|
0
|
1 <tool id="Readmap" name="Generate readmap and histograms from alignment files" version="0.9.2">
|
|
|
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 readmap.py
|
|
|
7 #if $refGenomeSource.genomeSource == "history":
|
|
|
8 --reference_fasta ## sys.argv[2]
|
|
|
9 $refGenomeSource.ownFile ## index source
|
|
|
10 #else:
|
|
|
11 #silent reference= filter( lambda x: str( x[0] ) == str( $refGenomeSource.series[0].input.dbkey ), $__app__.tool_data_tables[ 'bowtie_indexes' ].get_fields() )[0][-1]
|
|
|
12 --reference_bowtie_index
|
|
|
13 $reference
|
|
|
14 #end if
|
|
|
15 --rcode
|
|
|
16 $plotCode
|
|
|
17 --output_readmap
|
|
|
18 $readmap_dataframe
|
|
|
19 --output_size_distribution
|
|
|
20 $size_distribution_dataframe
|
|
|
21 --minquery
|
|
|
22 $minquery
|
|
|
23 --maxquery
|
|
|
24 $maxquery
|
|
|
25 --input
|
|
|
26 #for $i in $refGenomeSource.series
|
|
|
27 $i.input
|
|
|
28 #end for
|
|
|
29 --ext
|
|
|
30 #for $i in $refGenomeSource.series
|
|
|
31 $i.input.ext
|
|
|
32 #end for
|
|
|
33 --label
|
|
|
34 #for $i in $refGenomeSource.series
|
|
|
35 "$i.input.name"
|
|
|
36 #end for
|
|
|
37 --normalization_factor
|
|
|
38 #for $i in $refGenomeSource.series
|
|
|
39 $i.norm
|
|
|
40 #end for
|
|
|
41 #if $gff:
|
|
|
42 --gff
|
|
|
43 $gff
|
|
|
44 #end if
|
|
|
45
|
|
|
46 </command>
|
|
|
47 <inputs>
|
|
|
48 <conditional name="refGenomeSource">
|
|
|
49 <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">
|
|
|
50 <option value="indexed">Use a built-in index</option>
|
|
|
51 <option value="history">Use one from the history</option>
|
|
|
52 </param>
|
|
|
53 <when value="indexed">
|
|
|
54 <repeat name="series" title="Add alignment files">
|
|
|
55 <param name="input" type="data" label="Select multiple alignments to parse">
|
|
|
56 <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."/>
|
|
|
57 </param>
|
|
|
58 <param name="norm" type="float" value="1" label="Indicate a normalization factor to compare multiple aligments"/>
|
|
|
59 </repeat>
|
|
|
60 </when>
|
|
|
61 <when value="history">
|
|
|
62 <repeat name="series" title="Add alignment files">
|
|
|
63 <param name="input" type="data" label="Select multiple alignments to parse"/>
|
|
|
64 <param name="norm" type="integer" value="1" label="Indicate a normalization factor to compare multiple aligments"/>
|
|
|
65 </repeat>
|
|
|
66 </when>
|
|
|
67 </conditional>
|
|
|
68 <param name="gff" type="data" optional="true" label="Optional: select a GFF to investigate regions of interest" help="GFF must match genome build"/>
|
|
|
69 <!-- <validator type="dataset_metadata_in_data_table" table_name="bowtie_indexes" metadata_name="dbkey" metadata_column="0" message="GFF database and alignment file databse do not match!"/> -->
|
|
|
70 <param name="minquery" type="integer" size="3" value="18" label="Min size of query small RNAs" help="'18' = 18 nucleotides"/>
|
|
|
71 <param name="maxquery" type="integer" size="3" value="28" label="Max size of query small RNAs" help="'28' = 28 nucleotides"/>
|
|
|
72 <param name="title" type="text" size="15" value= "Readmaps and size distributions" label="Main Titles"/>
|
|
|
