|
25
|
1 <?xml version="1.0" encoding="UTF-8"?>
|
|
|
2 <tool id="edger_dge" name="edgeR: Differential Gene(Expression) Analysis">
|
|
|
3 <description>RNA-Seq gene expression analysis using edgeR (R package)</description>
|
|
|
4
|
|
|
5 <requirements>
|
|
33
|
6 <requirement type="package" version="3.0.3">R</requirement>
|
|
29
|
7 <requirement type="package" version="latest">package_biocLite_edgeR_limma</requirement>
|
|
25
|
8 </requirements>
|
|
|
9
|
|
|
10 <command>
|
|
|
11 <!--
|
|
|
12 The following script is written in the "Cheetah" language:
|
|
|
13 http://www.cheetahtemplate.org/docs/users_guide_html_multipage/contents.html
|
|
|
14 -->
|
|
|
15
|
|
|
16 R --vanilla --slave -f $R_script '--args
|
|
|
17 $expression_matrix
|
|
|
18 $design_matrix
|
|
|
19 $contrast
|
|
|
20
|
|
|
21 $fdr
|
|
|
22
|
|
|
23 $output_count_edgeR
|
|
|
24 $output_cpm
|
|
|
25
|
|
|
26 /dev/null <!-- Calculation of FPKM/RPKM should come here -->
|
|
|
27
|
|
|
28 #if $output_raw_counts:
|
|
|
29 $output_raw_counts
|
|
|
30 #else:
|
|
|
31 /dev/null
|
|
|
32 #end if
|
|
|
33
|
|
|
34 #if $output_MDSplot:
|
|
|
35 $output_MDSplot
|
|
|
36 #else:
|
|
|
37 /dev/null
|
|
|
38 #end if
|
|
|
39
|
|
|
40 #if $output_BCVplot:
|
|
|
41 $output_BCVplot
|
|
|
42 #else:
|
|
|
43 /dev/null
|
|
|
44 #end if
|
|
|
45
|
|
|
46 #if $output_MAplot:
|
|
|
47 $output_MAplot
|
|
|
48 #else:
|
|
|
49 /dev/null
|
|
|
50 #end if
|
|
|
51
|
|
|
52 #if $output_PValue_distribution_plot:
|
|
|
53 $output_PValue_distribution_plot
|
|
|
54 #else:
|
|
|
55 /dev/null
|
|
|
56 #end if
|
|
|
57
|
|
|
58 #if $output_hierarchical_clustering_plot:
|
|
|
59 $output_hierarchical_clustering_plot
|
|
|
60 #else:
|
|
|
61 /dev/null
|
|
|
62 #end if
|
|
|
63
|
|
|
64 #if $output_heatmap_plot:
|
|
|
65 $output_heatmap_plot
|
|
|
66 #else:
|
|
|
67 /dev/null
|
|
|
68 #end if
|
|
|
69
|
|
|
70 #if $output_RData_obj:
|
|
|
71 $output_RData_obj
|
|
|
72 #else:
|
|
|
73 /dev/null
|
|
|
74 #end if
|
|
|
75 '
|
|
|
76 #if $output_R:
|
|
|
77 > $output_R
|
|
|
78 #else:
|
|
|
79 > /dev/null
|
|
|
80 #end if
|
|
|
81
|
|
|
82 2> stderr.txt
|
|
|
83 ;
|
|
|
84 grep -v 'Calculating library sizes from column' stderr.txt 1>&2
|
|
|
85
|
|
|
86 </command>
|
|
|
87
|
|
|
88 <inputs>
|
|
|
89 <param name="expression_matrix" type="data" format="tabular" label="Expression (read count) matrix" />
|
|
|
90 <param name="design_matrix" type="data" format="tabular" label="Design matrix" hepl="Ensure your samplenames are identical to those in the expression matrix. Preferentially, create the contrast matrix using 'edgeR: Design- from Expression matrix'." />
|
|
|
91
|
|
|
92 <param name="contrast" type="text" label="Contrast (biological question)" help="e.g. 'tumor-normal' or '(G1+G2)/2-G3' using the factors chosen in the design matrix. Read the 'makeContrasts' manual from Limma package for more info: http://www.bioconductor.org/packages/release/bioc/html/limma.html and http://www.bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf." />
|
|
|
93
|
|
|
94 <param name="fdr" type="float" min="0" max="1" value="0.05" label="False Discovery Rate (FDR)" />
