Mercurial > repos > artbio > cpm_tpm_rpk
comparison cpm_tpm_rpk.xml @ 1:b74bab5157c4 draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/cpm_tpm_rpk commit d46436d5d73356c8803d6d97a110a2754e8a03fb
author | artbio |
---|---|
date | Tue, 05 Feb 2019 19:51:38 -0500 |
parents | 35d032c46a4e |
children | 563337e780ce |
comparison
equal
deleted
inserted
replaced
0:35d032c46a4e | 1:b74bab5157c4 |
---|---|
1 <tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPK" version="0.1.0"> | 1 <tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPK" version="0.2.0"> |
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="1.3.2=r3.3.2_0">r-optparse</requirement> | 4 <requirement type="package" version="1.3.2=r3.3.2_0">r-optparse</requirement> |
5 <requirement type="package" version="0.13=r3.3.2_0">r-rtsne</requirement> | |
6 <requirement type="package" version="2.2.1=r3.3.2_0">r-ggplot2</requirement> | |
5 </requirements> | 7 </requirements> |
6 <stdio> | 8 <stdio> |
7 <exit_code range="1:" level="fatal" description="Tool exception" /> | 9 <exit_code range="1:" level="fatal" description="Tool exception" /> |
8 </stdio> | 10 </stdio> |
9 <command detect_errors="exit_code"><![CDATA[ | 11 <command detect_errors="exit_code"><![CDATA[ |
10 Rscript $__tool_directory__/cpm_tpm_rpk.R | 12 Rscript $__tool_directory__/cpm_tpm_rpk.R |
11 -d $input | 13 -d $input |
12 -t $option.type_transfo | 14 -t $option.type_transfo |
13 -s $input_sep | 15 -s $input_sep |
14 -c $input_header | 16 -c $input_header |
15 #if $option.type_transfo == "tpm": | 17 #if $option.type_transfo == "tpm": |
16 -f $option.gene_file | 18 -f $option.gene_file |
17 --gene_sep $option.gene_sep | 19 --gene_sep $option.gene_sep |
18 --gene_header $option.gene_header | 20 --gene_header $option.gene_header |
19 #end if | 21 #end if |
20 #if $option.type_transfo == "rpk": | 22 #if $option.type_transfo == "rpk": |
21 -f $option.gene_file | 23 -f $option.gene_file |
22 --gene_sep $option.gene_sep | 24 --gene_sep $option.gene_sep |
23 --gene_header $option.gene_header | 25 --gene_header $option.gene_header |
24 #end if | 26 #end if |
25 -l $log | 27 -l $log |
26 #if $log == "FALSE": | 28 #if $log == "FALSE": |
27 -o ${output} | 29 -o ${output} |
28 #end if | 30 #else if $log == "TRUE": |
29 #if $log == "TRUE": | 31 -o ${output_log} |
30 -o ${output_log} | 32 #end if |
31 #end if | 33 #if $visu_option.visualisation == "tsne": |
34 --tsne 'TRUE' | |
35 --seed '$visu_option.seed' | |
36 --perp '$visu_option.perp' | |
37 --theta '$visu_option.theta' | |
38 --tsne_out '$tsne_out' | |
39 #end if | |
32 ]]></command> | 40 ]]></command> |
33 <inputs> | 41 <inputs> |
34 <param name="input" type="data" format="txt" label="Raw counts of expression data"/> | 42 <param name="input" type="data" format="txt" label="Raw counts of expression data"/> |
35 <param name="input_sep" type="select" label="Input column separator"> | 43 <param name="input_sep" type="select" label="Input column separator"> |
36 <option value="tab" selected="true">Tabs</option> | 44 <option value="tab" selected="true">Tabs</option> |
42 </param> | 50 </param> |
43 <param name="input_header" type="select" label="Consider first line of input file as header?"> | 51 <param name="input_header" type="select" label="Consider first line of input file as header?"> |
44 <option value="TRUE" selected="true">Yes</option> | 52 <option value="TRUE" selected="true">Yes</option> |
45 <option value="FALSE">No</option> | 53 <option value="FALSE">No</option> |
46 </param> | 54 </param> |
47 <conditional name="option"> | 55 <conditional name="option"> |
48 <param name="type_transfo" type="select" label="Type of transformation"> | 56 <param name="type_transfo" type="select" label="Type of transformation"> |
49 <option value="cpm" selected="true">CPM</option> | 57 <option value="cpm" selected="true">CPM</option> |
50 <option value="tpm">TPM</option> | 58 <option value="tpm">TPM</option> |
51 <option value="rpk">RPK</option> | 59 <option value="rpk">RPK</option> |
52 </param> | |
53 <when value="tpm"> | |
54 <param name="gene_file" type="data" format="txt" label="Gene length file"/> | |
55 <param name="gene_sep" type="select" label="Gene length column separator"> | |
56 <option value="tab" selected="true">Tabs</option> | |
57 <option value=",">Commas</option> | |
58 <option value="\ ">Whitespaces</option> | |
59 <option value=".">Dots</option> | |
60 <option value="_">Underscores</option> | |
61 <option value="-">Dashes</option> | |
62 </param> | 60 </param> |
63 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?"> | 61 <when value="tpm"> |
64 <option value="TRUE" selected="true">Yes</option> | 62 <param name="gene_file" type="data" format="txt" label="Gene length file"/> |
65 <option value="FALSE">No</option> | 63 <param name="gene_sep" type="select" label="Gene length column separator"> |
66 </param> | 64 <option value="tab" selected="true">Tabs</option> |
67 </when> | 65 <option value=",">Commas</option> |
68 <when value="rpk"> | 66 <option value="\ ">Whitespaces</option> |
69 <param name="gene_file" type="data" format="txt" label="Gene length file"/> | 67 <option value=".">Dots</option> |
70 <param name="gene_sep" type="select" label="Gene length column separator"> | 68 <option value="_">Underscores</option> |
