort_score" type="select" label="Sort output by score?">
|
|
|
64 <option value="no" selected="True">No</option>
|
|
|
65 <option value="asc">Yes, in ascending order</option>
|
|
|
66 <option value="desc">Yes, in descending order</option>
|
|
|
67 </param>
|
|
|
68 </inputs>
|
|
|
69 <outputs>
|
|
|
70 <collection name="closest_C_pdf" type="list" label="closest C: ${tool.name} on ${on_string}">
|
|
4
|
71 <filter>output_files == "all" and method in ["all", "closest"]</filter>
|
|
0
|
72 <discover_datasets pattern="(?P<designation>.*)" directory="closest_C" ext="pdf" visible="false" />
|
|
|
73 </collection>
|
|
|
74 <collection name="largest_C_pdf" type="list" label="largest C: ${tool.name} on ${on_string}">
|
|
4
|
75 <filter>output_files == "all" and method in ["all", "largest"]</filter>
|
|
0
|
76 <discover_datasets pattern="(?P<designation>.*)" directory="largest_C" ext="pdf" visible="false" />
|
|
|
77 </collection>
|
|
|
78 <collection name="mode_C_pdf" type="list" label="mode C: ${tool.name} on ${on_string}">
|
|
4
|
79 <filter>output_files == "all" and method in ["all", "mode"]</filter>
|
|
0
|
80 <discover_datasets pattern="(?P<designation>.*)" directory="mode_C" ext="pdf" visible="false" />
|
|
|
81 </collection>
|
|
|
82 <collection name="closest_D" type="list" label="closest D: ${tool.name} on ${on_string}">
|
|
4
|
83 <filter>output_files in ["all", "simple_orphan_detail"] and method in ["all", "closest"]</filter>
|
|
0
|
84 <discover_datasets pattern="(?P<designation>.*)" directory="closest_D" ext="tabular" visible="false" />
|
|
|
85 </collection>
|
|
|
86 <collection name="largest_D" type="list" label="largest D: ${tool.name} on ${on_string}">
|
|
4
|
87 <filter>output_files in ["all", "simple_orphan_detail"] and method in ["all", "largest"]</filter>
|
|
0
|
88 <discover_datasets pattern="(?P<designation>.*)" directory="largest_D" ext="tabular" visible="false" />
|
|
|
89 </collection>
|
|
|
90 <collection name="mode_D" type="list" label="mode D: ${tool.name} on ${on_string}">
|
|
4
|
91 <filter>output_files in ["all", "simple_orphan_detail"] and method in ["all", "mode"]</filter>
|
|
0
|
92 <discover_datasets pattern="(?P<designation>.*)" directory="mode_D" ext="tabular" visible="false" />
|
|
|
93 </collection>
|
|
|
94 <collection name="closest_F_pdf" type="list" label="closest F: ${tool.name} on ${on_string}">
|
|
4
|
95 <filter>output_files == "all" and method in ["all", "closest"]</filter>
|
|
0
|
96 <discover_datasets pattern="(?P<designation>.*)" directory="closest_F" ext="pdf" visible="false" />
|
|
|
97 </collection>
|
|
|
98 <collection name="largest_F_pdf" type="list" label="largest F: ${tool.name} on ${on_string}">
|
|
4
|
99 <filter>output_files == "all" and method in ["all", "largest"]</filter>
|
|
0
|
100 <discover_datasets pattern="(?P<designation>.*)" directory="largest_F" ext="pdf" visible="false" />
|
|
|
101 </collection>
|
|
|
102 <collection name="mode_F_pdf" type="list" label="mode F: ${tool.name} on ${on_string}">
|
|
4
|
103 <filter>output_files == "all" and method in ["all", "mode"]</filter>
|
|
0
|
104 <discover_datasets pattern="(?P<designation>.*)" directory="mode_F" ext="pdf" visible="false" />
|
|
|
105 </collection>
|
|
|
106 <collection name="closest_O" type="list" label="closest O: ${tool.name} on ${on_string}">
|
|
4
|
107 <filter>output_files in ["all", "simple_orphan", "simple_orphan_detail"] and method in ["all", "closest"]</filter>
|
|
0
|
108 <discover_datasets pattern="(?P<designation>.*)" directory="closest_O" ext="tabular" visible="false" />
|
|
|
109 </collection>
|
|
|
110 <collection name="largest_O" type="list" label="largest O: ${tool.name} on ${on_string}">
|
|
4
|
111 <filter>output_files in ["all", "simple_orphan", "simple_orphan_detail"] and method in ["all", "largest"]</filter>
|
|
0
|
112 <discover_datasets pattern="(?P<designation>.*)" directory="largest_O" ext="tabular" visible="false" />
|
|
|
113 </collection>
|
|
|
114 <collection name="mode_O" type="list" label="mode O: ${tool.name} on ${on_string}">
|
|
4
|
115 <filter>output_files in ["all", "simple_orphan", "simple_orphan_detail"] and method in ["all", "mode"]</filter>
|
|
0
|
116 <discover_datasets pattern="(?P<designation>.*)" directory="mode_O" ext="tabular" visible="false" />
|
|
|
117 </collection>
|
|
|
118 <collection name="closest_P_pdf" type="list" label="closest P: ${tool.name} on ${on_string}">
