Mercurial > repos > artbio > gsc_cpm_tpm_rpk

comparison cpm_tpm_rpk.xml @ 0:ce3d027ec26b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/gsc_cpm_tpm_rpk commit 09dcd74dbc01f448518cf3db3e646afb0675a6fe
author artbio
date Mon, 24 Jun 2019 13:37:16 -0400
parents
children 46507a10106c
comparison
equal deleted inserted replaced
-1:000000000000 0:ce3d027ec26b
1 <tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPK" version="0.9.0">
2 <description>from raw counts expression values</description>
3 <requirements>
4 <requirement type="package" version="1.6.0">r-optparse</requirement>
5 </requirements>
6 <stdio>
7 <exit_code range="1:" level="fatal" description="Tool exception" />
8 </stdio>
9 <command detect_errors="exit_code"><![CDATA[
10 Rscript $__tool_directory__/cpm_tpm_rpk.R
11 --data '$input'
12 --type '$option.type_transfo'
13 --sep '$input_sep'
14 --colnames '$input_header'
15 #if $option.type_transfo == "tpm":
16 -f '$option.gene_file'
17 --gene_sep $option.gene_sep
18 --gene_header $option.gene_header
19 #end if
20 #if $option.type_transfo == "rpk":
21 -f '$option.gene_file'
22 --gene_sep '$option.gene_sep'
23 --gene_header '$option.gene_header'
24 #end if
25 --log '$log'
26 #if $log == "FALSE":
27 -o ${output}
28 #else if $log == "TRUE":
29 -o ${output_log}
30 #end if
31 ]]></command>
32 <inputs>
33 <param name="input" type="data" format="txt,tabular" label="Raw counts of expression data"/>
34 <param name="input_sep" type="select" label="Input column separator">
35 <option value="tab" selected="true">Tabulation</option>
36 <option value=",">Comma</option>
37 </param>
38 <param name="input_header" type="select" label="Consider first line of input file as header?">
39 <option value="TRUE" selected="true">Yes</option>
40 <option value="FALSE">No</option>
41 </param>
42 <conditional name="option">
43 <param name="type_transfo" type="select" label="Type of transformation">
44 <option value="cpm" selected="true">CPM</option>
45 <option value="tpm">TPM</option>
46 <option value="rpk">RPK</option>
47 </param>
48 <when value="tpm">
49 <param name="gene_file" type="data" format="txt,tabular" label="Gene length file"/>
50 <param name="gene_sep" type="select" label="Gene length column separator">
51 <option value="tab" selected="true">Tabulation</option>
52 <option value=",">Commas</option>
53 </param>
54 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?">
55 <option value="TRUE" selected="true">Yes</option>
56 <option value="FALSE">No</option>
57 </param>
58 </when>
59 <when value="rpk">
60 <param name="gene_file" type="data" format="txt,tabular" label="Gene length file"/>
61 <param name="gene_sep" type="select" label="Gene length column separator">
62 <option value="tab" selected="true">Tabs</option>
63 <option value=",">Commas</option>
64 </param>
65 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?">
66 <option value="TRUE" selected="true">Yes</option>
67 <option value="FALSE">No</option>
68 </param>
69 </when>
70 <when value="cpm">
71 </when>
72 </conditional>
73 <param name="log" type="select" label="Data should be log transformed ?">
74 <option value="FALSE" selected="true">No</option>
75 <option value="TRUE">Yes</option>
76 </param>
77 </inputs>
78 <outputs>
79 <data name="output" format="tabular" label="${option.type_transfo} from ${on_string}">
80 <filter>log == "FALSE"</filter>
81 </data>
82 <data name="output_log" format="tabular" label="log2(${option.type_transfo} +1) from ${on_string}">
83 <filter>log == "TRUE"</filter>
84 </data>
85 </outputs>
86 <tests>
87 <test>
88 <param name="input" value="counts.tab" ftype="tabular"/>
89 <param name="type_transfo" value="cpm"/>
90 <param name="log" value="TRUE"/>
91 <output name="output" file="logcpm.tab" ftype="tabular"/>
92 </test>
93 <test>
94 <param name="input" value="counts.tab" ftype="tabular"/>
95 <param name="type_transfo" value="tpm"/>
96 <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
97 <param name="log" value="TRUE"/>
98 <output name="output" file="logtpm.tab" ftype="tabular"/>
99 </test>
100 <!-- test without t-SNE -->
101 <test>
102 <param name="input" value="counts.tab" ftype="tabular"/>
103 <param name="type_transfo" value="cpm"/>
104 <output name="output" file="cpm.tab" ftype="tabular"/>
105 </test>
106 <test>
107 <param name="input" value="counts.tab" ftype="tabular"/>
108 <param name="type_transfo" value="tpm"/>
109 <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
110 <param name="gene_header" value="TRUE"/>
111 <output name="output" file="tpm.tab" ftype="tabular"/>
112 </test>
113 <test>
114 <param name="input" value="counts.tab" ftype="tabular"/>
115 <param name="type_transfo" value="rpk"/>
116 <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
117 <param name="gene_header" value="TRUE"/>
118 <output name="output" file="rpk.tab" ftype="tabular"/>
119 </test>
120 <test>
121 <param name="input" value="counts.tab" ftype="tabular"/>
122 <param name="type_transfo" value="rpk"/>
123 <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
124 <param name="gene_header" value="TRUE"/>
125 <param name="log" value="TRUE"/>
126 <output name="output" file="logrpk.tab" ftype="tabular"/>
127 </test>
128 </tests>
129 <help>
130
131 **What it does**
132
133 Takes a raw count expression matrix and returns a table of normalized expression values.
134
135 Normalization can be:
136
137 - CPM (Counts Per Million) are obtained by dividing counts by the library counts sum and multiplying the results by a million.
138 - RPK (Reads Per Kilobases) are obtained by dividing read counts by gene lengths (expressed in kilo-nucleotides).
139 - TPM (Transcripts Per Million) are obtained by dividing RPK values by the sum of all RPK values in a sample and multiplying the results by 1 million.
140
141 RPK and TPM require a two-column correspondance table gene_name - gene length where the length is specified in nucleotide. Both these metrics are relevant only for sequencing of full length RNAs.
142
143 Note: First header row must NOT start with a '#' comment character
144
145 Computed values may be base-2 log-transformed (log2([CPM or RPK or TPM]+1))
146
147 </help>
148 <citations>
149 <citation type="bibtex">
150 @Manual{,
151 title = {R: A Language and Environment for Statistical Computing},
152 author = {{R Core Team}},
153 organization = {R Foundation for Statistical Computing},
154 address = {Vienna, Austria},
155 year = {2014},
156 url = {http://www.R-project.org/},
157 }
158 </citation>
159 </citations>
160 </tool>