Mercurial > repos > drosofff > mi_rna_parser

comparison MirParser.xml @ 0:906544162710 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author drosofff
date Sun, 22 Jun 2014 18:30:21 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:906544162710
1 <tool id="MirParser" name="Parse miRNAs" version="0.9.1">
2 <description>from sRbowtie aligment</description>
3 <requirements><requirement type='package'>bowtie-inspect</requirement></requirements>
4 <parallelism method="basic"></parallelism>
5 <command interpreter="python">
6 MirParser.py
7 #if $refGenomeSource.genomeSource == "history":
8 $refGenomeSource.ownFile ## index source sys.arg[1]
9 --do_not_extract_index ## sys.argv[2]
10 #else:
11 #silent reference= filter( lambda x: str( x[0] ) == str( $input_list.dbkey ), $__app__.tool_data_tables[ 'bowtie_indexes' ].get_fields() )[0][-1]
12 $reference ## sys.argv[1]
13 --extract_index ## sys.argv[2]
14 #end if
15 $output1 ## for pre-mirs ## sys.argv[3]
16 $output2 ## for mature mirs ## sys.argv[4]
17 $GFF3 ## sys.argv[5]
18 #if $plotting.plottingOption == "yes":
19 $lattice_dataframe ## sys.argv[6]
20 $plotCode ## sys.argv[7]
21 $latticePDF ## sys.argv[8]
22 #else:
23 "dummy_dataframe_path" ## sys.argv[6]
24 "dummy_plotCode" ## sys.argv[7]
25 "dummy_latticePDF" ## sys.argv[8]
26 #end if
27 #for $i in $refGenomeSource.input_list
28 $i $i.ext "$i.name" ## sys.argv[9,10,11] modulo 3
29 #end for
30 #silent plottingoption = $plotting.plottingOption
31 </command>
32 <inputs>
33 <conditional name="refGenomeSource">
34 <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
35 <option value="indexed">Use a built-in index</option>
36 <option value="history">Use one from the history</option>
37 </param>
38 <when value="indexed">
39 <param name="input_list" type="data" label="Select multiple alignments to parse" multiple="true">
40 <validator type="dataset_metadata_in_data_table" table_name="bowtie_indexes" metadata_name="dbkey" metadata_column="0" message="database not set for this bowtie output. Select the database(=genome used for matching) manually, or select a reference fasta from your history."/>
41 </param>
42 </when>
43 <when value="history">
44 <param name="input_list" type="data" label="Select multiple alignments to parse" multiple="true"/>
45 <param name="ownFile" type="data" format="fasta" label="Select the fasta reference" />
46 </when>
47 </conditional> <!-- refGenomeSource -->
48 <param name="GFF3" type="data" label="miRbase GFF3 guide" />
49 <conditional name="plotting">
50 <param name="plottingOption" type="select" label="Additional mir coverage graphs">
51 <option value="no" selected="True">No</option>
52 <option value="yes">YES</option>
53 </param>
54 <when value="yes">
55 <param name="display" type="select" label="Display Coverage with absolute number of reads or relatively to the total number of read matching the gene or mir">
56 <option value="relative" selected="True">Relative Coverage</option>
57 <option value="absolute">Absolute Coverage</option>
58 </param>
59 </when>
60 </conditional>
61 </inputs>
62 <configfiles>
63 <configfile name="plotCode">
64 #if $plotting.plottingOption == "yes":
65 graph_type = "${plotting.display}" ## "relative" or "absolute"
66 ## Setup R error handling to go to stderr
67 options( show.error.messages=F,
68 error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
69 library(lattice)