|
|
4
|
119 <filter>output_files == "all" and method in ["all", "closest"]</filter>
|
|
0
|
120 <discover_datasets pattern="(?P<designation>.*)" directory="closest_P" ext="pdf" visible="false" />
|
|
|
121 </collection>
|
|
|
122 <collection name="largest_P_pdf" type="list" label="largest P: ${tool.name} on ${on_string}">
|
|
4
|
123 <filter>output_files == "all" and method in ["all", "largest"]</filter>
|
|
0
|
124 <discover_datasets pattern="(?P<designation>.*)" directory="largest_P" ext="pdf" visible="false" />
|
|
|
125 </collection>
|
|
|
126 <collection name="mode_P_pdf" type="list" label="mode P: ${tool.name} on ${on_string}">
|
|
4
|
127 <filter>output_files == "all" and method in ["all", "mode"]</filter>
|
|
0
|
128 <discover_datasets pattern="(?P<designation>.*)" directory="mode_P" ext="pdf" visible="false" />
|
|
|
129 </collection>
|
|
|
130 <collection name="closest_S" type="list" label="closest S: ${tool.name} on ${on_string}">
|
|
|
131 <filter>method in ["all", "closest"]</filter>
|
|
|
132 <discover_datasets pattern="(?P<designation>.*)" directory="closest_S" ext="gff" visible="false" />
|
|
|
133 </collection>
|
|
|
134 <collection name="largest_S" type="list" label="largest S: ${tool.name} on ${on_string}">
|
|
|
135 <filter>method in ["all", "largest"]</filter>
|
|
|
136 <discover_datasets pattern="(?P<designation>.*)" directory="largest_S" ext="gff" visible="false" />
|
|
|
137 </collection>
|
|
|
138 <collection name="mode_S" type="list" label="mode S: ${tool.name} on ${on_string}">
|
|
|
139 <filter>method in ["all", "mode"]</filter>
|
|
|
140 <discover_datasets pattern="(?P<designation>.*)" directory="mode_S" ext="gff" visible="false" />
|
|
|
141 </collection>
|
|
|
142 <data name="statistics_output" format="tabular" label="Statistics: ${tool.name} on ${on_string}" />
|
|
|
143 </outputs>
|
|
|
144 <tests>
|
|
|
145 <test>
|
|
|
146 <param name="input" value="cwpair2_input1.gff" />
|
|
|
147 <param name="method" value="all" />
|
|
|
148 <param name="up_distance" value="25" />
|
|
|
149 <param name="down_distance" value="100" />
|
|
|
150 <param name="binsize" value="1" />
|
|
|
151 <param name="threshold_format" value="relative_threshold" />
|
|
|
152 <param name="relative_threshold" value="0.0" />
|
|
|
153 <param name="output_files" value="simple" />
|
|
|
154 <param name="sort_chromosome" value="asc" />
|
|
|
155 <param name="sort_score" value="asc" />
|
|
|
156 <output_collection name="closest_S" type="list">
|
|
|
157 <element name="closest_S_data_1_f0u25d100b1" file="closest_s_output1.gff" ftype="gff" />
|
|
|
158 </output_collection>
|
|
|
159 <output_collection name="largest_S" type="list">
|
|
|
160 <element name="largest_S_data_1_f0u25d100b1" file="largest_s_output1.gff" ftype="gff" />
|
|
|
161 </output_collection>
|
|
|
162 <output_collection name="mode_S" type="list">
|
|
|
163 <element name="mode_S_data_1_f0u25d100b1" file="mode_s_output1.gff" ftype="gff" />
|
|
|
164 </output_collection>
|
|
|
165 <output name="statistics_output" file="statistics1.tabular" ftype="tabular" />
|
|
|
166 </test>
|
|
|
167 <test>
|
|
|
168 <param name="input" value="cwpair2_input1.gff" />
|
|
|
169 <param name="method" value="all" />
|
|
|
170 <param name="up_distance" value="50" />
|
|
|
171 <param name="down_distance" value="100" />
|
|
|
172 <param name="binsize" value="1" />
|
|
|
173 <param name="threshold_format" value="relative_threshold" />
|
|
|
174 <param name="relative_threshold" value="0.0" />
|
|
|
175 <param name="output_files" value="all" />
|
|
|
176 <param name="sort_chromosome" value="asc" />
|
|
|
177 <param name="sort_score" value="no" />
|
|
|
178 <output_collection name="closest_D" type="list">
|
|
|
179 <element name="closest_D_data_1_f0u50d100b1" file="closest_d_output2.tabular" ftype="tabular" />
|
|
|
180 </output_collection>
|
|
|
181 <output_collection name="closest_F" type="list">
|
|
|
182 <element name="closest_F_data_1_f0u50d100b1" file="closest_f_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
183 </output_collection>
|
|
|
184 <output_collection name="closest_O" type="list">
|
|
|
185 <element name="closest_O_data_1_f0u50d100b1" file="closest_o_output2.tabular" ftype="tabular" />
|
|
|
186 </output_collection>
|
|
|
187 <output_collection name="closest_S" type="list">
|
|
|
