Mercurial > repos > fubar > differential_count_models
annotate rgedgeRpaired_nocamera.xml @ 149:3107df74056e draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
| author | iuc |
|---|---|
| date | Mon, 04 May 2015 22:47:36 -0400 |
| parents | 474c08e747b6 |
| children |
| rev | line source |
|---|---|
| 146 | 1 <?xml version="1.0"?> |
| 2 <tool id="rgdifferentialcount" name="Differential_Count" version="0.28"> | |
| 3 <description>models using BioConductor packages</description> | |
| 4 <requirements> | |
| 5 <requirement type="package" version="3.1.2">R</requirement> | |
| 6 <requirement type="package" version="1.3.18">graphicsmagick</requirement> | |
| 7 <requirement type="package" version="9.10">ghostscript</requirement> | |
| 8 <requirement type="package" version="2.14">biocbasics</requirement> | |
| 9 </requirements> | |
| 10 <stdio> | |
| 11 <exit_code range="4" level="fatal" description="Number of subject ids must match total number of samples in the input matrix"/> | |
| 12 </stdio> | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
13 <command interpreter="python"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
14 rgToolFactory.py --script_path "$runme" --interpreter "Rscript" --tool_name "Differential_Counts" |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
15 --output_dir "$html_file.files_path" --output_html "$html_file" --make_HTML "yes" |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
16 </command> |
| 146 | 17 <configfiles> |
| 18 <configfile name="runme"><![CDATA[ | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
19 # |
| 146 | 20 # edgeR.Rscript |
| 21 # updated feb 2014 adding outlier-robust deviance estimate options by ross for R 3.0.2/bioc 2.13 | |
| 22 # updated npv 2011 for R 2.14.0 and edgeR 2.4.0 by ross | |
| 23 # Performs DGE on a count table containing n replicates of two conditions | |
| 24 # | |
| 25 # Parameters | |
| 26 # | |
| 27 # 1 - Output Dir | |
| 28 | |
| 29 # Original edgeR code by: S.Lunke and A.Kaspi | |
| 30 reallybig = log10(.Machine\$double.xmax) | |
| 31 reallysmall = log10(.Machine\$double.xmin) | |
| 32 library("gplots") | |
| 33 library("edgeR") | |
| 34 library('stringr') | |
| 35 hmap2 = function(cmat,nsamp=100,outpdfname='heatmap2.pdf', TName='Treatment',group=NA,myTitle='title goes here') | |
| 36 { | |
| 37 # Perform clustering for significant pvalues after controlling FWER | |
| 38 samples = colnames(cmat) | |
| 39 gu = unique(group) | |
| 40 gn = rownames(cmat) | |
| 41 if (length(gu) == 2) { | |
| 42 col.map = function(g) {if (g==gu[1]) "#FF0000" else "#0000FF"} | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
43 pcols = unlist(lapply(group,col.map)) |
| 146 | 44 } else { |
| 45 colours = rainbow(length(gu),start=0,end=4/6) | |
| 46 pcols = colours[match(group,gu)] } | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
47 dm = cmat[(! is.na(gn)),] |
| 146 | 48 # remove unlabelled hm rows |
| 49 nprobes = nrow(dm) | |
| 50 # sub = paste('Showing',nprobes,'contigs ranked for evidence of differential abundance') | |
| 51 if (nprobes > nsamp) { | |
| 52 dm =dm[1:nsamp,] | |
| 53 #sub = paste('Showing',nsamp,'contigs ranked for evidence for differential abundance out of',nprobes,'total') | |
| 54 } | |
| 55 newcolnames = substr(colnames(dm),1,20) | |
| 56 colnames(dm) = newcolnames | |
| 57 pdf(outpdfname) | |
| 58 heatmap.2(dm,main=myTitle,ColSideColors=pcols,col=topo.colors(100),dendrogram="col",key=T,density.info='none', | |
| 59 Rowv=F,scale='row',trace='none',margins=c(8,8),cexRow=0.4,cexCol=0.5) | |
| 60 dev.off() | |
| 61 } | |
| 62 | |
