Mercurial > repos > drosofff > msp_sr_signature

comparison signature.xml @ 0:d613dbee3ce4

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author drosofff
date Mon, 03 Nov 2014 10:29:28 -0500
parents
children 9274c7b1e85c
comparison
equal deleted inserted replaced
-1:000000000000 0:d613dbee3ce4
1 <tool id="signature" name="Small RNA Signatures" version="2.0.0">
2 <description></description>
3 <requirements>
4 <requirement type="package" version="0.12.7">bowtie</requirement>
5 <requirement type="package" version="0.1.18">samtools</requirement>
6 <requirement type="package" version="0.7.7">pysam</requirement>
7 <requirement type="package" version="2.14">biocbasics</requirement>
8 <requirement type="package" version="3.0.3">R</requirement>
9 </requirements>
10 <command interpreter="python">
11 signature.py
12 --input $refGenomeSource.input
13 --inputFormat $refGenomeSource.input.ext
14 --minquery $minquery
15 --maxquery $maxquery
16 --mintarget $mintarget
17 --maxtarget $maxtarget
18 --minscope $minscope
19 --maxscope $maxscope
20 --outputOverlapDataframe $output
21 #if $refGenomeSource.genomeSource == "history":
22 --referenceGenome $refGenomeSource.ownFile
23 #else:
24 #silent reference= filter( lambda x: str( x[0] ) == str( $input.dbkey ), $__app__.tool_data_tables[ 'bowtie_indexes' ].get_fields() )[0][-1]
25 --referenceGenome $reference
26 --extract_index
27 #end if
28 --graph $graph_type
29 --rcode $sigplotter
30 </command>
31
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" type="data" format="tabular,sam,bam" label="Compute signature from this bowtie standard output">
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="ownFile" type="data" format="fasta" label="Select the fasta reference" />
45 <param name="input" type="data" format="tabular,sam,bam" label="Compute signature from this bowtie standard output"/>
46 </when>
47 </conditional> <!-- refGenomeSource -->
48 <param name="minquery" type="integer" size="3" value="23" label="Min size of query small RNAs" help="'23' = 23 nucleotides"/>
49 <param name="maxquery" type="integer" size="3" value="29" label="Max size of query small RNAs" help="'29' = 29 nucleotides"/>
50 <param name="mintarget" type="integer" size="3" value="23" label="Min size of target small RNAs" help="'23' = 23 nucleotides"/>
51 <param name="maxtarget" type="integer" size="3" value="29" label="Max size of target small RNAs" help="'29' = 29 nucleotides"/>
52 <param name="minscope" type="integer" size="3" value="1" label="Minimal relative overlap analyzed" help="'1' = 1 nucleotide overlap"/>
53 <param name="maxscope" type="integer" size="3" value="26" label="Maximal relative overlap analyzed" help="'1' = 1 nucleotide overlap"/>
54 <param name="graph_type" type="select" label="Graph type" help="Signature can be computed globally or by item present in the alignment file">
55 <option value="global" selected="True">Global</option>
56 <option value="lattice">Lattice</option>
57 </param>
58 </inputs>
59
60 <configfiles>
61 <configfile name="sigplotter">
62 graph_type = "${graph_type}"
63
64 globalgraph = function () {
65 ## Setup R error handling to go to stderr
66 options( show.error.messages=F,
67 error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
68 signature = read.delim("${output}", header=TRUE)
69 signaturez=(signature[,2] -mean(signature[,2]))/sd(signature[,2])
70 YLIM=max(signature[,2])
71
72 ## Open output2 PDF file
73 pdf( "${output2}" )
74 par(mfrow=c(2,2),oma = c(0, 0, 3, 0))
75
76 plot(signature[,1:2], type = "h", main="Numbers of pairs", cex.main=1, xlab="overlap (nt)", ylim=c(0,YLIM), ylab="Numbers of pairs", col="darkslateblue", lwd=4)