188 <element name="closest_S_data_1_f0u50d100b1" file="closest_s_output2.gff" ftype="gff" />
|
|
|
189 </output_collection>
|
|
|
190 <output_collection name="largest_D" type="list">
|
|
|
191 <element name="largest_D_data_1_f0u50d100b1" file="largest_d_output2.tabular" ftype="tabular" />
|
|
|
192 </output_collection>
|
|
|
193 <output_collection name="largest_F" type="list">
|
|
|
194 <element name="largest_F_data_1_f0u50d100b1" file="largest_f_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
195 </output_collection>
|
|
|
196 <output_collection name="largest_O" type="list">
|
|
|
197 <element name="largest_O_data_1_f0u50d100b1" file="largest_o_output2.tabular" ftype="tabular" />
|
|
|
198 </output_collection>
|
|
|
199 <output_collection name="largest_S" type="list">
|
|
|
200 <element name="largest_S_data_1_f0u50d100b1" file="largest_s_output2.gff" ftype="gff" />
|
|
|
201 </output_collection>
|
|
|
202 <output_collection name="mode_C" type="list">
|
|
|
203 <element name="mode_C_data_1_f0u50d100b1" file="mode_c_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
204 </output_collection>
|
|
|
205 <output_collection name="mode_D" type="list">
|
|
|
206 <element name="mode_D_data_1_f0u50d100b1" file="mode_d_output2.tabular" ftype="tabular" />
|
|
|
207 </output_collection>
|
|
|
208 <output_collection name="mode_F" type="list">
|
|
|
209 <element name="mode_F_data_1_f0u50d100b1" file="mode_f_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
210 </output_collection>
|
|
|
211 <output_collection name="mode_O" type="list">
|
|
|
212 <element name="mode_O_data_1_f0u50d100b1" file="mode_o_output2.tabular" ftype="tabular" />
|
|
|
213 </output_collection>
|
|
|
214 <output_collection name="mode_P" type="list">
|
|
|
215 <element name="mode_P_data_1_f0u50d100b1" file="mode_p_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
216 </output_collection>
|
|
|
217 <output_collection name="mode_S" type="list">
|
|
|
218 <element name="mode_S_data_1_f0u50d100b1" file="mode_s_output2.gff" ftype="gff" />
|
|
|
219 </output_collection>
|
|
|
220 <output name="statistics_output" file="statistics2.tabular" ftype="tabular" />
|
|
|
221 </test>
|
|
|
222 </tests>
|
|
|
223 <help>
|
|
|
224 **What it does**
|
|
|
225
|
|
|
226 Takes a list of called peaks on both strands and produces a list of matched pairs and a list of unmatched orphans
|
|
|
227 using a specified method for finding matched pairs. Methods for finding matched pairs are mode, closest, largest
|
|
|
228 or all (where the analysis is run for each method). A statistics dataset is generated and a collection of datasets
|
|
|
229 is produced for each method as follows.
|
|
|
230
|
|
4
|
231 * **closest/largest/mode C** - the stastics graph in pdf format
|
|
0
|
232 * **closest/largest/mode D** - the details in tabular format
|
|
4
|
233 * **closest/largest/mode F** - the final plots graph in pdf format
|
|
0
|
234 * **closest/largest/mode O** - the orphans in tabular format
|
|
4
|
235 * **closest/largest/mode P** - the preview plots graph in pdf format
|
|
0
|
236 * **closest/largest/mode S** - the matched pairs in gff format
|
|
|
237
|
|
4
|
238 -----
|
|
0
|
239
|
|
|
240 **Options**
|
|
|
241
|
|
|
242 * **Output files** - Restrict output dataset collections to matched pairs only or one of several combinations of collection types.
|
|
|
243 * **Method of finding match** - Method of finding matched pair, mode, closest, largest, or all (run with each method).
|
|
|
244 * **Distance upstream from a peak to allow a pair** - Distance upstream from a Watson peak to allow a Crick pair.
|
|
|
245 * **Distance downstream from a peak to allow a pair** - Distance downstream from a Watson peak to allow a Crick pair.
|
|
|
246 * **Percentage of the 95 percentile value to filter below** - Percentage of the 95 percentile value below which to filter when using a relative threshold.
|
|
|
247 * **Absolute value to filter below** - Absolute value below which to filter when using an absolute threshold.
|
|
|
248 * **Sort output by chromosomes in** - Output will be sorted by chromsome in the specified order.
|
|
|
249 * **Sort output by score?** - If yes, output will be sorted by score in the specified order.
|
|
|
250 * **Summary output format** - Format for summary output.
|
|
|
251
|
|
|
252 </help>
|
|
|
253 <expand macro="citations" />
|
|
|
254 </tool>
|