|
|
|
95
|
|
|
96 <param name="outputs" type="select" label="Optional desired outputs" multiple="true" display="checkboxes">
|
|
|
97 <option value="make_output_raw_counts">Raw counts table</option>
|
|
|
98 <option value="make_output_MDSplot">MDS-plot</option>
|
|
|
99 <option value="make_output_BCVplot">BCV-plot</option>
|
|
|
100 <option value="make_output_MAplot">MA-plot</option>
|
|
|
101 <option value="make_output_PValue_distribution_plot">P-Value distribution plot</option>
|
|
|
102 <option value="make_output_hierarchical_clustering_plot">Hierarchical custering</option>
|
|
|
103 <option value="make_output_heatmap_plot">Heatmap</option>
|
|
|
104
|
|
43
|
105 <option value="make_output_R_stdout">R stdout</option>
|
|
25
|
106 <option value="make_output_RData_obj">R Data object</option>
|
|
|
107 </param>
|
|
|
108 </inputs>
|
|
|
109
|
|
|
110 <configfiles>
|
|
|
111 <configfile name="R_script">
|
|
|
112 library(limma,quietly=TRUE) ## enable quietly to avoid unnecessaity stderr dumping
|
|
|
113 library(edgeR,quietly=TRUE) ## enable quietly to avoid unnecessaity stderr dumping
|
|
|
114 library(splines,quietly=TRUE) ## enable quietly to avoid unnecessaity stderr dumping
|
|
|
115
|
|
|
116 ## Fetch commandline arguments
|
|
|
117 args <- commandArgs(trailingOnly = TRUE)
|
|
|
118
|
|
|
119 expression_matrix_file = args[1]
|
|
|
120 design_matrix_file = args[2]
|
|
|
121 contrast = args[3]
|
|
|
122
|
|
|
123 fdr = args[4]
|
|
|
124
|
|
|
125 output_count_edgeR = args[5]
|
|
|
126 output_cpm = args[6]
|
|
|
127
|
|
43
|
128 output_xpkm = args[7] ##FPKM file - yet to be implemented
|
|
25
|
129
|
|
|
130 output_raw_counts = args[8]
|
|
|
131 output_MDSplot = args[9]
|
|
|
132 output_BCVplot = args[10]
|
|
|
133 output_MAplot = args[11]
|
|
|
134 output_PValue_distribution_plot = args[12]
|
|
|
135 output_hierarchical_clustering_plot = args[13]
|
|
|
136 output_heatmap_plot = args[14]
|
|
|
137 output_RData_obj = args[15]
|
|
|
138
|
|
|
139
|
|
|
140 library(edgeR)
|
|
|
141 ##raw_data <- read.delim(designmatrix,header=T,stringsAsFactors=T)
|
|
|
142 ## Obtain read-counts
|
|
|
143
|
|
|
144 expression_matrix <- read.delim(expression_matrix_file,header=T,stringsAsFactors=F,row.names=1,check.names=FALSE,na.strings=c(""))
|
|
|
145 design_matrix <- read.delim(design_matrix_file,header=T,stringsAsFactors=F,row.names=1,check.names=FALSE,na.strings=c(""))
|
|
|
146
|
|
|
147 colnames(design_matrix) <- make.names(colnames(design_matrix))
|
|
|
148
|
|
|
149 for(i in 1:ncol(design_matrix)) {
|
|
|
150 old = design_matrix[,i]
|
|
|
151 design_matrix[,i] = make.names(design_matrix[,i])
|
|
|
152 if(paste(design_matrix[,i],collapse="\t") != paste(old,collapse="\t")) {
|
|
|
153 print("Renaming of factors:")
|
|
|
154 print(old)
|
|
|
155 print("To:")
|
|
|
156 print(design_matrix[,i])
|
|
|
157 }
|
|
|
158 design_matrix[,i] <- as.factor(design_matrix[,i])
|
|
|
159 }
|
|
|
160
|
|
44
|
161 ## 1) In the expression matrix, you only want to have the samples described in the design matrix
|
|
25
|
162 columns <- match(rownames(design_matrix),colnames(expression_matrix))
|