| 63 hmap = function(cmat,nmeans=4,outpdfname="heatMap.pdf",nsamp=250,TName='Treatment',group=NA,myTitle="Title goes here") | |
| 64 { | |
| 65 # for 2 groups only was | |
| 66 #col.map = function(g) {if (g==TName) "#FF0000" else "#0000FF"} | |
| 67 #pcols = unlist(lapply(group,col.map)) | |
| 68 gu = unique(group) | |
| 69 colours = rainbow(length(gu),start=0.3,end=0.6) | |
| 70 pcols = colours[match(group,gu)] | |
| 71 nrows = nrow(cmat) | |
| 72 mtitle = paste(myTitle,'Heatmap: n contigs =',nrows) | |
| 73 if (nrows > nsamp) { | |
| 74 cmat = cmat[c(1:nsamp),] | |
| 75 mtitle = paste('Heatmap: Top ',nsamp,' DE contigs (of ',nrows,')',sep='') | |
| 76 } | |
| 77 newcolnames = substr(colnames(cmat),1,20) | |
| 78 colnames(cmat) = newcolnames | |
| 79 pdf(outpdfname) | |
| 80 heatmap(cmat,scale='row',main=mtitle,cexRow=0.3,cexCol=0.4,Rowv=NA,ColSideColors=pcols) | |
| 81 dev.off() | |
| 82 } | |
| 83 | |
| 84 qqPlot = function(descr='qqplot',pvector, outpdf='qqplot.pdf',...) | |
| 85 # stolen from https://gist.github.com/703512 | |
| 86 { | |
| 87 o = -log10(sort(pvector,decreasing=F)) | |
| 88 e = -log10( 1:length(o)/length(o) ) | |
| 89 o[o==-Inf] = reallysmall | |
| 90 o[o==Inf] = reallybig | |
| 91 maint = descr | |
| 92 pdf(outpdf) | |
| 93 plot(e,o,pch=19,cex=1, main=maint, ..., | |
| 94 xlab=expression(Expected~~-log[10](italic(p))), | |
| 95 ylab=expression(Observed~~-log[10](italic(p))), | |
| 96 xlim=c(0,max(e)), ylim=c(0,max(o))) | |
| 97 lines(e,e,col="red") | |
| 98 grid(col = "lightgray", lty = "dotted") | |
| 99 dev.off() | |
| 100 } | |
| 101 | |
| 102 smearPlot = function(myDGEList,deTags, outSmear, outMain) | |
| 103 { | |
| 104 pdf(outSmear) | |
| 105 plotSmear(myDGEList,de.tags=deTags,main=outMain) | |
| 106 grid(col="lightgray", lty="dotted") | |
| 107 dev.off() | |
| 108 } | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
109 |
| 146 | 110 boxPlot = function(rawrs,cleanrs,maint,myTitle,pdfname) |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
111 { |
| 146 | 112 nc = ncol(rawrs) |
| 113 ##### for (i in c(1:nc)) {rawrs[(rawrs[,i] < 0),i] = NA} | |
| 114 fullnames = colnames(rawrs) | |
| 115 newcolnames = substr(colnames(rawrs),1,20) | |
| 116 colnames(rawrs) = newcolnames | |
| 117 newcolnames = substr(colnames(cleanrs),1,20) | |
| 118 colnames(cleanrs) = newcolnames | |
| 119 defpar = par(no.readonly=T) | |
| 120 print.noquote('@@@ Raw contig counts by sample:') | |
| 121 print.noquote(summary(rawrs)) | |
| 122 print.noquote('@@@ Library size contig counts by sample:') | |
| 123 print.noquote(summary(cleanrs)) | |
| 124 pdf(pdfname) | |
| 125 par(mfrow=c(1,2)) | |
| 126 boxplot(rawrs,varwidth=T,notch=T,ylab='log contig count',col="maroon",las=3,cex.axis=0.35,main='log2 raw counts') | |
| 127 grid(col="lightgray",lty="dotted") | |
| 128 boxplot(cleanrs,varwidth=T,notch=T,ylab='log contig count',col="maroon",las=3,cex.axis=0.35,main=paste('log2 counts after ',maint)) | |
| 129 grid(col="lightgray",lty="dotted") | |
| 130 dev.off() | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
131 pdfname = "sample_counts_histogram.pdf" |
| 146 | 132 nc = ncol(rawrs) |
| 133 print.noquote(paste('Using ncol rawrs=',nc)) | |
| 134 ncroot = round(sqrt(nc)) | |
| 135 if (ncroot*ncroot < nc) { ncroot = ncroot + 1 } | |
| 136 m = c() | |
| 137 for (i in c(1:nc)) { | |
| 138 rhist = hist(rawrs[,i],breaks=100,plot=F) | |
| 139 m = append(m,max(rhist\$counts)) | |
| 140 } | |
| 141 ymax = max(m) | |
| 142 ncols = length(fullnames) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
143 if (ncols > 20) |
| 146 | 144 { |
| 145 scale = 7*ncols/20 | |
