|
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 --up_distance $up_distance
|
|
|
15 --down_distance $down_distance
|
|
10
|
16 --method $method
|
|
0
|
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 $output_files
|
|
0
|
25 --statistics_output "$statistics_output"
|
|
|
26 ]]>
|
|
|
27 </command>
|
|
|
28 <inputs>
|
|
|
29 <param name="input" type="data" format="gff" multiple="True" label="Find matched pairs on" />
|
|
10
|
30 <param name="up_distance" type="integer" value="50" min="0" label="Distance upstream from a peak to allow a pair" />
|
|
|
31 <param name="down_distance" type="integer" value="100" min="0" label="Distance downstream from a peak to allow a pair" />
|
|
0
|
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="binsize" type="integer" value="1" min="0" label="Width of bins for frequency plots and mode calculation" help="Value 1 implies no bins" />
|
|
|
39 <conditional name="threshold_format_cond">
|
|
|
40 <param name="threshold_format" type="select" label="Filter using">
|
|
|
41 <option value="relative_threshold" selected="True">Relative threshold</option>
|
|
|
42 <option value="absolute_threshold">Absolute threshold</option>
|
|
|
43 </param>
|
|
|
44 <when value="relative_threshold">
|
|
|
45 <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" />
|
|
|
46 </when>
|
|
|
47 <when value="absolute_threshold">
|
|
|
48 <param name="absolute_threshold" type="float" value="0.0" min="0.0" label="Absolute value to filter below" />
|
|
|
49 </when>
|
|
|
50 </conditional>
|
|
4
|
51 <param name="output_files" type="select" label="Restrict output to" help="Statistics will always be generated." >
|
|
10
|
52 <option value="all" selected="True">no restrictions (output everything: C,D,F,O,P,MP)</option>
|
|
|
53 <option value="matched_pair">matched pairs only (MP)</option>
|
|
|
54 <option value="matched_pair_orphan">matched pairs and orphans only (O,MP)</option>
|
|
|
55 <option value="matched_pair_orphan_detail">matched pairs, orphans and details only (D,O,MP)</option>
|
|
0
|
56 </param>
|
|
|
57 </inputs>
|
|
|
58 <outputs>
|
|
10
|
59 <data name="statistics_output" format="tabular" label="Statistics Table: ${tool.name} on ${on_string}" />
|
|
|
60 <collection name="H" type="list" label="Statistics Histogram: ${tool.name} on ${on_string}">
|
|
|
61 <filter>output_files == "all"</filter>
|
|
|
62 <discover_datasets pattern="(?P<designation>.*)" directory="H" ext="pdf" visible="false" />
|
|
0
|
63 </collection>
|
|
10
|
64 <collection name="D" type="list" label="Data D: ${tool.name} on ${on_string}">
|
|
|
65 <filter>output_files in ["all", "matched_pair_orphan_detail"]</filter>
|
|
|
66 <discover_datasets pattern="(?P<designation>.*)" directory="data_D" ext="tabular" visible="false" />
|
|
0
|
67 </collection>
|
|
10
|
68 <collection name="O" type="list" label="Data O: ${tool.name} on ${on_string}">
|
|
|
69 <filter>output_files in ["all", "matched_pair_orphan", "matched_pair_orphan_detail"]</filter>
|
|
|
70 <discover_datasets pattern="(?P<designation>.*)" directory="data_O" ext="tabular" visible="false" />
|
|
0
|
71 </collection>
|
|
10
|
72 <collection name="MP" type="list" label="Data MP: ${tool.name} on ${on_string}">
|
|
|
73 <discover_datasets pattern="(?P<designation>.*)" directory="data_MP" ext="gff" visible="false" />
|
|
0
|
74 </collection>
|
|
|
75 </outputs>
|
|
|
76 <tests>
|
|
|
77 <test>
|
|
|
78 <param name="input" value="cwpair2_input1.gff" />
|
|
|
79 <param name="up_distance" value="25" />
|
|
|
80 <param name="down_distance" value="100" />
|
|
10
|
81 <param name="method" value="all" />
|
|
0
|
82 <param name="binsize" value="1" />
|
|
|
83 <param name="threshold_format" value="relative_threshold" />
|
|
|
84 <param name="relative_threshold" value="0.0" />
|
|
10
|
85 <param name="output_files" value="matched_pair" />
|
|
|
86 <output name="statistics_output" file="statistics1.tabular" ftype="tabular" />
|
|
|
87 <output_collection name="MP" type="list">
|
|
|
88 <element name="f0u25d100_on_data_1" file="closest_mp_output1.gff" ftype="gff" />
|
|
|
89 <element name="f0u25d100_on_data_1" file="largest_mp_output1.gff" ftype="gff" />
|
|
|
90 <element name="f0u25d100_on_data_1" file="mode_mp_output1.gff" ftype="gff" />
|
|
0
|
91 </output_collection>
|
|
|
92 </test>
|
|
|
93 <test>
|
|
|
94 <param name="input" value="cwpair2_input1.gff" />
|
|
|
95 <param name="up_distance" value="50" />