|
43
|
163 columns <- columns[!is.na(columns)]
|
|
25
|
164 read_counts <- expression_matrix[,columns]
|
|
|
165
|
|
44
|
166 ## 2) In the design matrix, you only want to have samples of which you really have the counts
|
|
|
167 columns <- match(colnames(expression_matrix),rownames(design_matrix))
|
|
|
168 columns <- columns[!is.na(columns)]
|
|
|
169 design_matrix <- design_matrix[columns,,drop=FALSE]
|
|
25
|
170
|
|
|
171 ## Filter for HTSeq predifined counts:
|
|
|
172 exclude_HTSeq <- c("no_feature","ambiguous","too_low_aQual","not_aligned","alignment_not_unique")
|
|
|
173 exclude_DEXSeq <- c("_ambiguous","_empty","_lowaqual","_notaligned")
|
|
|
174
|
|
44
|
175 exclude <- match(c(exclude_HTSeq, exclude_DEXSeq),rownames(read_counts))
|
|
|
176 exclude <- exclude[is.na(exclude)==0]
|
|
25
|
177 if(length(exclude) != 0) {
|
|
44
|
178 read_counts <- read_counts[-exclude,]
|
|
25
|
179 }
|
|
|
180
|
|
|
181
|
|
44
|
182 empty_samples <- apply(read_counts,2,function(x) sum(x) == 0)
|
|
25
|
183 if(sum(empty_samples) > 0) {
|
|
|
184 write(paste("There are ",sum(empty_samples)," empty samples found:",sep=""),stderr())
|
|
|
185 write(colnames(read_counts)[empty_samples],stderr())
|
|
|
186 } else {
|
|
|
187
|
|
|
188 dge <- DGEList(counts=read_counts,genes=rownames(read_counts))
|
|
|
189
|
|
|
190 formula <- paste(c("~0",make.names(colnames(design_matrix))),collapse = " + ")
|
|
|
191 design_matrix_tmp <- design_matrix
|
|
|
192 colnames(design_matrix_tmp) <- make.names(colnames(design_matrix_tmp))
|
|
|
193 design <- model.matrix(as.formula(formula),design_matrix_tmp)
|
|
|
194 rm(design_matrix_tmp)
|
|
|
195
|
|
|
196 # Filter prefixes
|
|
|
197 prefixes = colnames(design_matrix)[attr(design,"assign")]
|
|
|
198 avoid = nchar(prefixes) == nchar(colnames(design))
|
|
|
199 replacements = substr(colnames(design),nchar(prefixes)+1,nchar(colnames(design)))
|
|
|
200 replacements[avoid] = colnames(design)[avoid]
|
|
|
201 colnames(design) = replacements
|
|
|
202
|
|
|
203 # Do normalization
|
|
|
204 write("Calculating normalization factors...",stdout())
|
|
|
205 dge <- calcNormFactors(dge)
|
|
|
206 write("Estimating common dispersion...",stdout())
|
|
|
207 dge <- estimateGLMCommonDisp(dge,design)
|
|
|
208 write("Estimating trended dispersion...",stdout())
|
|
|
209 dge <- estimateGLMTrendedDisp(dge,design)
|
|
|
210 write("Estimating tagwise dispersion...",stdout())
|
|
|
211 dge <- estimateGLMTagwiseDisp(dge,design)
|
|
|
212
|
|
|
213
|
|
|
214 if(output_MDSplot != "/dev/null") {
|
|
|
215 write("Creating MDS plot",stdout())
|
|
|
216 ##points <- plotMDS(dge,method="bcv",labels=rep("",nrow(dge\$samples)))# Get coordinates of unflexible plot
|
|
|
217 points <- plotMDS.DGEList(dge,labels=rep("",nrow(dge\$samples)))# Get coordinates of unflexible plot
|
|
|
218 dev.off()# Kill it
|
|
|
219
|
|
|
220 pdf(output_MDSplot)
|
|
|
221 diff_x <- abs(max(points\$x)-min(points\$x))
|
|
|
222 diff_y <-(max(points\$y)-min(points\$y))
|
|
|
223 plot(c(min(points\$x),max(points\$x) + 0.45 * diff_x), c(min(points\$y) - 0.05 * diff_y,max(points\$y) + 0.05 * diff_y), main="edgeR MDS Plot",type="n", xlab="BCV distance 1", ylab="BCV distance 2")
