Mercurial > repos > devteam > subtract_query

comparison subtract_query.xml @ 0:8a3448727cec draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author devteam
date Tue, 01 Apr 2014 09:12:49 -0400
parents
children f58ba0382c26
comparison
equal deleted inserted replaced
-1:000000000000 0:8a3448727cec
1 <tool id="subtract_query1" name="Subtract Whole Dataset" version="0.1">
2 <description>from another dataset</description>
3 <requirements>
4 <requirement type="package" version="0.7.1">bx-python</requirement>
5 <requirement type="package" version="1.0.0">galaxy-ops</requirement>
6 </requirements>
7 <command interpreter="python">
8 subtract_query.py $input1 $input2 $begin_col $end_col $output
9 #if str($ignore_empty_end_cols) == 'true':
10 --ignore-empty-end-cols
11 #end if
12
13 </command>
14 <inputs>
15 <param format="txt" name="input2" type="data" label="Subtract" help="Second dataset" />
16 <param format="txt" name="input1" type="data" label="from" help="First dataset" />
17 <param name="begin_col" type="data_column" data_ref="input1" force_select="False" label="Restrict subtraction between 'begin column'" />
18 <param name="end_col" type="data_column" data_ref="input1" force_select="False" label="and 'end column'" help="Specifying columns for restricting subtraction is available only for tabular formatted datasets" />
19 <param name="ignore_empty_end_cols" type="boolean" label="Ignore empty columns and whitespace at end of line when subtracting"/>
20 </inputs>
21 <outputs>
22 <data format="input" name="output" metadata_source="input1" />
23 </outputs>
24 <tests>
25 <!-- Subtract 2 non-tabular files with no column restrictions. -->
26 <!-- Cannot figure out why this test won't pass, it works in real time... -->
27 <!--
28 <test>
29 <param name="input1" value="1.txt" />
30 <param name="input2" value="2.txt" />
31 <param name="begin_col" value="None" />
32 <param name="end_col" value="None" />
33 <output name="output" file="subtract-query-1.dat" />
34 </test>
35 -->
36 <!-- Subtract 2 tabular files with no column restrictions. -->
37 <test>
38 <param name="input1" value="eq-showbeginning.dat" />
39 <param name="input2" value="eq-showtail.dat" />
40 <param name="begin_col" value="None" />
41 <param name="end_col" value="None" />
42 <output name="output" file="subtract-query-2.dat" />
43 </test>
44 <!-- Subtract 2 tabular files with column restrictions. -->
45 <test>
46 <param name="input1" value="eq-showbeginning.dat" />
47 <param name="input2" value="eq-removebeginning.dat" />
48 <param name="begin_col" value="c1" />
49 <param name="end_col" value="c3" />
50 <output name="output" file="subtract-query-3.dat" />
51 </test>
52 <!-- Subtract a non-tabular file from a tabular file with no column restrictions. -->
53 <test>
54 <param name="input1" value="eq-showbeginning.dat" />
55 <param name="input2" value="2.txt" />
56 <param name="begin_col" value="None" />
57 <param name="end_col" value="None" />
58 <output name="output" file="subtract-query-4.dat" />
59 </test>
60 <!-- Subtract 2 tabular files with no column restrictions, ignoring empty end columns. -->
61 <test>
62 <param name="input1" value="eq-showbeginning_e.dat" />
63 <param name="input2" value="eq-showtail.dat" />
64 <param name="begin_col" value="None" />
65 <param name="end_col" value="None" />
66 <param name="ignore_empty_end_cols" value="true" />
67 <output name="output" file="subtract-query-2.dat" />
68 </test>
69 </tests>
70 <help>
71
72 .. class:: infomark
73
74 **TIP:** This tool complements the tool in the **Operate on Genomic Intervals** tool set which subtracts the intervals of two datasets.
75
76
77 -----
78
79 **Syntax**
80
81 This tool subtracts an entire dataset from another dataset.
82
83 - Any text format is valid.
84 - If both dataset formats are tabular, you may restrict the subtraction to specific columns **contained in both datasets** and the resulting dataset will include only the columns specified.
85 - The begin column must be less than or equal to the end column. If it is not, begin column is switched with end column.
86 - If begin column is specified but end column is not, end column will default to begin_column (and vice versa).
87 - All blank and comment lines are skipped and not included in the resulting dataset (comment lines are lines beginning with a # character).
88 - Duplicate lines are eliminated from both dataset prior to subtraction. If any duplicate lines were eliminated from the first dataset, the number is displayed in the resulting history item.
89
90 -----
91
92 **Example**
93
94 If this is the **First dataset**::
95
96 chr1 4225 19670
97 chr10 6 8
98 chr1 24417 24420
99 chr6_hla_hap2 0 150
100 chr2 1 5
101 chr10 2 10
102 chr1 30 55
103 chrY 1 20
104 chr1 1225979 42287290
105 chr10 7 8
106
107 and this is the **Second dataset**::
108
109 chr1 4225 19670
110 chr10 6 8
111 chr1 24417 24420
112 chr6_hla_hap2 0 150
113 chr2 1 5
114 chr1 30 55
115 chrY 1 20
116 chr1 1225979 42287290
117
118 Subtracting the **Second dataset** from the **First dataset** (including all columns) will yield::
119
120 chr10 7 8
121 chr10 2 10
122
123 Conversely, subtracting the **First dataset** from the **Second dataset** (including all columns) will result in an empty dataset.
124
125 Subtracting the **Second dataset** from the **First dataset** (restricting to columns c1 and c2) will yield::
126
127 chr10 7
128 chr10 2
129
130 </help>
131 </tool>