|
|
|
96 <param name="down_distance" value="100" />
|
|
10
|
97 <param name="method" value="all" />
|
|
0
|
98 <param name="binsize" value="1" />
|
|
|
99 <param name="threshold_format" value="relative_threshold" />
|
|
|
100 <param name="relative_threshold" value="0.0" />
|
|
|
101 <param name="output_files" value="all" />
|
|
10
|
102 <output name="statistics_output" file="statistics2.tabular" ftype="tabular" />
|
|
|
103 <output_collection name="H" type="list">
|
|
|
104 <element name="histogram_C_mode_f0u50d100_on_data_1" file="mode_c_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
105 <element name="histogram_F_closest_f0u50d100_on_data_1" file="closest_f_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
106 <element name="histogram_F_largest_f0u50d100_on_data_1" file="largest_f_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
107 <element name="histogram_F_mode_f0u50d100_on_data_1" file="mode_f_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
|
108 <element name="histogram_P_mode_f0u50d100_on_data_1" file="mode_p_output2.pdf" ftype="pdf" compare="sim_size" />
|
|
0
|
109 </output_collection>
|
|
10
|
110 <output_collection name="D" type="list">
|
|
|
111 <element name="data_D_closest_f0u50d100_on_data_1" file="closest_d_output2.tabular" ftype="tabular" />
|
|
|
112 <element name="data_D_largest_f0u50d100_on_data_1" file="largest_d_output2.tabular" ftype="tabular" />
|
|
|
113 <element name="data_D_mode_f0u50d100_on_data_1" file="mode_d_output2.tabular" ftype="tabular" />
|
|
0
|
114 </output_collection>
|
|
10
|
115 <output_collection name="O" type="list">
|
|
|
116 <element name="data_O_closest_f0u50d100_on_data_1" file="closest_o_output2.tabular" ftype="tabular" />
|
|
|
117 <element name="data_O_largest_f0u50d100_on_data_1" file="largest_o_output2.tabular" ftype="tabular" />
|
|
|
118 <element name="data_O_mode_f0u50d100_on_data_1" file="mode_o_output2.tabular" ftype="tabular" />
|
|
0
|
119 </output_collection>
|
|
10
|
120 <output_collection name="MP" type="list">
|
|
|
121 <element name="data_MP_closest_f0u50d100_on_data_1" file="closest_mp_output2.gff" ftype="gff" />
|
|
|
122 <element name="data_MP_largest_f0u50d100_on_data_1" file="largest_mp_output2.gff" ftype="gff" />
|
|
|
123 <element name="data_MP_mode_f0u50d100_on_data_1" file="mode_mp_output2.gff" ftype="gff" />
|
|
0
|
124 </output_collection>
|
|
|
125 </test>
|
|
|
126 </tests>
|
|
|
127 <help>
|
|
|
128 **What it does**
|
|
|
129
|
|
10
|
130 Takes a list of called peaks on both strands and produces lists of matched pairs and unmatched peaks using a
|
|
|
131 specified method for finding matched pairs. Methods for finding matched pairs are mode, closest, largest or
|
|
|
132 all (where the analysis is run for each method). A statistics dataset is generated and a collection of datasets
|
|
0
|
133 is produced for each method as follows.
|
|
|
134
|
|
10
|
135 **Data Files**
|
|
|
136
|
|
|
137 * **closest/largest/mode MP** - the Matched Pairs in gff format
|
|
|
138 * **closest/largest/mode O** - the Orphans in tabular format
|
|
|
139 * **closest/largest/mode D** - the Details in tabular format
|
|
|
140
|
|
|
141 **Statistics Files**
|
|
|
142
|
|
4
|
143 * **closest/largest/mode C** - the stastics graph in pdf format
|
|
10
|
144 * **closest/largest/mode P** - the preview plots graph in pdf format
|
|
4
|
145 * **closest/largest/mode F** - the final plots graph in pdf format
|
|
0
|
146
|
|
4
|
147 -----
|
|
0
|
148
|
|
|
149 **Options**
|
|
|
150
|
|
|
151 * **Method of finding match** - Method of finding matched pair, mode, closest, largest, or all (run with each method).
|
|
|
152 * **Distance upstream from a peak to allow a pair** - Distance upstream from a Watson peak to allow a Crick pair.
|
|
|
153 * **Distance downstream from a peak to allow a pair** - Distance downstream from a Watson peak to allow a Crick pair.
|
|
|
154 * **Percentage of the 95 percentile value to filter below** - Percentage of the 95 percentile value below which to filter when using a relative threshold.
|
|
|
155 * **Absolute value to filter below** - Absolute value below which to filter when using an absolute threshold.
|
|
10
|
156 * **Output files** - Restrict output dataset collections to matched pairs only or one of several combinations of collection types.
|
|
0
|
157
|
|
|
158 </help>
|
|
|
159 <expand macro="citations" />
|
|
|
160 </tool>
|
