annotate datamash.xml @ 0:0163ea7bc5b3

GNU Datamash version 1.0.5, galaxy tool v1 (prod)
author A. Gordon <gordon@cshl.edu>
date Thu, 17 Jul 2014 07:43:31 +0300
parents
children f6af66d4ded6 c553b0d578d9
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
1 <tool id="GroupCompute" name="Datamash" version="1.0.5">
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
2 <description>(operations on tabular data)</description>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
3
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
4 <requirements>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
5 <requirement type="package" version="1.0.5">datamash</requirement>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
6 </requirements>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
7
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
8 <command>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
9 datamash
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
10 $header_in
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
11 $header_out
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
12 $need_sort
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
13 $print_full_line
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
14 $ignore_case
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
15 #if str($grouping)>0
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
16 --group '$grouping'
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
17 #end if
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
18 #for $oper in $operations
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
19 ${oper.op_name}
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
20 ${oper.op_column}
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
21 #end for
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
22 &lt; $in_file &gt; $out_file
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
23 </command>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
24 <inputs>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
25 <param format="tabular" name="in_file" type="data" label="Select Input Data" help=""/>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
26
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
27 <param name="grouping" label="Group by fields" type="text" help="Example: 1,4 - To group by the first and fourth fields. Leave empty to perform operation on entire file as one group."/>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
28
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
29 <param name="header_in" type="boolean" truevalue="--header-in" falsevalue=""
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
30 label="Input file has a header line" help="Mark this if the input file's first line is a header line" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
31
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
32 <param name="header_out" type="boolean" truevalue="--header-out" falsevalue=""
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
33 label="Print header line" help="Mark this if you want the first line to show the field names" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
34
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
35 <param name="need_sort" type="boolean" truevalue="--sort" falsevalue=""
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
36 label="Sort input" help="Mark if the input file is not sorted. If the input file is already sorted, unmark this option to reduce computing time." />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
37
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
38 <param name="print_full_line" type="boolean" truevalue="--full" falsevalue=""
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
39 label="Print all fields from input file" help="If set, all input fields will be printed. If unset, only fields used for grouping will be printed." />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
40
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
41 <param name="ignore_case" type="boolean" truevalue="--ignore-case" falsevalue=""
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
42 label="Ignore case when grouping" help="If set, upper/lowercase differences will be ignored when grouping fields." />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
43
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
44 <repeat name="operations" title="Operation to perform on each group">
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
45 <param name="op_name" type="select" label="Type">
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
46 <option value="count">count</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
47 <option value="sum">sum</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
48 <option value="min">minimum</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
49 <option value="max">maximum</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
50 <option value="absmin">Absolute minimum</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
51 <option value="absmax">Absolute maximum</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
52 <option value="mean">Mean</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
53 <option value="pstdev">Population Standard deviantion</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
54 <option value="sstdev">Sample Standard deviantion</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
55 <option value="median">Median</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
56 <option value="q1">1st quartile</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
57 <option value="q3">3rd quartile</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
58 <option value="iqr">Inter-quartile range</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
59 <option value="mad">Median Absolute Deviation</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
60 <option value="pvar">Variance (population)</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
61 <option value="svar">Variance (sample)</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
62 <option value="sskew">Skewness (sample)</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
63 <option value="pskew">Skewness (population)</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
64 <option value="skurt">Kurtosis (sample)</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
65 <option value="pkurt">Kurtosis (population)</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
66 <option value="jarque">Jarque-Bera Normality test</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
67 <option value="dpo">DAgostino-Pearson Omnibus Normality Test</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
68 <option value="mode">Mode</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
69 <option value="antimode">Anti-Mode</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
70 <option value="unique">Combine all unique values</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
71 <option value="collapse">Combine all values</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
72 <option value="countunique">Count Unique values</option>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
73 </param>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
74 <param name="op_column" label="On column" type="data_column" data_ref="in_file" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
75 </repeat>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
76 </inputs>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
77
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
78 <outputs>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
79 <data format="tabular" name="out_file" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
80 </outputs>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
81
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
82 <tests>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
83 <test>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
84 <param name="in_file" value="group_compute_input.txt" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
85 <param name="grouping" value="2" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
86 <param name="header_in" value="true" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
87 <param name="header_out" value="true" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
88 <param name="need_sort" value="true" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
89 <param name="print_full_line" value="false" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
90 <param name="op_column" value="3" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
91 <param name="op_name" value="sum" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
92 <param name="ignore_case" value="false" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
93 <output name="out_file" file="group_compute_output.txt" />
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
94 </test>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
95 </tests>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
96 <help>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
97
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
98 .. class:: infomark
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
99
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
100 **TIP:** Input data must be TAB delimited. If the desired dataset does not appear in the input list, use *Text Manipulation-&gt;Convert* to convert it to **Tabular** type.