| 146 pdf(pdfname,width=scale,height=scale) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
147 } else { |
| 146 | 148 pdf(pdfname) |
| 149 } | |
| 150 par(mfrow=c(ncroot,ncroot)) | |
| 151 for (i in c(1:nc)) { | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
152 hist(rawrs[,i], main=paste("Contig logcount",i), xlab='log raw count', col="maroon", |
| 146 | 153 breaks=100,sub=fullnames[i],cex=0.8,ylim=c(0,ymax)) |
| 154 } | |
| 155 dev.off() | |
| 156 par(defpar) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
157 |
| 146 | 158 } |
| 159 | |
| 160 cumPlot = function(rawrs,cleanrs,maint,myTitle) | |
| 161 { # updated to use ecdf | |
| 162 pdfname = "Differential_rowsum_bar_charts.pdf" | |
| 163 defpar = par(no.readonly=T) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
164 lrs = log(rawrs,10) |
| 146 | 165 lim = max(lrs) |
| 166 pdf(pdfname) | |
| 167 par(mfrow=c(2,1)) | |
| 168 hist(lrs,breaks=100,main=paste('Before:',maint),xlab="# Reads (log)", | |
| 169 ylab="Count",col="maroon",sub=myTitle, xlim=c(0,lim),las=1) | |
| 170 grid(col="lightgray", lty="dotted") | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
171 lrs = log(cleanrs,10) |
| 146 | 172 hist(lrs,breaks=100,main=paste('After:',maint),xlab="# Reads (log)", |
| 173 ylab="Count",col="maroon",sub=myTitle,xlim=c(0,lim),las=1) | |
| 174 grid(col="lightgray", lty="dotted") | |
| 175 dev.off() | |
| 176 par(defpar) | |
| 177 } | |
| 178 | |
| 179 cumPlot1 = function(rawrs,cleanrs,maint,myTitle) | |
| 180 { # updated to use ecdf | |
| 181 pdfname = paste(gsub(" ","", myTitle , fixed=TRUE),"RowsumCum.pdf",sep='_') | |
| 182 pdf(pdfname) | |
| 183 par(mfrow=c(2,1)) | |
| 184 lastx = max(rawrs) | |
| 185 rawe = knots(ecdf(rawrs)) | |
| 186 cleane = knots(ecdf(cleanrs)) | |
| 187 cy = 1:length(cleane)/length(cleane) | |
| 188 ry = 1:length(rawe)/length(rawe) | |
| 189 plot(rawe,ry,type='l',main=paste('Before',maint),xlab="Log Contig Total Reads", | |
| 190 ylab="Cumulative proportion",col="maroon",log='x',xlim=c(1,lastx),sub=myTitle) | |
| 191 grid(col="blue") | |
| 192 plot(cleane,cy,type='l',main=paste('After',maint),xlab="Log Contig Total Reads", | |
| 193 ylab="Cumulative proportion",col="maroon",log='x',xlim=c(1,lastx),sub=myTitle) | |
| 194 grid(col="blue") | |
| 195 dev.off() | |
| 196 } | |
| 197 | |
| 198 | |
| 199 | |
| 200 doGSEAold = function(y=NULL,design=NULL,histgmt="", | |
| 201 bigmt="/data/genomes/gsea/3.1/Abetterchoice_nocgp_c2_c3_c5_symbols_all.gmt", | |
| 202 ntest=0, myTitle="myTitle", outfname="GSEA.xls", minnin=5, maxnin=2000,fdrthresh=0.05,fdrtype="BH") | |
| 203 { | |
| 204 sink('Camera.log') | |
| 205 genesets = c() | |
| 206 if (bigmt > "") | |
| 207 { | |
| 208 bigenesets = readLines(bigmt) | |
| 209 genesets = bigenesets | |
| 210 } | |
| 211 if (histgmt > "") | |
| 212 { | |
| 213 hgenesets = readLines(histgmt) | |
| 214 if (bigmt > "") { | |
| 215 genesets = rbind(genesets,hgenesets) | |
| 216 } else { | |
| 217 genesets = hgenesets | |
| 218 } # use only history if no bi | |
| 219 } | |
| 220 print.noquote(paste("@@@read",length(genesets), 'genesets from',histgmt,bigmt)) | |
| 221 genesets = strsplit(genesets,'\t') # tabular. genesetid\tURLorwhatever\tgene_1\t..\tgene_n | |
| 222 outf = outfname | |
| 223 head=paste(myTitle,'edgeR GSEA') | |
| 224 write(head,file=outfname,append=F) | |
| 225 ntest=length(genesets) | |
| 226 urownames = toupper(rownames(y)) | |
| 227 upcam = c() | |
| 228 downcam = c() | |
| 229 for (i in 1:ntest) { | |
| 230 gs = unlist(genesets[i]) | |
| 231 g = gs[1] # geneset_id | |
| 232 u = gs[2] | |