71 <option value="tab" selected="true">Tabs</option> | 69 <option value="-">Dashes</option> |
72 <option value=",">Commas</option> | 70 </param> |
73 <option value="\ ">Whitespaces</option> | 71 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?"> |
74 <option value=".">Dots</option> | 72 <option value="TRUE" selected="true">Yes</option> |
75 <option value="_">Underscores</option> | 73 <option value="FALSE">No</option> |
76 <option value="-">Dashes</option> | 74 </param> |
77 </param> | 75 </when> |
78 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?"> | 76 <when value="rpk"> |
79 <option value="TRUE" selected="true">Yes</option> | 77 <param name="gene_file" type="data" format="txt" label="Gene length file"/> |
80 <option value="FALSE">No</option> | 78 <param name="gene_sep" type="select" label="Gene length column separator"> |
81 </param> | 79 <option value="tab" selected="true">Tabs</option> |
82 </when> | 80 <option value=",">Commas</option> |
83 <when value="cpm"> | 81 <option value="\ ">Whitespaces</option> |
84 </when> | 82 <option value=".">Dots</option> |
85 </conditional> | 83 <option value="_">Underscores</option> |
84 <option value="-">Dashes</option> | |
85 </param> | |
86 <param name="gene_header" type="select" label="Consider first line of gene length file as header ?"> | |
87 <option value="TRUE" selected="true">Yes</option> | |
88 <option value="FALSE">No</option> | |
89 </param> | |
90 </when> | |
91 <when value="cpm"> | |
92 </when> | |
93 </conditional> | |
86 <param name="log" type="select" label="Data should be log transformed ?"> | 94 <param name="log" type="select" label="Data should be log transformed ?"> |
87 <option value="FALSE" selected="true">No</option> | 95 <option value="FALSE" selected="true">No</option> |
88 <option value="TRUE">Yes</option> | 96 <option value="TRUE">Yes</option> |
89 </param> | 97 </param> |
98 <conditional name="visu_option"> | |
99 <param name="visualisation" type="select" label="Visualisation of data with various dimensionality reduction methods" > | |
100 <option value="no" selected="true">No visualisation</option> | |
101 <option value="tsne" >tsne</option> | |
102 </param> | |
103 <when value="tsne"> | |
104 <param name="seed" value="42.0" type="float" label="Seed value for reproducibiity" help="Set to 42 as default" /> | |
105 <param name="perp" value="10.0" type="float" label="perplexity"/> | |
106 <param name="theta" value="1.0" type="float" label="theta"/> | |
107 </when> | |
108 <when value="no" /> | |
109 </conditional> | |
90 </inputs> | 110 </inputs> |
91 <outputs> | 111 <outputs> |
92 <data name="output" format="tabular" label="${option.type_transfo} from ${on_string}"> | 112 <data name="output" format="tabular" label="${option.type_transfo} from ${on_string}"> |
93 <filter>log == "FALSE"</filter> | 113 <filter>log == "FALSE"</filter> |
94 </data> | 114 </data> |
95 <data name="output_log" format="tabular" label="log2(${option.type_transfo} +1) from ${on_string}"> | 115 <data name="output_log" format="tabular" label="log2(${option.type_transfo} +1) from ${on_string}"> |
96 <filter>log == "TRUE"</filter> | 116 <filter>log == "TRUE"</filter> |
97 </data> | 117 </data> |
118 <data name="tsne_out" format="pdf" label="tsne from ${on_string}"> | |
119 <filter>visu_option['visualisation'] == 'tsne'</filter> | |
120 </data> | |
98 </outputs> | 121 </outputs> |
99 <tests> | 122 <tests> |
123 <!-- test t-SNE --> | |
124 <test> | |
125 <param name="input" value="counts.tab" ftype="tabular"/> | |
126 <param name="type_transfo" value="cpm"/> | |
127 <param name="visualisation" value="tsne"/> | |
128 <param name="seed" value="49"/> | |
129 <param name="perp" value="2"/> | |
130 <param name="theta" value="1" /> | |
131 <output name="output" file="cpm.tab" ftype="tabular"/> | |
132 <output name="tsne_out" file="tsne.pdf" ftype="pdf"/> | |
133 </test> | |
134 <!-- test without t-SNE --> | |
100 <test> | 135 <test> |
101 <param name="input" value="counts.tab" ftype="tabular"/> | 136 <param name="input" value="counts.tab" ftype="tabular"/> |
102 <param name="type_transfo" value="cpm"/> | 137 <param name="type_transfo" value="cpm"/> |
103 <output name="output" file="cpm.tab" ftype="tabular"/> | 138 <output name="output" file="cpm.tab" ftype="tabular"/> |
104 </test> | 139 </test> |
141 </tests> | 176 </tests> |
142 <help> | 177 <help> |
143 | 178 |
144 **What it does** | 179 **What it does** |
145 | 180 |
146 And returns a table of normalized expression values. | 181 Takes a raw count expression matrix and returns a table of normalized expression values. |
147 | 182 |
148 Normalization can be: | 183 Normalization can be: |
149 | 184 |
150 - CPM (Counts Per Million) are obtained by dividing counts by the library counts sum and multiplying the results by a million. | 185 - CPM (Counts Per Million) are obtained by dividing counts by the library counts sum and multiplying the results by a million. |
151 - RPK (Reads Per Kilobases) are obtained by dividing read counts by gene lengths (expressed in kilo-nucleotides). | 186 - RPK (Reads Per Kilobases) are obtained by dividing read counts by gene lengths (expressed in kilo-nucleotides). |