Mercurial > repos > artbio > cpm_tpm_rpk

comparison cpm_tpm_rpk.xml @ 7:f00c1c34565e draft default tip

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/main/tools/cpm_tpm_rpk commit 8cca5f05212cd25113955fb9c11801f4047c12b4
author artbio
date Wed, 03 Jul 2024 14:39:26 +0000
parents d2575928b824
children
comparison
equal deleted inserted replaced
6:d2575928b824 7:f00c1c34565e
1 <tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPK" version="0.5.2"> 1 <tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPKM" version="0.6.0">
2 <description>from raw counts expression values</description> 2 <description>from raw counts expression values</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="1.7.1">r-optparse</requirement> 4 <requirement type="package" version="1.7.5">r-optparse</requirement>
5 <requirement type="package" version="0.16">r-rtsne</requirement> 5 <requirement type="package" version="0.17">r-rtsne</requirement>
6 <requirement type="package" version="3.3.6">r-ggplot2</requirement> 6 <requirement type="package" version="3.5.1">r-ggplot2</requirement>
7 <requirement type="package" version="0.4.14">r-ggfortify</requirement> 7 <requirement type="package" version="0.4.17">r-ggfortify</requirement>
8 <requirement type="package" version="1.4.4">r-reshape2</requirement> 8 <requirement type="package" version="1.4.4">r-reshape2</requirement>
9 </requirements> 9 </requirements>
10 <stdio> 10 <stdio>
11 <exit_code range="1:" level="fatal" description="Tool exception" /> 11 <exit_code range="1:" level="fatal" description="Tool exception" />
12 </stdio> 12 </stdio>
19 #if $option.type_transfo == "tpm": 19 #if $option.type_transfo == "tpm":
20 -f $option.gene_file 20 -f $option.gene_file
21 --gene_sep $option.gene_sep 21 --gene_sep $option.gene_sep
22 --gene_header $option.gene_header 22 --gene_header $option.gene_header
23 #end if 23 #end if
24 #if $option.type_transfo == "rpk": 24 #if $option.type_transfo == "rpkm":
25 -f $option.gene_file 25 -f $option.gene_file
26 --gene_sep $option.gene_sep 26 --gene_sep $option.gene_sep
27 --gene_header $option.gene_header 27 --gene_header $option.gene_header
28 #end if 28 #end if
29 -l $log 29 -l $log
62 </param> 62 </param>
63 <conditional name="option"> 63 <conditional name="option">
64 <param name="type_transfo" type="select" label="Type of transformation"> 64 <param name="type_transfo" type="select" label="Type of transformation">
65 <option value="cpm" selected="true">CPM</option> 65 <option value="cpm" selected="true">CPM</option>
66 <option value="tpm">TPM</option> 66 <option value="tpm">TPM</option>
67 <option value="rpk">RPK</option> 67 <option value="rpkm">RPKM</option>
68 <option value="none">NONE</option> 68 <option value="none">NONE</option>
69 </param> 69 </param>
70 <when value="tpm"> 70 <when value="tpm">
71 <param name="gene_file" type="data" format="txt" label="Gene length file"/> 71 <param name="gene_file" type="data" format="txt" label="Gene length file"/>
72 <param name="gene_sep" type="select" label="Gene length column separator"> 72 <param name="gene_sep" type="select" label="Gene length column separator">
80 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?"> 80 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?">
81 <option value="TRUE" selected="true">Yes</option> 81 <option value="TRUE" selected="true">Yes</option>
82 <option value="FALSE">No</option> 82 <option value="FALSE">No</option>
83 </param> 83 </param>
84 </when> 84 </when>
85 <when value="rpk"> 85 <when value="rpkm">
86 <param name="gene_file" type="data" format="txt" label="Gene length file"/> 86 <param name="gene_file" type="data" format="txt" label="Gene length file"/>
87 <param name="gene_sep" type="select" label="Gene length column separator"> 87 <param name="gene_sep" type="select" label="Gene length column separator">
88 <option value="tab" selected="true">Tabs</option> 88 <option value="tab" selected="true">Tabs</option>
89 <option value=",">Commas</option> 89 <option value=",">Commas</option>
90 <option value="\ ">Whitespaces</option> 90 <option value="\ ">Whitespaces</option>
206 <param name="log" value="TRUE"/> 206 <param name="log" value="TRUE"/>
207 <output name="output" file="logtpm.tab" ftype="tabular" /> 207 <output name="output" file="logtpm.tab" ftype="tabular" />
208 </test> 208 </test>
209 <test expect_num_outputs="1"> 209 <test expect_num_outputs="1">
210 <param name="input" value="counts.tab" ftype="tabular"/> 210 <param name="input" value="counts.tab" ftype="tabular"/>
211 <param name="type_transfo" value="rpk"/> 211 <param name="type_transfo" value="rpkm"/>
212 <param name="gene_file" value="gene_length.tab" ftype="tabular"/> 212 <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
213 <param name="gene_header" value="TRUE"/> 213 <param name="gene_header" value="TRUE"/>
214 <output name="output" file="rpk.tab" ftype="tabular" /> 214 <output name="output" file="rpkm.tab" ftype="tabular" />
215 </test> 215 </test>
216 <test expect_num_outputs="1"> 216 <test expect_num_outputs="1">
217 <param name="input" value="counts.tab" ftype="tabular"/> 217 <param name="input" value="counts.tab" ftype="tabular"/>
218 <param name="type_transfo" value="rpk"/> 218 <param name="type_transfo" value="rpkm"/>
219 <param name="gene_file" value="gene_length.tab" ftype="tabular"/> 219 <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
220 <param name="gene_header" value="TRUE"/> 220 <param name="gene_header" value="TRUE"/>
221 <param name="log" value="TRUE"/> 221 <param name="log" value="TRUE"/>
222 <output name="output" file="logrpk.tab" ftype="tabular" /> 222 <output name="output" file="logrpkm.tab" ftype="tabular" />
223 </test> 223 </test>
224 </tests> 224 </tests>
225 <help> 225 <help>
226 226
227 **What it does** 227 **What it does**
229 Takes a raw count expression matrix and returns a table of normalized expression values. 229 Takes a raw count expression matrix and returns a table of normalized expression values.
230 230
231 Normalization can be: 231 Normalization can be:
232 232
233 - CPM (Counts Per Million) are obtained by dividing counts by the library counts sum and multiplying the results by a million. 233 - CPM (Counts Per Million) are obtained by dividing counts by the library counts sum and multiplying the results by a million.
234 - RPK (Reads Per Kilobases) are obtained by dividing read counts by gene lengths (expressed in kilo-nucleotides). 234 - RPK (Reads Per Kilobase) are obtained by dividing read counts by gene lengths (expressed as kilo-nucleotides).
235 - RPKM (Reads Per Kilobase per Million of Counts) are obtained by dividing read counts by gene lengths (expressed in kilo-nucleotides) then by the sum of library counts (expressed as millions of reads)
235 - 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. 236 - 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.
236 237
237 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. 238 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.
238 239
239 Note: do not comment you header line if you have header line in you tabular input (ie do not start the header line with a '#' character) 240 Note: do not comment you header line if you have header line in you tabular input (ie do not start the header line with a '#' character)