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
101
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
102 -----
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
103
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
104 **Syntax**
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
105
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
106 This tools performs common operations (such as summing, counting, mean, standard-deviation) on input file, based on tabular data. The tool can also optionaly group the input based on a given field.
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
107
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
108 -----
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
109
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
110 **Example 1**
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
111
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
112 - Find the average score in statistics course of college students, grouped by their college major. The input file has three fields (Name,Major,Score) and a header line::
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
113
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
114 Name Major Score
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
115 Bryan Arts 68
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
116 Isaiah Arts 80
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
117 Gabriel Health-Medicine 100
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
118 Tysza Business 92
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
119 Zackery Engineering 54
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
120 ...
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
121 ...
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
122
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
123 - Grouping the input by the second column (*Major*), and performing operations **mean** and **sample standard deviation** on the third column (*Score*), gives::
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
124
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
125 GroupBy(Major) mean(Score) sstdev(Score)
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
126 Arts 68.9474 10.4215
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
127 Business 87.3636 5.18214
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
128 Engineering 66.5385 19.8814
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
129 Health-Medicine 90.6154 9.22441
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
130 Life-Sciences 55.3333 20.606
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
131 Social-Sciences 60.2667 17.2273
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
132
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
133 This sample file is available at http://www.gnu.org/software/datamash .
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
134
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
135 **Example 2**
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
136
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
137 - Using the UCSC RefSeq Human Gene Track, available at: http://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/refGene.txt.gz
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
138
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
139 - List the number and identifiers of isoforms per gene. The gene identifier is in column 13, the isoform/transcript identifier is in column 2. Grouping by column 13 and performing **count** and **Combine all values** on column 2, gives::
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
140
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
141 GroupBy(field-13) count(field-2) collapse(field-2)
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
142 A1BG 1 NM_130786
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
143 A1BG-AS1 1 NR_015380
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
144 A1CF 6 NM_001198818,NM_001198819,NM_001198820,NM_014576,NM_138932,NM_138933
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
145 A2M 1 NM_000014
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
146 A2M-AS1 1 NR_026971
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
147 A2ML1 2 NM_001282424,NM_144670
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
148 ...
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
149
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
150 - Count how many transcripts are listed for each chromosome and strand. Chromosome is on column 3, Strand is in column 4. Transcript identifiers are in column 2. Grouping by columns **3,4** and performing operation **count** on column 2, gives::
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
151
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
152 GroupBy(field-3) GroupBy(field-4) count(field-2)
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
153 chr1 + 2456
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
154 chr1 - 2431
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
155 chr2 + 1599
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
156 chr2 - 1419
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
157 chr3 + 1287
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
158 chr3 - 1249
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
159 ...
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
160
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
161 -----
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
162
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
163 **GNU Datamash** is a Free and Open Source Software, see more details on the Datamash_ Website.
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
164
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
165 **GNU Datamash** is also available as a command-line program, see http://www.gnu.org/software/datamash/download/ .
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
166
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
167 For more details about supported statistical operations, see Datamash_ website.
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
168
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
169 .. _Datamash: http://www.gnu.org/software/datamash/
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
170
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
171 </help>
0163ea7bc5b3 GNU Datamash version 1.0.5, galaxy tool v1 (prod)
A. Gordon <gordon@cshl.edu>
parents:
diff changeset
172 </tool>