| 233 if (u > "") { u = paste("<a href=\'",u,"\'>",u,"</a>",sep="") } | |
| 234 glist = gs[3:length(gs)] # member gene symbols | |
| 235 glist = toupper(glist) | |
| 236 inglist = urownames %in% glist | |
| 237 nin = sum(inglist) | |
| 238 if ((nin > minnin) && (nin < maxnin)) { | |
| 239 ### print(paste('@@found',sum(inglist),'genes in glist')) | |
| 240 camres = camera(y=y,index=inglist,design=design) | |
| 241 if (! is.null(camres)) { | |
| 242 rownames(camres) = g # gene set name | |
| 243 camres = cbind(GeneSet=g,URL=u,camres) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
244 if (camres\$Direction == "Up") |
| 146 | 245 { |
| 246 upcam = rbind(upcam,camres) } else { | |
| 247 downcam = rbind(downcam,camres) | |
| 248 } | |
| 249 } | |
| 250 } | |
| 251 } | |
| 252 uscam = upcam[order(upcam\$PValue),] | |
| 253 unadjp = uscam\$PValue | |
| 254 uscam\$adjPValue = p.adjust(unadjp,method=fdrtype) | |
| 255 nup = max(10,sum((uscam\$adjPValue < fdrthresh))) | |
| 256 dscam = downcam[order(downcam\$PValue),] | |
| 257 unadjp = dscam\$PValue | |
| 258 dscam\$adjPValue = p.adjust(unadjp,method=fdrtype) | |
| 259 ndown = max(10,sum((dscam\$adjPValue < fdrthresh))) | |
| 260 write.table(uscam,file=paste('camera_up',outfname,sep='_'),quote=F,sep='\t',row.names=F) | |
| 261 write.table(dscam,file=paste('camera_down',outfname,sep='_'),quote=F,sep='\t',row.names=F) | |
| 262 print.noquote(paste('@@@@@ Camera up top',nup,'gene sets:')) | |
| 263 write.table(head(uscam,nup),file="",quote=F,sep='\t',row.names=F) | |
| 264 print.noquote(paste('@@@@@ Camera down top',ndown,'gene sets:')) | |
| 265 write.table(head(dscam,ndown),file="",quote=F,sep='\t',row.names=F) | |
| 266 sink() | |
| 267 } | |
| 268 | |
| 269 | |
| 270 | |
| 271 | |
| 272 doGSEA = function(y=NULL,design=NULL,histgmt="", | |
| 273 bigmt="/data/genomes/gsea/3.1/Abetterchoice_nocgp_c2_c3_c5_symbols_all.gmt", | |
| 274 ntest=0, myTitle="myTitle", outfname="GSEA.xls", minnin=5, maxnin=2000,fdrthresh=0.05,fdrtype="BH") | |
| 275 { | |
| 276 sink('Camera.log') | |
| 277 genesets = c() | |
| 278 if (bigmt > "") | |
| 279 { | |
| 280 bigenesets = readLines(bigmt) | |
| 281 genesets = bigenesets | |
| 282 } | |
| 283 if (histgmt > "") | |
| 284 { | |
| 285 hgenesets = readLines(histgmt) | |
| 286 if (bigmt > "") { | |
| 287 genesets = rbind(genesets,hgenesets) | |
| 288 } else { | |
| 289 genesets = hgenesets | |
| 290 } # use only history if no bi | |
| 291 } | |
| 292 print.noquote(paste("@@@read",length(genesets), 'genesets from',histgmt,bigmt)) | |
| 293 genesets = strsplit(genesets,'\t') # tabular. genesetid\tURLorwhatever\tgene_1\t..\tgene_n | |
| 294 outf = outfname | |
| 295 head=paste(myTitle,'edgeR GSEA') | |
| 296 write(head,file=outfname,append=F) | |
| 297 ntest=length(genesets) | |
| 298 urownames = toupper(rownames(y)) | |
| 299 upcam = c() | |
| 300 downcam = c() | |
| 301 incam = c() | |
| 302 urls = c() | |
| 303 gsids = c() | |
| 304 for (i in 1:ntest) { | |
| 305 gs = unlist(genesets[i]) | |
| 306 gsid = gs[1] # geneset_id | |
| 307 url = gs[2] | |
| 308 if (url > "") { url = paste("<a href=\'",url,"\'>",url,"</a>",sep="") } | |
| 309 glist = gs[3:length(gs)] # member gene symbols | |
| 310 glist = toupper(glist) | |
| 311 inglist = urownames %in% glist | |
| 312 nin = sum(inglist) | |
| 313 if ((nin > minnin) && (nin < maxnin)) { | |
| 314 incam = c(incam,inglist) | |
| 315 gsids = c(gsids,gsid) | |
| 316 urls = c(urls,url) | |
| 317 } | |
| 318 } | |
| 319 incam = as.list(incam) | |
| 320 names(incam) = gsids | |
| 321 allcam = camera(y=y,index=incam,design=design) | |
| 322 allcamres = cbind(geneset=gsids,allcam,URL=urls) | |