73 <param name="xlabel" type="text" size="15" value="Coordinates/read size" label="x axis label"/>
|
|
|
74 <param name="ylabel" type="text" size="15" value="Number of reads" label="y axis label"/>
|
|
|
75 <param name="rows_per_page" type="text" size="9" value="8" label="How many items to display per page?">
|
|
|
76 <validator type="in_range" min="6" max="20" message="Select between 6 and 20 rows, as the readability will suffer otherwise."/>
|
|
|
77 </param>
|
|
|
78 </inputs>
|
|
|
79 <configfiles>
|
|
|
80 <configfile name="plotCode">
|
|
|
81 ## Setup R error handling to go to stderr
|
|
|
82 options( show.error.messages=F,
|
|
|
83 error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
|
|
|
84 library(RColorBrewer)
|
|
|
85 library(lattice)
|
|
|
86 library(latticeExtra)
|
|
|
87 library(grid)
|
|
|
88 library(gridExtra)
|
|
|
89 ##cheetahtemplate data frame implementation
|
|
|
90
|
|
|
91 rm=read.delim("${readmap_dataframe}", header=T, row.names=NULL)
|
|
|
92 pdf(file="${readmap_PDF}", paper="special", height=11.69, width=8.2677)
|
|
|
93 n_samples=length(unique(rm\$sample))
|
|
|
94
|
|
|
95 genes=unique(levels(rm\$gene))
|
|
|
96 per_gene_readmap=lapply(genes, function(x) subset(rm, gene==x))
|
|
|
97 n_genes=length(per_gene_readmap)
|
|
|
98
|
|
|
99
|
|
|
100 par.settings.readmap=list(layout.heights=list(top.padding=0, bottom.padding=-3), fontsize = list(text=96/${rows_per_page}, points=8))
|
|
|
101 par.settings.size=list(layout.heights=list(top.padding=-1, bottom.padding=-3), fontsize = list(text=96/${rows_per_page}, points=8))
|
|
|
102 par.settings.combination.readmap=list(layout.heights=list(top.padding=0, bottom.padding=-3), fontsize = list(text=96/${rows_per_page}, points=8))
|
|
|
103 par.settings.combination.size=list(layout.heights=list(top.padding=-2, bottom.padding=-0.5), fontsize = list(text=96/${rows_per_page}, points=8))
|
|
|
104
|
|
|
105
|
|
|
106 plot_readmap=function(df, ...) {
|
|
|
107 combineLimits(xyplot(count~coord|factor(sample, levels=unique(sample))+reorder(gene, count, function(x) -sum(abs(x))),
|
|
|
108 data=df,
|
|
|
109 type='h',
|
|
|
110 scales= list(relation="free", x=list(rot=0, cex=0.75, axs="i", tck=0.5), y=list(tick.number=4, rot=90, cex=0.75)),
|
|
|
111 xlab=NULL, main=NULL, ylab=NULL,
|
|
|
112 as.table=T,
|
|
|
113 origin = 0,
|
|
|
114 horizontal=FALSE,
|
|
|
115 group=polarity,
|
|
|
116 col=c("red","blue"),
|
|
|
117 ...))
|
|
|
118 }
|
|
|
119
|
|
|
120 plot_size_distribution= function(df, ...) {
|
|
|
121 smR.prepanel=function(x,y,...){; yscale=c(-max(abs(y)), max(abs(y)));list(ylim=yscale);}
|
|
|
122 bc= barchart(count~as.factor(size)|factor(sample, levels=unique(sample))+gene, data = df, origin = 0,
|
|
|
123 horizontal=FALSE,
|
|
|
124 group=polarity,
|
|
|
125 stack=TRUE,
|
|
|
126 col=c('red', 'blue'),
|
|
|
127 cex=0.75,
|
|
|
128 scales=list(y=list(tick.number=4, rot=90, relation="free"), cex=0.75),
|
|
|
129 prepanel=smR.prepanel,
|
|
|
130 xlab = NULL,
|
|
|
131 ylab = NULL,
|
|
|
132 # par.settings=list(layout.heights=list(top.padding=-2, bottom.padding=-3), fontsize = list(text=8, points=8)),
|
|
|
133 main = NULL , as.table=TRUE, newpage = T, ...)
