Mercurial > repos > crs4 > edge_pro

comparison edge_pro.xml @ 6:e6e6f5f9b9c4 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://bitbucket.org/crs4/orione-tools/src/bb-orione-tools/custom/edge_pro/ commit 02541df6373bc61be0cdc0617c8549cf8b49b832
author crs4
date Thu, 31 Aug 2017 12:54:08 -0400
parents d5464c9e1723
children
comparison
equal deleted inserted replaced
5:407b894abb08 6:e6e6f5f9b9c4
1 <tool id="edge_pro" name="EDGE-pro" version="1.0.1"> 1 <tool id="edge_pro" name="EDGE-pro" version="1.0.2">
2 <description>Gene expression in Prokaryotes</description> 2 <description>Gene expression in Prokaryotes</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="2.1.0">bowtie2</requirement> 4 <requirement type="package" version="2.1.0">bowtie2</requirement>
5 <requirement type="package" version="1.3.1">edge-pro</requirement> 5 <requirement type="package" version="1.3.1">edge-pro</requirement>
6 </requirements> 6 </requirements>
7 <command> 7 <command detect_errors="exit_code"><![CDATA[
8 edge.pl -t \${GALAXY_SLOTS:-4} -o edge_out 8 edge.pl -t \${GALAXY_SLOTS:-4} -o edge_out
9 ## Mandatory input parameters 9 ## Mandatory input parameters
10 -g $genome 10 -g '$genome'
11 -p $ptt 11 -p '$ptt'
12 -r $rnt 12 -r '$rnt'
13 13
14 #if $singlePaired.sPaired == "single" 14 #if $singlePaired.sPaired == "single"
15 -u $singlePaired.input1 15 -u '$singlePaired.input1'
16 #else if $singlePaired.sPaired == "paired" 16 #else if $singlePaired.sPaired == "paired"
17 -u $singlePaired.input1 17 -u '$singlePaired.input1'
18 -v $singlePaired.input2 18 -v '$singlePaired.input2'
19 #else if $singlePaired.sPaired == "pairedCollection" 19 #else if $singlePaired.sPaired == "pairedCollection"
20 -u $singlePaired.input.forward 20 -u '$singlePaired.input.forward'
21 -v $singlePaired.input.reverse 21 -v '$singlePaired.input.reverse'
22 #end if 22 #end if
23 23
24 #if $singlePaired.sPaired in ["paired", "pairedCollection"] 24 #if $singlePaired.sPaired in ("paired", "pairedCollection")
25 #if str($singlePaired.minInsertSize) 25 #if str($singlePaired.minInsertSize)
26 -m $singlePaired.minInsertSize 26 -m $singlePaired.minInsertSize
27 #end if 27 #end if
28 #if str($singlePaired.maxInsertSize) 28 #if str($singlePaired.maxInsertSize)
29 -M $singlePaired.maxInsertSize 29 -M $singlePaired.maxInsertSize
30 #end if 30 #end if
31 #end if 31 #end if
32
33 ## Optional input parameters
34 #if $params.settingsType == "full"
35 #if str($params.window)
36 -w $params.window
37 #end if
38 #if str($params.utrSize)
39 -i $params.utrSize
40 #end if
41 #if str($params.similarity)
42 -x $params.similarity
43 #end if
44 #if str($params.readLength)
45 -l $params.readLength
46 #end if
47 #if str($params.minCoverage)
48 -c $params.minCoverage
49 #end if
50 #end if
51 &gt; $out_log 2&gt;&amp;1 ## need to redirect stderr because edge.pl calls bowtie2 and count which write some logging info there
52 &amp;&amp; cat edge_out.rpkm_* > $out_rpkm
53 </command>
54 <stdio>
55 <exit_code range="1:" level="fatal" />
56 </stdio>
57 <inputs>
58 <conditional name="singlePaired">
59 <param name="sPaired" type="select" label="Is this library mate-paired?">
60 <option value="single">Single-end</option>
61 <option value="paired">Paired-end</option>
62 <option value="pairedCollection">Paired-end collection</option>
63 </param>
64 <when value="single">
65 <param format="fastqsanger" name="input1" type="data" label="FASTQ file" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)"/>
66 </when>
67 <when value="paired">
68 <param format="fastqsanger" name="input1" type="data" label="Forward FASTQ file" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)" />
69 <param format="fastqsanger" name="input2" type="data" label="Reverse FASTQ file" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)" />
70 <param name="minInsertSize" type="integer" optional="true" min="0" value="0" label="Minimun insert size in paired-end library for Bowtie2 (-m)" />
71 <param name="maxInsertSize" type="integer" optional="true" min="1" value="500" label="Maximun insert size in paired-end library for Bowtie2 (-M)" />
72 </when>
73 <when value="pairedCollection">