| 323 for (i in 1:ntest) { | |
| 324 camres = allcamres[i] | |
| 325 res = try(test = (camres\$Direction == "Up")) | |
| 326 if ("try-error" %in% class(res)) { | |
| 327 cat("test failed, camres = :") | |
| 328 print.noquote(camres) | |
| 329 } else { if (camres\$Direction == "Up") | |
| 330 { upcam = rbind(upcam,camres) | |
| 331 } else { downcam = rbind(downcam,camres) | |
| 332 } | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
333 |
| 146 | 334 } |
| 335 } | |
| 336 uscam = upcam[order(upcam\$PValue),] | |
| 337 unadjp = uscam\$PValue | |
| 338 uscam\$adjPValue = p.adjust(unadjp,method=fdrtype) | |
| 339 nup = max(10,sum((uscam\$adjPValue < fdrthresh))) | |
| 340 dscam = downcam[order(downcam\$PValue),] | |
| 341 unadjp = dscam\$PValue | |
| 342 dscam\$adjPValue = p.adjust(unadjp,method=fdrtype) | |
| 343 ndown = max(10,sum((dscam\$adjPValue < fdrthresh))) | |
| 344 write.table(uscam,file=paste('camera_up',outfname,sep='_'),quote=F,sep='\t',row.names=F) | |
| 345 write.table(dscam,file=paste('camera_down',outfname,sep='_'),quote=F,sep='\t',row.names=F) | |
| 346 print.noquote(paste('@@@@@ Camera up top',nup,'gene sets:')) | |
| 347 write.table(head(uscam,nup),file="",quote=F,sep='\t',row.names=F) | |
| 348 print.noquote(paste('@@@@@ Camera down top',ndown,'gene sets:')) | |
| 349 write.table(head(dscam,ndown),file="",quote=F,sep='\t',row.names=F) | |
| 350 sink() | |
| 351 } | |
| 352 | |
| 353 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
354 edgeIt = function (Count_Matrix=c(),group=c(),out_edgeR=F,out_Voom=F,out_DESeq2=F,fdrtype='fdr',priordf=5, |
| 146 | 355 fdrthresh=0.05,outputdir='.', myTitle='Differential Counts',libSize=c(),useNDF=F, |
| 356 filterquantile=0.2, subjects=c(),TreatmentName="Rx",ControlName="Ctrl",mydesign=NULL, | |
| 357 doDESeq2=T,doVoom=T,doCamera=T,doedgeR=T,org='hg19', | |
| 358 histgmt="", bigmt="/data/genomes/gsea/3.1/Abetterchoice_nocgp_c2_c3_c5_symbols_all.gmt", | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
359 doCook=F,DESeq_fitType="parameteric",robust_meth='ordinary') |
| 146 | 360 { |
| 361 | |
| 362 logf = file('Differential.log', open = "a") | |
| 363 sink(logf,type = c("output", "message")) | |
| 364 | |
| 365 | |
| 366 run_edgeR = function(workCM,pdata,subjects,group,priordf,robust_meth,mydesign,mt,cmrowsums,out_edgeR,nonzerod) | |
| 367 { | |
| 368 logf = file('edgeR.log', open = "a") | |
| 369 sink(logf,type = c("output", "message")) | |
| 370 #### Setup myDGEList object | |
| 371 myDGEList = DGEList(counts=workCM, group = group) | |
| 372 myDGEList = calcNormFactors(myDGEList) | |
| 373 if (robust_meth == 'ordinary') { | |
| 374 myDGEList = estimateGLMCommonDisp(myDGEList,mydesign) | |
| 375 myDGEList = estimateGLMTrendedDisp(myDGEList,mydesign) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
376 if (priordf > 0) { myDGEList = estimateGLMTagwiseDisp(myDGEList,mydesign,prior.df = priordf) |
| 146 | 377 } else { myDGEList = estimateGLMTagwiseDisp(myDGEList,mydesign) } |
| 378 comdisp = myDGEList\$common.dispersion | |
| 379 estpriorn = getPriorN(myDGEList) | |
| 380 print(paste("Common Dispersion =",comdisp,"CV = ",sqrt(comdisp),"getPriorN = ",estpriorn),quote=F) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
381 } else { |
| 146 | 382 myDGEList = estimateGLMRobustDisp(myDGEList,design=mydesign, prior.df = priordf, maxit = 6, residual.type = robust_meth) |
| 383 } | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
384 |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
385 |
| 146 | 386 DGLM = glmFit(myDGEList,design=mydesign) |