|
|
|
224 points(points\$x,points\$y,pch=20)
|
|
|
225 text(points\$x, points\$y,rownames(dge\$samples),cex=0.7,col="gray",pos=4)
|
|
|
226 rm(diff_x,diff_y)
|
|
|
227
|
|
|
228 dev.off()
|
|
|
229 }
|
|
|
230
|
|
|
231 if(output_BCVplot != "/dev/null") {
|
|
|
232 write("Creating Biological coefficient of variation plot",stdout())
|
|
|
233 pdf(output_BCVplot)
|
|
|
234 plotBCV(dge, cex=0.4, main="edgeR: Biological coefficient of variation (BCV) vs abundance")
|
|
|
235 dev.off()
|
|
|
236 }
|
|
|
237
|
|
|
238
|
|
|
239 write("Fitting GLM...",stdout())
|
|
|
240 fit <- glmFit(dge,design)
|
|
|
241
|
|
|
242 write(paste("Performing likelihood ratio test: ",contrast,sep=""),stdout())
|
|
|
243 cont <- c(contrast)
|
|
|
244 cont <- makeContrasts(contrasts=cont, levels=design)
|
|
|
245
|
|
|
246 lrt <- glmLRT(fit, contrast=cont[,1])
|
|
|
247 write(paste("Exporting to file: ",output_count_edgeR,sep=""),stdout())
|
|
|
248 write.table(file=output_count_edgeR,topTags(lrt,n=nrow(read_counts))\$table,sep="\t",row.names=TRUE,col.names=NA)
|
|
|
249 write.table(file=output_cpm,cpm(dge,normalized.lib.sizes=TRUE),sep="\t",row.names=TRUE,col.names=NA)
|
|
|
250
|
|
|
251 ## todo EXPORT FPKM
|
|
|
252 write.table(file=output_raw_counts,dge\$counts,sep="\t",row.names=TRUE,col.names=NA)
|
|
|
253
|
|
|
254
|
|
34
|
255 if(output_MAplot != "/dev/null" || output_PValue_distribution_plot != "/dev/null") {
|
|
25
|
256 etable <- topTags(lrt, n=nrow(dge))\$table
|
|
|
257 etable <- etable[order(etable\$FDR), ]
|
|
32
|
258
|
|
|
259 if(output_MAplot != "/dev/null") {
|
|
|
260 write("Creating MA plot...",stdout())
|
|
|
261 pdf(output_MAplot)
|
|
|
262 with(etable, plot(logCPM, logFC, pch=20, main="edgeR: Fold change vs abundance"))
|
|
|
263 with(subset(etable, FDR < fdr), points(logCPM, logFC, pch=20, col="red"))
|
|
|
264 abline(h=c(-1,1), col="blue")
|
|
|
265 dev.off()
|
|
|
266 }
|
|
25
|
267
|
|
32
|
268 if(output_PValue_distribution_plot != "/dev/null") {
|
|
|
269 write("Creating P-value distribution plot...",stdout())
|
|
|
270 pdf(output_PValue_distribution_plot)
|
|
|
271 expressed_genes <- subset(etable, PValue < 0.99)
|
|
|
272 h <- hist(expressed_genes\$PValue,breaks=nrow(expressed_genes)/15,main="Binned P-Values (< 0.99)")
|
|
|
273 center <- sum(h\$counts) / length(h\$counts)
|
|
|
274 lines(c(0,1),c(center,center),lty=2,col="red",lwd=2)
|
|
|
275 k <- ksmooth(h\$mid, h\$counts)
|
|
|
276 lines(k\$x,k\$y,col="red",lwd=2)
|
|
|
277 rmsd <- (h\$counts) - center
|
|
|
278 rmsd <- rmsd^2
|
|
|
279 rmsd <- sum(rmsd)
|
|
|
280 rmsd <- sqrt(rmsd)
|
|
|
281 text(0,max(h\$counts),paste("e=",round(rmsd,2),sep=""),pos=4,col="blue")
|
|
|
282 ## change e into epsilon somehow
|
|
|
283 dev.off()
|
|
|
284 }
|
|
40
|
285 }
|
|
|
286
|
|
|
287 if(output_heatmap_plot != "/dev/null") {
|
|
42
|
288 pdf(output_heatmap_plot,width=10.5)
|
|
40
|
289 etable2 <- topTags(lrt, n=100)\$table
|
|
|
290 order <- rownames(etable2)
|
|
|
291 cpm_sub <- cpm(dge,normalized.lib.sizes=TRUE,log=TRUE)[as.numeric(order),]
|
|
|
292 heatmap(t(cpm_sub))