74 <param format="fastqsanger" name="input" type="data_collection" collection_type="paired" label="FASTQ paired collection" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)" />
75 <param name="minInsertSize" type="integer" optional="true" min="0" value="0" label="Minimun insert size in paired-end library for Bowtie2 (-m)" />
76 <param name="maxInsertSize" type="integer" optional="true" min="1" value="500" label="Maximun insert size in paired-end library for Bowtie2 (-M)" />
77 </when>
78 </conditional>
79
80 <param format="fasta" name="genome" type="data" label="Select the reference genome from your history (-g)" help="FASTA format" />
81 <param format="ptt" name="ptt" type="data" label="Coordinates of coding genes (PTT file)" help="PTT file with coordinates of coding genes (-p)" />
82 <param format="rnt" name="rnt" type="data" label="Coordinates of structural RNAs (RNT file)" help="RNT file with coordinates of structural RNA (-r)" />
83
84 <conditional name="params">
85 <param name="settingsType" type="select" label="Parameter settings" help="For most needs, use default settings. If you want full control use Full Parameter List">
86 <option value="preSet">Use defaults</option>
87 <option value="full">Full parameter list</option>
88 </param>
89 <when value="preSet" />
90 <when value="full">
91 <param name="window" type="integer" optional="true" value="100" label="Window length for coverage distribution (-w)" help="Used to distribute the coverage between two overlapping genes. See help below for details" />
92 <param name="utrSize" type="integer" optional="true" value="40" label="Size of the untranslated region (-i)" help="Enter the size of the untranslated region between the initial transcription site and the start codon" />
93 <param name="similarity" type="float" optional="true" value="0.15" label="Percentage for similar coverage (-x)" help="Enter the percentage used to determine when two coverage values are considered similar. See help below for details" />
94 <param name="readLength" type="integer" optional="true" value="" label="Read length (-l)" help="If not specified, the first 1000 reads are used to approximate the read length" />
95 <param name="minCoverage" type="integer" optional="true" value="3" label="Minimum average coverage for expressed genes (-c)" help="Coverage less than specified is assumed to be noise and gene is considered to not be expressed" />
96 </when>
97 </conditional>
98 </inputs>
99 32
100 <outputs> 33 ## Optional input parameters
101 <data format="sam" name="out_aln" label="${tool.name} on ${on_string}: alignment" from_work_dir="edge_out.alignments" /> 34 #if $params.settingsType == "full"
102 <data format="tabular" name="out_rpkm" label="${tool.name} on ${on_string}: rpkm"/> 35 #if str($params.window)
103 <data format="txt" name="out_log" label="${tool.name} on ${on_string}: log"/> 36 -w $params.window
104 </outputs> 37 #end if
38 #if str($params.utrSize)
39 -i $params.utrSize
40 #end if
41 #if str($params.similarity)
42 -x $params.similarity
43 #end if
44 #if str($params.readLength)
45 -l $params.readLength
46 #end if
47 #if str($params.minCoverage)
48 -c $params.minCoverage
49 #end if
50 #end if
51 > '$out_log' 2>&1 ## need to redirect stderr because edge.pl calls bowtie2 and count which write some logging info there
52 && cat edge_out.rpkm_* > '$out_rpkm'
53 ]]></command>
54 <inputs>
55 <conditional name="singlePaired">
56 <param name="sPaired" type="select" label="Is this library mate-paired?">
57 <option value="single">Single-end</option>
58 <option value="paired">Paired-end</option>
59 <option value="pairedCollection">Paired-end collection</option>
60 </param>
61 <when value="single">
62 <param name="input1" type="data" format="fastqsanger" label="FASTQ file" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)"/>
63 </when>
64 <when value="paired">
65 <param name="input1" type="data" format="fastqsanger" label="Forward FASTQ file" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)" />
66 <param name="input2" type="data" format="fastqsanger" label="Reverse FASTQ file" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)" />