| 387 DE = glmLRT(DGLM,coef=ncol(DGLM\$design)) # always last one - subject is first if needed | |
| 388 normData = cpm(myDGEList) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
389 uoutput = cbind( |
| 146 | 390 Name=as.character(rownames(myDGEList\$counts)), |
| 391 DE\$table, | |
| 392 adj.p.value=p.adjust(DE\$table\$PValue, method=fdrtype), | |
| 393 Dispersion=myDGEList\$tagwise.dispersion,totreads=cmrowsums,normData, | |
| 394 myDGEList\$counts | |
| 395 ) | |
| 396 soutput = uoutput[order(DE\$table\$PValue),] # sorted into p value order - for quick toptable | |
| 397 goodness = gof(DGLM, pcutoff=fdrthresh) | |
| 398 if (sum(goodness\$outlier) > 0) { | |
| 399 print.noquote('GLM outliers:') | |
| 400 print(paste(rownames(DGLM)[(goodness\$outlier)],collapse=','),quote=F) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
401 } else { |
| 146 | 402 print('No GLM fit outlier genes found\n') |
| 403 } | |
| 404 z = limma::zscoreGamma(goodness\$gof.statistic, shape=goodness\$df/2, scale=2) | |
| 405 pdf(paste("edgeR",mt,"GoodnessofFit.pdf",sep='_')) | |
| 406 qq = qqnorm(z, panel.first=grid(), main="tagwise dispersion") | |
| 407 abline(0,1,lwd=3) | |
| 408 points(qq\$x[goodness\$outlier],qq\$y[goodness\$outlier], pch=16, col="maroon") | |
| 409 dev.off() | |
| 410 uniqueg = unique(group) | |
| 411 write.table(soutput,file=out_edgeR, quote=FALSE, sep="\t",row.names=F) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
412 tt = cbind( |
| 146 | 413 Name=as.character(rownames(myDGEList)), |
| 414 DE\$table, | |
| 415 adj.p.value=p.adjust(DE\$table\$PValue, method=fdrtype), | |
| 416 Dispersion=myDGEList\$tagwise.dispersion,totreads=cmrowsums | |
| 417 ) | |
| 418 tt = cbind(tt,URL=contigurls) # add to end so table isn't laid out strangely | |
| 419 stt = tt[order(DE\$table\$PValue),] | |
| 420 print.noquote("@@ edgeR Top tags\n") | |
| 421 print.noquote(stt[1:50,]) | |
| 422 deTags = rownames(uoutput[uoutput\$adj.p.value < fdrthresh,]) | |
| 423 nsig = length(deTags) | |
| 424 print.noquote(paste('@@',nsig,'tags significant at adj p=',fdrthresh)) | |
| 425 deColours = ifelse(deTags,'red','black') | |
| 426 pdf(paste("edgeR",mt,"BCV_vs_abundance.pdf",sep="_")) | |
| 427 plotBCV(myDGEList, cex=0.3, main="Biological CV vs abundance") | |
| 428 dev.off() | |
| 429 dg = myDGEList[order(DE\$table\$PValue),] | |
| 430 outpdfname= paste("edgeR",mt,"top_100_heatmap.pdf",sep="_") | |
| 431 ocpm = normData[order(DE\$table\$PValue),] | |
| 432 ocpm = ocpm[c(1:100),] | |
| 433 hmap2(ocpm,TName=TName,group=group,outpdfname=outpdfname,myTitle=paste(myTitle,'Heatmap')) | |
| 434 outSmear = paste("edgeR",mt,"smearplot.pdf",sep="_") | |
| 435 outMain = paste("Smear Plot for ",TName,' Vs ',CName,' (FDR@',fdrthresh,' N = ',nsig,')',sep='') | |
| 436 smearPlot(myDGEList=myDGEList,deTags=deTags, outSmear=outSmear, outMain = outMain) | |
| 437 qqPlot(descr=paste(myTitle,'edgeR adj p QQ plot'),pvector=tt\$adj.p.value,outpdf=paste('edgeR',mt,'qqplot.pdf',sep='_')) | |
| 438 topresults.edgeR = soutput[which(soutput\$adj.p.value < fdrthresh), ] | |
| 439 edgeRcountsindex = which(allgenes %in% rownames(topresults.edgeR)) | |
| 440 edgeRcounts = rep(0, length(allgenes)) | |
| 441 edgeRcounts[edgeRcountsindex] = 1 # Create venn diagram of hits | |
| 442 sink() | |
| 443 return(list(myDGEList=myDGEList,edgeRcounts=edgeRcounts)) | |
| 444 } ### run_edgeR | |
| 445 | |
| 446 | |
| 447 run_DESeq2 = function(workCM,pdata,subjects,group,out_DESeq2,mt,DESeq_fitType) | |
| 448 | |
| 449 { | |
| 450 logf = file("DESeq2.log", open = "a") | |
| 451 sink(logf,type = c("output", "message")) | |
| 452 # DESeq2 | |