|
|
|
134 combineLimits(bc)
|
|
|
135 }
|
|
|
136
|
|
|
137 for (i in seq(1,n_genes,${rows_per_page})) {
|
|
|
138 start=i
|
|
|
139 end=i+${rows_per_page}-1
|
|
|
140 if (end>n_genes) {end=n_genes}
|
|
|
141 readmap_plot.list=lapply(per_gene_readmap[start:end], function(x) plot_readmap(x, par.settings=par.settings.readmap))
|
|
|
142 args.list=c(readmap_plot.list, list(nrow=${rows_per_page}, ncol=1, main="readmaps", left="${ylabel}", sub="readmap coordinate"))
|
|
|
143 do.call(grid.arrange, args.list)
|
|
|
144 }
|
|
|
145
|
|
|
146 devname=dev.off()
|
|
|
147
|
|
|
148 size=read.delim("${size_distribution_dataframe}", header=T, row.names=NULL)
|
|
|
149 per_gene_size=lapply(genes, function(x) subset(size, gene==x))
|
|
|
150
|
|
|
151 pdf(file="${size_PDF}", paper="special", height=11.69, width=8.2677)
|
|
|
152
|
|
|
153 for (i in seq(1,n_genes,${rows_per_page})) {
|
|
|
154 start=i
|
|
|
155 end=i+${rows_per_page}-1
|
|
|
156 if (end>n_genes) {end=n_genes}
|
|
|
157 plot.list=lapply(per_gene_size[start:end], function(x) plot_size_distribution(x, par.settings=par.settings.size))
|
|
|
158 args.list=c(plot.list, list(nrow=${rows_per_page}, ncol=1, main="size distribution", left="${ylabel}", sub="readsize in nucleotides"))
|
|
|
159 do.call(grid.arrange, args.list)
|
|
|
160 }
|
|
|
161
|
|
|
162 devname=dev.off()
|
|
|
163
|
|
|
164 pdf(file="${combi_PDF}", paper="special", height=11.69, width=8.2677)
|
|
|
165
|
|
|
166 for (i in seq(1,n_genes,${rows_per_page}/2)) {
|
|
|
167 start=i
|
|
|
168 end=i+${rows_per_page}/2-1
|
|
|
169 if (end>n_genes) {end=n_genes}
|
|
|
170 read_plot.list=lapply(per_gene_readmap[start:end], function(x) plot_readmap(x, par.settings=par.settings.combination.readmap))
|
|
|
171 size_plot.list=lapply(per_gene_size[start:end], function(x) plot_size_distribution(x, strip=FALSE, par.settings=par.settings.combination.size))
|
|
|
172 plot.list=rbind(read_plot.list, size_plot.list )
|
|
|
173 args.list=c(plot.list, list(nrow=${rows_per_page}, ncol=1, main="${title}", left="${ylabel}", sub="${xlabel}"))
|
|
|
174 do.call(grid.arrange, args.list)
|
|
|
175 }
|
|
|
176
|
|
|
177 devname=dev.off()
|
|
|
178
|
|
|
179
|
|
|
180 </configfile>
|
|
|
181 </configfiles>
|
|
|
182
|
|
|
183 <outputs>
|
|
|
184 <data format="tabular" name="readmap_dataframe" label="Readmap dataframe"/>
|
|
|
185 <data format="tabular" name="size_distribution_dataframe" label="Size distribution dataframe"/>
|
|
|
186 <data format="pdf" name="readmap_PDF" label="Readmaps"/>
|
|
|
187 <data format="pdf" name="size_PDF" label="Size distribution"/>
|
|
|
188 <data format="pdf" name="combi_PDF" label="Size distribution and Readmaps"/>
|
|
|
189 </outputs>
|
|
|
190 <help>
|
|
|
191
|
|
|
192 **What it does**
|
|
|
193
|
|
|
194 Takes one or more alignment files (BAM, SAM or tabular bowtie output) as input and produces a "Readmap",
|
|
|
195 where by default for each "chromosome" the position of the read is recorded on the x-axis, and the y-axis indicates
|
|
|
196 the number of reads per position. Reads that map in sense are on the top, reads that map antisense are on the bottom.
|
|
|
197
|
|
|
198
|
|
|
199 .. class:: warningmark
|
|
|
200
|
|
|
201 '''TIP''' The input data can be produced using the sRbowtie tool.
|
|
|
202
|
|
|
203 ----
|
|
|
204
|
|
|
205 '''Example'''
|
|
|
206
|
|
|
207 Query sequence::
|
|
|
208 For a SAM file as the following:
|
|
|
209
|
|
|
210 5 16 2L_79 24393 255 17M * 0 0 CCTTCATCTTTTTTTTT IIIIIIIIIIIIIIIII XA:i:0 MD:Z:17 NM:i:0
|
|
|
211
|
|
|
212 11 0 2R_1 12675 255 21M * 0 0 AAAAAAAACGCGTCCTTGTGC IIIIIIIIIIIIIIIIIIIII XA:i:0 MD:Z:21 NM:i:0
|
|
|
213
|
|
|
214 2 16 2L_5 669 255 23M * 0 0 TGTTGCTGCATTTCTTTTTTTTT IIIIIIIIIIIIIIIIIIIIIII XA:i:0 MD:Z:23 NM:i:0
|
|
|
215
|
|
|
216 produce a plot like this:
|
|
|
217
|
|
|
218 ----
|
|
|
219
|
|
|
220 .. image:: static/images/readmap.png
|
|
|
221 :height: 800
|
|
|
222 :width: 500
|
|
|
223
|
|
|
224 </help>
|
|
|
225 </tool>
|