|
|
|
293 dev.off()
|
|
25
|
294 }
|
|
|
295
|
|
|
296 ##output_hierarchical_clustering_plot = args[13]
|
|
|
297
|
|
35
|
298 if(output_RData_obj != "/dev/null") {
|
|
25
|
299 save.image(output_RData_obj)
|
|
|
300 }
|
|
|
301
|
|
|
302 write("Done!",stdout())
|
|
|
303 }
|
|
|
304 </configfile>
|
|
|
305 </configfiles>
|
|
|
306
|
|
|
307 <outputs>
|
|
|
308 <data format="tabular" name="output_count_edgeR" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - differtially expressed genes" />
|
|
|
309 <data format="tabular" name="output_cpm" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - CPM" />
|
|
|
310
|
|
|
311 <data format="tabular" name="output_raw_counts" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - raw counts">
|
|
|
312 <filter>("make_output_raw_counts" in outputs)</filter>
|
|
|
313 </data>
|
|
|
314
|
|
|
315 <data format="pdf" name="output_MDSplot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MDS-plot">
|
|
|
316 <filter>("make_output_MDSplot" in outputs)</filter>
|
|
|
317 </data>
|
|
|
318
|
|
|
319 <data format="pdf" name="output_BCVplot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - BCV-plot">
|
|
|
320 <filter>("make_output_BCVplot" in outputs)</filter>
|
|
|
321 </data>
|
|
|
322
|
|
|
323 <data format="pdf" name="output_MAplot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MA-plot">
|
|
|
324 <filter>("make_output_MAplot" in outputs)</filter>
|
|
|
325 </data>
|
|
|
326
|
|
|
327 <data format="pdf" name="output_PValue_distribution_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - P-Value distribution">
|
|
|
328 <filter>("make_output_PValue_distribution_plot" in outputs)</filter>
|
|
|
329 </data>
|
|
|
330
|
|
|
331 <data format="pdf" name="output_hierarchical_clustering_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - Hierarchical custering">
|
|
|
332 <filter>("make_output_hierarchical_clustering_plot" in outputs)</filter>
|
|
|
333 </data>
|
|
|
334
|
|
|
335 <data format="pdf" name="output_heatmap_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - Heatmap">
|
|
|
336 <filter>("make_output_heatmap_plot" in outputs)</filter>
|
|
|
337 </data>
|
|
|
338
|
|
|
339 <data format="RData" name="output_RData_obj" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - R data object">
|
|
40
|
340 <filter>("make_output_RData_obj" in outputs)</filter>
|
|
25
|
341 </data>
|
|
|
342
|
|
40
|
343 <data format="txt" name="output_R" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - R output (debug)" >
|
|
43
|
344 <filter>("make_output_R_stdout" in outputs)</filter>
|
|
25
|
345 </data>
|
|
|
346 </outputs>
|
|
|
347
|
|
|
348 <help>
|
|
|
349 edgeR: Differential Gene(Expression) Analysis
|
|
36
|
350 #############################################
|
|
25
|
351
|
|
36
|
352 Overview
|
|
|
353 --------
|
|
|
354 Differential expression analysis of RNA-seq and digital gene expression profiles with biological replication. Uses empirical Bayes estimation and exact tests based on the negative binomial distribution. Also useful for differential signal analysis with other types of genome-scale count data [1].