| 453 require('DESeq2') | |
| 454 library('RColorBrewer') | |
| 455 if (length(subjects) == 0) | |
| 456 { | |
| 457 pdata = data.frame(Name=colnames(workCM),Rx=group,row.names=colnames(workCM)) | |
| 458 deSEQds = DESeqDataSetFromMatrix(countData = workCM, colData = pdata, design = formula(~ Rx)) | |
| 459 } else { | |
| 460 pdata = data.frame(Name=colnames(workCM),Rx=group,subjects=subjects,row.names=colnames(workCM)) | |
| 461 deSEQds = DESeqDataSetFromMatrix(countData = workCM, colData = pdata, design = formula(~ subjects + Rx)) | |
| 462 } | |
| 463 deSeqDatsizefac = estimateSizeFactors(deSEQds) | |
| 464 deSeqDatdisp = estimateDispersions(deSeqDatsizefac,fitType=DESeq_fitType) | |
| 465 resDESeq = nbinomWaldTest(deSeqDatdisp) | |
| 466 rDESeq = as.data.frame(results(resDESeq)) | |
| 467 rDESeq = cbind(Contig=rownames(workCM),rDESeq,NReads=cmrowsums,URL=contigurls) | |
| 468 srDESeq = rDESeq[order(rDESeq\$pvalue),] | |
| 469 qqPlot(descr=paste(myTitle,'DESeq2 adj p qq plot'),pvector=rDESeq\$padj,outpdf=paste('DESeq2',mt,'qqplot.pdf',sep="_")) | |
| 470 cat("# DESeq top 50\n") | |
| 471 print.noquote(srDESeq[1:50,]) | |
| 472 write.table(srDESeq,file=out_DESeq2, quote=FALSE, sep="\t",row.names=F) | |
| 473 topresults.DESeq = rDESeq[which(rDESeq\$padj < fdrthresh), ] | |
| 474 DESeqcountsindex = which(allgenes %in% rownames(topresults.DESeq)) | |
| 475 DESeqcounts = rep(0, length(allgenes)) | |
| 476 DESeqcounts[DESeqcountsindex] = 1 | |
| 477 pdf(paste("DESeq2",mt,"dispersion_estimates.pdf",sep='_')) | |
| 478 plotDispEsts(resDESeq) | |
| 479 dev.off() | |
| 480 ysmall = abs(min(rDESeq\$log2FoldChange)) | |
| 481 ybig = abs(max(rDESeq\$log2FoldChange)) | |
| 482 ylimit = min(4,ysmall,ybig) | |
| 483 pdf(paste("DESeq2",mt,"MA_plot.pdf",sep="_")) | |
| 484 plotMA(resDESeq,main=paste(myTitle,"DESeq2 MA plot"),ylim=c(-ylimit,ylimit)) | |
| 485 dev.off() | |
| 486 rlogres = rlogTransformation(resDESeq) | |
| 487 sampledists = dist( t( assay(rlogres) ) ) | |
| 488 sdmat = as.matrix(sampledists) | |
| 489 pdf(paste("DESeq2",mt,"sample_distance_plot.pdf",sep="_")) | |
| 490 heatmap.2(sdmat,trace="none",main=paste(myTitle,"DESeq2 sample distances"), | |
| 491 col = colorRampPalette( rev(brewer.pal(9, "RdBu")) )(255)) | |
| 492 dev.off() | |
| 493 result = try( (ppca = plotPCA( varianceStabilizingTransformation(deSeqDatdisp,blind=T), intgroup=c("Rx","Name")) ) ) | |
| 494 if ("try-error" %in% class(result)) { | |
| 495 print.noquote('DESeq2 plotPCA failed.') | |
| 496 } else { | |
| 497 pdf(paste("DESeq2",mt,"PCA_plot.pdf",sep="_")) | |
| 498 #### wtf - print? Seems needed to get this to work | |
| 499 print(ppca) | |
| 500 dev.off() | |
| 501 } | |
| 502 sink() | |
| 503 return(DESeqcounts) | |
| 504 } | |
| 505 | |
| 506 | |
| 507 run_Voom = function(workCM,pdata,subjects,group,mydesign,mt,out_Voom) | |
| 508 { | |
| 509 logf = file('VOOM.log', open = "a") | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
510 sink(logf,type = c("output", "message")) |
| 146 | 511 if (doedgeR == F) { |
| 512 #### Setup myDGEList object | |
| 513 myDGEList = DGEList(counts=workCM, group = group) | |
| 514 myDGEList = calcNormFactors(myDGEList) | |
| 515 myDGEList = estimateGLMCommonDisp(myDGEList,mydesign) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
516 myDGEList = estimateGLMTrendedDisp(myDGEList,mydesign) |
| 146 | 517 myDGEList = estimateGLMTagwiseDisp(myDGEList,mydesign) |
| 518 } | |
| 519 pdf(paste("VOOM",mt,"mean_variance_plot.pdf",sep='_')) | |
| 520 dat.voomed <- voom(myDGEList, mydesign, plot = TRUE, normalize.method="quantil", lib.size = NULL) | |
