-
Notifications
You must be signed in to change notification settings - Fork 0
/
clodius.xml
212 lines (202 loc) · 7.71 KB
/
clodius.xml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
<?xml version='1.0' encoding='utf-8'?>
<tool id="clodius" name="clodius" version="0.0.1">
<description>Clodius is a tool for breaking up large data sets into smaller tiles that can subsequently be displayed using an appropriate viewer.</description>
<requirements>
<requirement type="package" version="0.3.2">pybigwig</requirement>
<requirement type="package" version="0.2.19">negspy</requirement>
<requirement type="package" version="1.0.7">slugid</requirement>
<requirement type="package" version="0.6.5">clodius</requirement>
</requirements>
<command>
<![CDATA[
clodius aggregate $file_type $input_file --assembly $genome_assembly
#if $output_filename:
--output-file $output_filename
#end if
#if $file_type == "bedpe":
--chr1-col $chromosome_one_column
--from1-col $from_one_column
--to1-col $to_one_column
--chr2-col $chromosome_two_column
--from2-col $from_two_column
--to2-col $to_two_column
#end if
#if $file_type == "bedfile":
--max-per-tile $max_per_tile
--importance-column $importance_column
#if $delimiter == "tab":
--delimiter '\t'
#end if
#end if
#if $file_type == "bedgraph":
#if $chromosome_column:
--chromosome-col $chromosome_column
#end if
#if $from_position_column:
--from-pos-col $from_position_column
#end if
#if $to_position_column:
--to-pos-col $to_position_column
#end if
#if $value_column:
--value-col $value_column
#end if
#if $has_header:
--has-header
#end if
#if $nan_value:
--nan-value $nan_value
#end if
#end if
]]>
</command>
<inputs>
<param
name="chromosome_column"
type="integer"
label="The column number (1-based) which contains the chromosome name."
optional="true"/>
<param
name="chromosome_one_column"
type="integer"
label="The column containing the first chromosome."
optional="true"/>
<param
name="chromosome_two_column"
type="integer"
label="The column containing the second chromosome."
optional="true"/>
<param
name="delimiter"
type="text"
optional="true"/>
<param
name="file_type"
type="text"
label="Filetype to be aggregated">
<option value="bedpe">Bedpe-like file</option>
<option value="bedfile">Gene Annotation File</option>
<option value="bedgraph">BedGraph file</option>
<option value="bigwig">BigWig File</option>
</param>
<param
name="from_one_column"
type="integer"
label="The column containing the first start position."
optional="true"/>
<param
name="from_two_column"
type="integer"
label="The column containing the second start position."
optional="true"/>
<param
name="from_position_column"
type="integer"
label="The column number (1-based) which contains the starting position."
value="2"/>
<param
name="genome_assembly"
type="text"
label="Genome Assembly"
value="hg19"/>
<param
name="has_header"
type="boolean"
label="Does this file have a header that we should ignore?"
optional="true"/>
<param
name="input_file"
type="data"
label="File to be aggregated"/>
<param
name="importance_column"
type="integer"
label="The column (1-based) containing information about how important that row is.
If it's absent, then use the length of the region.
If the value is equal to `random`, then a random value will be used for the importance (effectively leading to random sampling)"
optional="true"/>
<param
name="max_per_tile"
type="integer"
label="Max per tile."
value="100"/>
<param
name="nan_value"
type="text"
label="The string to use as a NaN value."
optional="true"/>
<param
name="output_filename"
type="text"
label="The default output file name to use. If this isn't specified, clodius will replace the current extension with something resonable."
optional="true"/>
<param
name="to_one_column"
type="integer"
label="The column containing the first end position."
optional="true"/>
<param
name="to_two_column"
type="integer"
label="The column containing the second end position."
optional="true"/>
<param
name="to_position_column"
type="integer"
label="The column number (1-based) which contains the ending position."
value="3"/>
<param
name="value_column"
type="integer"
label="The column number (1-based) which contains the actual value position."
value="4"/>
</inputs>
<outputs>
<data name="output_file" />
</outputs>
<tests>
<test expect_num_outputs="1" expect_exit_code="0">
<param name="input_file" value="Rao_RepA_GM12878_Arrowhead.txt"/>
<param name="file_type" value="bedpe" />
<param name="chromosome_one_column" value="1" />
<param name="chromosome_two_column" value="1" />
<param name="from_one_column" value="2" />
<param name="from_two_column" value="2" />
<param name="to_one_column" value="3" />
<param name="to_two_column" value="3" />
<param name="output_filename" value="bedpe_test.out" />
<output name="output_file" file="Rao_RepA_GM12878_Arrowhead.txt.multires" />
</test>
<test expect_num_outputs="1" expect_exit_code="0">
<param name="input_file" value="geneAnnotationsExonsUnions.short.bed" />
<param name="file_type" value="bedfile" />
<param name="importance_column" value="5" />
<param name="max_per_tile" value="20" />
<param name="output_filename" value="bedfile_test.out" />
</test>
<test expect_num_outputs="1" expect_exit_code="0">
<param name="input_file" value="cnvs_hw.tsv" />
<param name="file_type" value="bedgraph" />
<param name="genome_assembly" value="grch37" />
<param name="chromosome_column" value="2" />
<param name="from_position_column" value="3" />
<param name="to_position_column" value="4" />
<param name="value_column" value="5" />
<param name="has_header" value="true" />
<param name="nan_value" value="NA" />
<param name="output_filename" value="bedgraph_test.out" />
</test>
<test expect_num_outputs="1" expect_exit_code="0">
<param name="input_file" value="test.bw" />
<param name="file_type" value="bigwig" />
<param name="output_filename" value="bigwig_test.out" />
<output name="output_file" file="test.multires.bw" lines_diff="9"/>
</test>
</tests>
<help>
<![CDATA[
**What it does**
Clodius is a tool for breaking up large data sets into smaller tiles that can subsequently be displayed using an appropriate viewer.
]]>
</help>
</tool>