|
|
25
|
355
|
|
|
356 For every experiment, the algorithm requires a design matrix. This matrix describes which samples belong to which groups.
|
|
36
|
357 More details on this are given in the edgeR manual: http://www.bioconductor.org/packages/2.12/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf
|
|
25
|
358 and the limma manual.
|
|
|
359
|
|
|
360 Because the creation of a design matrix can be complex and time consuming, especially if no GUI is used, this package comes with an alternative tool which can help you with it.
|
|
|
361 This tool is called *edgeR Design Matrix Creator*.
|
|
|
362 If the appropriate design matrix (with corresponding links to the files) is given,
|
|
|
363 the correct contrast ( http://en.wikipedia.org/wiki/Contrast_(statistics) ) has to be given.
|
|
|
364
|
|
|
365 If you have for example two groups, with an equal weight, you would like to compare either
|
|
|
366 "g1~g2" or "normal~cancer".
|
|
|
367
|
|
36
|
368 The test function makes use of a MCF7 dataset used in a study that indicates that a higher sequencing depth is not neccesairily more important than a higher amount of replaciates[2].
|
|
25
|
369
|
|
36
|
370 Input
|
|
|
371 -----
|
|
|
372 Expression matrix
|
|
|
373 ^^^^^^^^^^^^^^^^^
|
|
|
374 ::
|
|
25
|
375
|
|
|
376 Geneid "\t" Sample-1 "\t" Sample-2 "\t" Sample-3 "\t" Sample-4 [...] "\n"
|
|
|
377 SMURF "\t" 123 "\t" 21 "\t" 34545 "\t" 98 ... "\n"
|
|
|
378 BRCA1 "\t" 435 "\t" 6655 "\t" 45 "\t" 55 ... "\n"
|
|
|
379 LINK33 "\t" 4 "\t" 645 "\t" 345 "\t" 1 ... "\n"
|
|
|
380 SNORD78 "\t" 498 "\t" 65 "\t" 98 "\t" 27 ... "\n"
|
|
|
381 [...]