70 coverage = read.delim("${lattice_dataframe}", header=T)
71 Numb_of_biosamples = length(levels(coverage\$sample))
72 if (graph_type=="relative") {
73 graph = xyplot(countsNorm~offsetNorm | mir, data=coverage, groups=polarity, col=c("red", "blue"), type="l", lwd=1,
74 scales=list(x=list(cex=.5), y=list(cex=.5)), par.strip.text=list(cex=.5), strip=strip.custom(which.given=1, bg="lightblue"), layout=c(Numb_of_biosamples,15), as.table=TRUE, main="miRNA coverage maps")
75 } else {
76 graph = xyplot(counts~offset | mir, data=coverage, groups=polarity, col=c("red", "blue"), type="l", lwd=1,
77 scales=list(x=list(cex=.5), y=list(cex=.5)), par.strip.text=list(cex=.5), strip=strip.custom(which.given=1, bg="lightblue"), layout=c(Numb_of_biosamples,15), as.table=TRUE, main="miRNA coverage maps")
78 }
79 ## pdf output
80 pdf(file="${latticePDF}", paper="special", height=11.69, width=8.2677)
81 plot(graph, newpage = T)
82 dev.off()
83 #end if
84 </configfile>
85 </configfiles>
86
87 <outputs>
88 <data format="tabular" name="output1" label="Premirs Count Lists"/>
89 <data format="tabular" name="output2" label="Mature Mirs Count Lists"/>
90 <data format="tabular" name="lattice_dataframe" label="Lattice Dataframe">
91 <filter>plotting['plottingOption'] == "yes"</filter>
92 </data>
93 <data format="pdf" name="latticePDF" label="Mir coverage">
94 <filter>plotting['plottingOption'] == "yes"</filter>
95 </data>
96 </outputs>
97 <help>
98
99 **What it does**
100
101 This tool uses a specie-specific GFF3 file from mirBase_ to guide the parsing of an alignment file produced with the sRbowtie tool.
102
103 .. _mirBase: ftp://mirbase.org/pub/mirbase/CURRENT/genomes/
104
105 ------
106
107 .. class:: warningmark
108
109 the Guide GFF3 file must be in the following format:
110
111 2L . miRNA_primary_transcript 243035 243141 . - . ID=MI0005821;Alias=MI0005821;Name=dme-mir-965
112
113 2L . miRNA 243055 243076 . - . ID=MIMAT0005480;Alias=MIMAT0005480;Name=dme-miR-965-3p;Derives_from=MI0005821
114
115 2L . miRNA 243096 243118 . - . ID=MIMAT0020861;Alias=MIMAT0020861;Name=dme-miR-965-5p;Derives_from=MI0005821
116
117 2L . miRNA_primary_transcript 857542 857632 . + . ID=MI0005813;Alias=MI0005813;Name=dme-mir-375
118
119 2L . miRNA 857596 857617 . + . ID=MIMAT0005472;Alias=MIMAT0005472;Name=dme-miR-375-3p;Derives_from=MI0005813
120
121 2L . miRNA 857556 857579 . + . ID=MIMAT0020853;Alias=MIMAT0020853;Name=dme-miR-375-5p;Derives_from=MI0005813
122
123 2L . miRNA_primary_transcript 1831685 1831799 . - . ID=MI0011290;Alias=MI0011290;Name=dme-mir-2280
124
125 With name for mature miRNA (3rd column = miRNA) containing either the -3p or -5p string in the attribute Name (Name=dme-miR-965-3p, for instance)
126
127 ------
128
129 **Input formats**
130
131 1. One or sereral alignment files generated with sRbowtie tool and **renamed** according to the name of the biosample (avoid spaces in biosample labels)
132
133 .. class:: warningmark
134
135 Alignment datasets generated with sRbowtie must be renamed according to a biosample name
136
137 2. A GFF3 file retrieved from mirBase_
138
139 ------
140
141 **Outputs**
142
143 Two count list files for counts of reads aligned to pre-mir or mature miRNA
144
145 A pdf of pre-mir coverages. Red coverages indicate that the mir gene is in the genomic up strand, blue coverages indicate that the mir gene is in the genomic down strand.
146
147 </help>
148 </tool>