67 <param name="minInsertSize" argument="-m" type="integer" optional="true" min="0" value="0" label="Minimun insert size in paired-end library for Bowtie2" />
68 <param name="maxInsertSize" argument="-M" type="integer" optional="true" min="1" value="500" label="Maximun insert size in paired-end library for Bowtie2" />
69 </when>
70 <when value="pairedCollection">
71 <param name="input" type="data_collection" collection_type="paired" format="fastqsanger" label="FASTQ paired collection" help="FASTQ format with Sanger-scaled quality values (Galaxy fastqsanger datatype)" />
72 <param name="minInsertSize" argument="-m" type="integer" optional="true" min="0" value="0" label="Minimun insert size in paired-end library for Bowtie2" />
73 <param name="maxInsertSize" argument="-M" type="integer" optional="true" min="1" value="500" label="Maximun insert size in paired-end library for Bowtie2" />
74 </when>
75 </conditional>
105 76
106 <help> 77 <param name="genome" argument="-g" type="data" format="fasta" label="Select the reference genome from your history" help="In FASTA format" />
78 <param name="ptt" argument="-p" type="data" format="ptt" label="Coordinates of coding genes (PTT file)" help="PTT file with coordinates of coding genes" />
79 <param name="rnt" argument="-r" type="data" format="rnt" label="Coordinates of structural RNAs (RNT file)" help="RNT file with coordinates of structural RNA" />
107 80
81 <section name="params" title="Advanced parameters" expanded="false">
82 <param name="window" argument="-w" type="integer" optional="true" value="100" label="Window length for coverage distribution" help="Used to distribute the coverage between two overlapping genes. See help below for details" />
83 <param name="utrSize" argument="-i" type="integer" optional="true" value="40" label="Size of the untranslated region" help="Enter the size of the untranslated region between the initial transcription site and the start codon" />
84 <param name="similarity" argument="-x" type="float" optional="true" value="0.15" label="Percentage for similar coverage" help="Enter the percentage used to determine when two coverage values are considered similar. See help below for details" />
85 <param name="readLength" argument="-l" type="integer" optional="true" value="" label="Read length" help="If not specified, the first 1000 reads are used to approximate the read length" />
86 <param name="minCoverage" argument="-c" type="integer" optional="true" value="3" label="Minimum average coverage for expressed genes" help="Coverage less than specified is assumed to be noise and gene is considered to not be expressed" />
87 </section>
88 </inputs>
89
90 <outputs>
91 <data name="out_aln" format="sam" label="${tool.name} on ${on_string}: alignment" from_work_dir="edge_out.alignments" />
92 <data name="out_rpkm" format="tabular" label="${tool.name} on ${on_string}: rpkm"/>
93 <data name="out_log" format="txt" label="${tool.name} on ${on_string}: log"/>
94 </outputs>
95
96 <help><![CDATA[
108 **What it does** 97 **What it does**
109 98
110 `EDGE-pro`_, Estimated Degree of Gene Expression in PROkaryots is an efficient software system to estimate gene expression levels in prokaryotic genomes from RNA-seq data. EDGE-pro uses Bowtie2 for alignment and then estimates expression directly from the alignment results. 99 `EDGE-pro`_, Estimated Degree of Gene Expression in PROkaryots is an efficient software system to estimate gene expression levels in prokaryotic genomes from RNA-seq data. EDGE-pro uses Bowtie2 for alignment and then estimates expression directly from the alignment results.
111 EDGE-pro includes routines to assign reads aligning to overlapping gene regions accurately. 15% or more of bacterial genes overlap other genes, making this a significant problem for bacterial RNA-seq, one that is generally ignored by programs designed for eukaryotic RNA-seq experiments. 100 EDGE-pro includes routines to assign reads aligning to overlapping gene regions accurately. 15% or more of bacterial genes overlap other genes, making this a significant problem for bacterial RNA-seq, one that is generally ignored by programs designed for eukaryotic RNA-seq experiments.