|
|
|
382
|
|
36
|
383 *Note: Make sure the number of columns in the header is identical to the number of columns in the body.*
|
|
25
|
384
|
|
36
|
385 Design matrix
|
|
|
386 ^^^^^^^^^^^^^
|
|
|
387 ::
|
|
25
|
388
|
|
|
389 Sample "\t" Condition "\t" Ethnicity "\t" Patient "\t" Batch "\n"
|
|
|
390 Sample-1 "\t" Tumor "\t" European "\t" 1 "\t" 1 "\n"
|
|
|
391 Sample-2 "\t" Normal "\t" European "\t" 1 "\t" 1 "\n"
|
|
|
392 Sample-3 "\t" Tumor "\t" European "\t" 2 "\t" 1 "\n"
|
|
|
393 Sample-4 "\t" Normal "\t" European "\t" 2 "\t" 1 "\n"
|
|
|
394 Sample-5 "\t" Tumor "\t" African "\t" 3 "\t" 1 "\n"
|
|
|
395 Sample-6 "\t" Normal "\t" African "\t" 3 "\t" 1 "\n"
|
|
|
396 Sample-7 "\t" Tumor "\t" African "\t" 4 "\t" 2 "\n"
|
|
|
397 Sample-8 "\t" Normal "\t" African "\t" 4 "\t" 2 "\n"
|
|
|
398 Sample-9 "\t" Tumor "\t" Asian "\t" 5 "\t" 2 "\n"
|
|
|
399 Sample-10 "\t" Normal "\t" Asian "\t" 5 "\t" 2 "\n"
|
|
|
400 Sample-11 "\t" Tumor "\t" Asian "\t" 6 "\t" 2 "\n"
|
|
|
401 Sample-12 "\t" Normal "\t" Asian "\t" 6 "\t" 2 "\n"
|
|
|
402
|
|
36
|
403 *Note: Avoid factor names that are (1) numerical, (2) contain mathematical symbols and preferebly only use letters.*
|
|
25
|
404
|
|
36
|
405 Contrast
|
|
|
406 ^^^^^^^^
|
|
|
407 The contrast represents the biological question. There can be many questions asked, e.g.:
|
|
25
|
408
|
|
36
|
409 - Tumor-Normal
|
|
|
410 - African-European
|
|
|
411 - 0.5*(Control+Placebo) / Treated
|
|
25
|
412
|
|
36
|
413 Installation
|
|
|
414 ------------
|
|
25
|
415
|
|
|
416 This tool requires no specific configurations. The following dependencies are installed automatically:
|
|
36
|
417
|
|
|
418 - R
|
|
|
419 - Bioconductor
|
|
25
|
420 - limma
|
|
36
|
421
|
|
25
|
422 - edgeR
|
|
|
423
|
|
36
|
424 License
|
|
|
425 -------
|
|
|
426 - R
|
|
|
427 - GPL-2 & GPL-3
|
|
|
428 - limma
|
|
|
429 - GPL (>=2)
|
|
|
430 - edgeR
|
|
|
431 - GPL (>=2)
|
|
|
432
|
|
|
433 References
|
|
|
434 ----------
|
|
|
435
|
|
|
436 EdgeR
|
|
|
437 ^^^^^
|
|
|
438 **[1] edgeR: a Bioconductor package for differential expression analysis of digital gene expression data.**
|
|
25
|
439
|
|
36
|
440 *Mark D. Robinson, Davis J. McCarthy and Gordon K. Smyth* - Bioinformatics (2010) 26 (1): 139-140.
|
|
|
441
|
|
|
442 - http://www.bioconductor.org/packages/2.12/bioc/html/edgeR.html
|
|
|
443 - http://dx.doi.org/10.1093/bioinformatics/btp616
|
|
|
444 - http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
|
|
25
|
445
|
|
36
|
446 Test-data (MCF7)
|
|
|
447 ^^^^^^^^^^^^^^^^
|
|
|
448 **[2] RNA-seq differential expression studies: more sequence or more replication?**
|
|
|
449
|
|
|
450 *Yuwen Liu, Jie Zhou and Kevin P. White* - Bioinformatics (2014) 30 (3): 301-304.
|
|
|
451
|
|
|
452 - http://www.ncbi.nlm.nih.gov/pubmed/24319002
|
|
|
453 - http://dx.doi.org/10.1093/bioinformatics/btt688
|
|
|
454
|
|
|
455 Contact
|
|
|
456 -------
|
|
25
|
457 The tool wrapper has been written by Youri Hoogstrate from the Erasmus Medical Center (Rotterdam, Netherlands) on behalf of the Translational Research IT (TraIT) project:
|
|
|
458 http://www.ctmm.nl/en/programmas/infrastructuren/traitprojecttranslationeleresearch
|
|
|
459
|
|
36
|
460 I would like to thank Hina Riaz - Naz Khan for her helpful contribution.
|
|
25
|
461
|
|
36
|
462 More tools by the Translational Research IT (TraIT) project can be found in the following repository:
|
|
|
463 http://testtoolshed.g2.bx.psu.edu/
|
|
25
|
464 </help>
|
|
|
465 </tool>
|