77
78 plot(signaturez, type = "l", main="Number of pairs Z-scores", cex.main=1, xlab="overlap (nt)", ylab="z-score", pch=19, cex=0.2, col="darkslateblue", lwd=2, cex.lab=1, cex.axis=1, xaxt="n")
79 axis(1, at=seq(from=1, to=length(signature[,1]), by=3) )
80
81 plot(signature[,1], signature[,3]*100, type = "l", main="Overlap probabilities",
82 cex.main=1, xlab="overlap (nt)", ylab="Probability [%]", ylim=c(0,50),
83 pch=19, col="darkslateblue", lwd=2, cex.lab=1, cex.axis=1, xaxt="n")
84 axis(1, at=seq(from=1, to=length(signature[,1]), by=3) )
85
86 overlap_prob_z=(signature[,3] -mean(signature[,3]))/sd(signature[,3])
87 plot(overlap_prob_z, type = "l", main="Overlap Probability Z-scores", cex.main=1, xlab="overlap (nt)", ylab="z-score", pch=19, cex=0.2, col="darkslateblue", lwd=2, cex.lab=1, cex.axis=1, xaxt="n")
88 axis(1, at=seq(from=1, to=length(signature[,1]), by=3) )
89
90 mtext("Overlap Signatures of ${minquery}-${maxquery} against ${mintarget}-${maxtarget}nt small RNAs", outer = TRUE, cex=1)
91 devname = dev.off()
92 ## Close the PDF file
93 }
94
95 treillisgraph = function () {
96 ## Open output2 PDF file
97 pdf( "${output2}", paper="special", height=11.69, width=8.2677 )
98 signature = read.delim("${output}", header=TRUE)
99 options( show.error.messages=F,
100 error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
101 library(lattice)
102 print (xyplot(signature[,3]*100~signature[,1]|signature[,4], type = "l", xlim=c(1,26), main="ping-pong Signature of ${minquery}-${maxquery} against ${mintarget}-${maxtarget}nt small RNAs",
103 par.strip.text=list(cex=.5), strip=strip.custom(which.given=1, bg="lightblue"), scales=list(cex=0.5),
104 cex.main=1, cex=.5, xlab="overlap (nt)", ylab="ping-pong signal [%]",
105 pch=19, col="darkslateblue", lwd =1.5, cex.lab=1.2, cex.axis=1.2,
106 layout=c(4,12), as.table=TRUE, newpage = T) )
107 devnname = dev.off()
108 }
109
110 if (graph_type=="global") {
111 globalgraph()
112
113 }
114 if(graph_type=="lattice") {
115 treillisgraph()
116 }
117 </configfile>
118 </configfiles>
119
120 <outputs>
121 <data name="output" format="tabular" label = "signature data frame"/>
122 <data name="output2" format="pdf" label="Overlap probabilities"/>
123 </outputs>
124
125 <help>
126
127 **What it does**
128
129 This tool computes the number of pairs by overlap classes (in nt) from a bowtie output file, the z-score calculated from these numbers of pairs, and the ping-pong signal as described in Brennecke et al (2009) Science.
130 The numerical options set the min and max size of both the query small rna class and the target small rna class
131 Three type of signals are plotted in separate pdf files, the number of pairs founds, the z-score calculated from these numbers of pairs, and the ping-pong signal as described in Brennecke et al (2009) Science.
132
133 </help>
134
135 <test>
136 <param name="genomeSource" value="history" />
137 <param name="ownFile" value ="transposons.fasta" ftype="fasta" />
138 <param name="input" value="sr_bowtie.output" ftype="tabular" />
139 <param name="minquery" value="23" />
140 <param name="maxquery" value="29" />
141 <param name="mintarget" value="23" />
142 <param name="maxtarget" value="29" />
143 <param name="minscope" value="1" />
144 <param name="maxscope" value="26" />
145 <param name="graph_type" value="global" />
146 <output name="readmap_dataframe" ftype="tabular" value="signature_data_frame.tab"/>
147 <output name="readmap_PDF" ftype="pdf" value="Overlap_probabilities.pdf"/>
148 </test>
149
150
151
152 </tool>
153