112 101
115 .. class:: infomark 104 .. class:: infomark
116 105
117 Input files with gene coordinates in PTT and RNT format can be retrieved with the Get EDGE-pro Files tool available in Galaxy, or downloaded from the `NCBI ftp repository`_. 106 Input files with gene coordinates in PTT and RNT format can be retrieved with the Get EDGE-pro Files tool available in Galaxy, or downloaded from the `NCBI ftp repository`_.
118 This tool accepts files in Sanger FASTQ format (Galaxy *fastqsanger* datatype). Use the FASTQ Groomer tool to prepare your files. 107 This tool accepts files in Sanger FASTQ format (Galaxy *fastqsanger* datatype). Use the FASTQ Groomer tool to prepare your files.
119 108
120 .. _NCBI ftp repository: ftp://ftp.ncbi.nlm.nih.gov/genomes/Bacteria/ 109 .. _NCBI ftp repository: ftp://ftp.ncbi.nlm.nih.gov/genomes/genbank/bacteria/
121 110
122 .. class:: warningmark 111 .. class:: warningmark
123 112
124 All 3 types of files (FASTA reference genome, PTT and RNT) must have the same order of chromosomes/plasmids (e.g. if chr1 is before chr2 in genome.fasta file, then chr1 must be before chr2 in ptt and rnt files as well). If there is no PTT or RNT file for one of chromosomes/plasmids, place this chromosome/plasmid at the end of the file. 113 All 3 types of files (FASTA reference genome, PTT and RNT) must have the same order of chromosomes/plasmids (e.g. if chr1 is before chr2 in genome.fasta file, then chr1 must be before chr2 in ptt and rnt files as well). If there is no PTT or RNT file for one of chromosomes/plasmids, place this chromosome/plasmid at the end of the file.
125 114
126 **License and citation** 115 **License and citation**
127 116
128 This Galaxy tool is Copyright © 2012-2014 `CRS4 Srl.`_ and is released under the `MIT license`_. 117 This Galaxy tool is Copyright © 2012-2014 `CRS4 Srl.`_ and is released under the `MIT license`_.
129 118
130 .. _CRS4 Srl.: http://www.crs4.it/ 119 .. _CRS4 Srl.: http://www.crs4.it/
131 .. _MIT license: http://opensource.org/licenses/MIT 120 .. _MIT license: https://opensource.org/licenses/MIT
132 121
133 You can use this tool only if you agree to the license terms of: `EDGE-pro`_. 122 You can use this tool only if you agree to the license terms of: `EDGE-pro`_.
134 123
135 .. _EDGE-pro: http://ccb.jhu.edu/software/EDGE-pro/ 124 .. _EDGE-pro: http://ccb.jhu.edu/software/EDGE-pro/
136 125 ]]></help>
137 If you use this tool, please cite: 126 <citations>
138 127 <citation type="doi">10.4137/EBO.S11250</citation>
139 - |Cuccuru2014|_ 128 <citation type="doi">10.1093/bioinformatics/btu135</citation>
140 - |Magoc2013|_. 129 </citations>
141
142 .. |Cuccuru2014| replace:: Cuccuru, G., Orsini, M., Pinna, A., Sbardellati, A., Soranzo, N., Travaglione, A., Uva, P., Zanetti, G., Fotia, G. (2014) Orione, a web-based framework for NGS analysis in microbiology. *Bioinformatics* 30(13), 1928-1929
143 .. _Cuccuru2014: http://bioinformatics.oxfordjournals.org/content/30/13/1928
144 .. |Magoc2013| replace:: Magoc, T., Wood, D., Salzberg, S. L. (2013) EDGE-pro: Estimated Degree of Gene Expression in Prokaryotic Genomes. *Evol. Bioinform.* 2013:9, 127-136
145 .. _Magoc2013: http://www.la-press.com/edge-pro-estimated-degree-of-gene-expression-in-prokaryotic-genomes-article-a3586
146 </help>
147 </tool> 130 </tool>