| 521 dev.off() | |
| 522 # Use limma to fit data | |
| 523 fit = lmFit(dat.voomed, mydesign) | |
| 524 fit = eBayes(fit) | |
| 525 rvoom = topTable(fit, coef = length(colnames(mydesign)), adj = fdrtype, n = Inf, sort="none") | |
| 526 qqPlot(descr=paste(myTitle,'VOOM-limma adj p QQ plot'),pvector=rvoom\$adj.P.Val,outpdf=paste('VOOM',mt,'qqplot.pdf',sep='_')) | |
| 527 rownames(rvoom) = rownames(workCM) | |
| 528 rvoom = cbind(Contig=rownames(workCM),rvoom,NReads=cmrowsums,URL=contigurls) | |
| 529 srvoom = rvoom[order(rvoom\$P.Value),] | |
| 530 cat("# VOOM top 50\n") | |
| 531 print(srvoom[1:50,]) | |
| 532 write.table(srvoom,file=out_Voom, quote=FALSE, sep="\t",row.names=F) | |
| 533 # Use an FDR cutoff to find interesting samples for edgeR, DESeq and voom/limma | |
| 534 topresults.voom = rvoom[which(rvoom\$adj.P.Val < fdrthresh), ] | |
| 535 voomcountsindex <- which(allgenes %in% rownames(topresults.voom)) | |
| 536 voomcounts = rep(0, length(allgenes)) | |
| 537 voomcounts[voomcountsindex] = 1 | |
| 538 sink() | |
| 539 return(voomcounts) | |
| 540 } | |
| 541 | |
| 542 | |
| 543 #### data cleaning and analsis control starts here | |
| 544 | |
| 545 | |
| 546 # Error handling | |
| 547 nugroup = length(unique(group)) | |
| 548 if (nugroup!=2){ | |
| 549 print("Number of conditions identified in experiment does not equal 2") | |
| 550 q() | |
| 551 } | |
| 552 require(edgeR) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
553 options(width = 512) |
| 146 | 554 mt = paste(unlist(strsplit(myTitle,'_')),collapse=" ") |
| 555 allN = nrow(Count_Matrix) | |
| 556 nscut = round(ncol(Count_Matrix)/2) # half samples | |
| 557 colTotmillionreads = colSums(Count_Matrix)/1e6 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
558 counts.dataframe = as.data.frame(c()) |
| 146 | 559 rawrs = rowSums(Count_Matrix) |
| 560 nonzerod = Count_Matrix[(rawrs > 0),] # remove all zero count genes | |
| 561 nzN = nrow(nonzerod) | |
| 562 nzrs = rowSums(nonzerod) | |
| 563 zN = allN - nzN | |
| 564 print('@@@ Quantiles for non-zero row counts:',quote=F) | |
| 565 print(quantile(nzrs,probs=seq(0,1,0.1)),quote=F) | |
| 566 if (useNDF == T) | |
| 567 { | |
| 568 gt1rpin3 = rowSums(Count_Matrix/expandAsMatrix(colTotmillionreads,dim(Count_Matrix)) >= 1) >= nscut | |
| 569 lo = colSums(Count_Matrix[!gt1rpin3,]) | |
| 570 workCM = Count_Matrix[gt1rpin3,] | |
| 571 cleanrs = rowSums(workCM) | |
| 572 cleanN = length(cleanrs) | |
| 573 meth = paste( "After removing",length(lo),"contigs with fewer than ",nscut," sample read counts >= 1 per million, there are",sep="") | |
| 574 print(paste("Read",allN,"contigs. Removed",zN,"contigs with no reads.",meth,cleanN,"contigs"),quote=F) | |
| 575 maint = paste('Filter >=1/million reads in >=',nscut,'samples') | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
576 } else { |
| 146 | 577 useme = (nzrs > quantile(nzrs,filterquantile)) |
| 578 workCM = nonzerod[useme,] | |
| 579 lo = colSums(nonzerod[!useme,]) | |
| 580 cleanrs = rowSums(workCM) | |
| 581 cleanN = length(cleanrs) | |
| 582 meth = paste("After filtering at count quantile =",filterquantile,", there are",sep="") | |
| 583 print(paste('Read',allN,"contigs. Removed",zN,"with no reads.",meth,cleanN,"contigs"),quote=F) | |
| 584 maint = paste('Filter below',filterquantile,'quantile') | |
| 585 } | |
| 586 cumPlot(rawrs=rawrs,cleanrs=cleanrs,maint=maint,myTitle=myTitle) | |
| 587 allgenes = rownames(workCM) | |
| 588 reg = "^chr([0-9]+):([0-9]+)-([0-9]+)" # ucsc chr:start-end regexp | |
| 589 genecards="<a href=\'http://www.genecards.org/index.php?path=/Search/keyword/" | |
| 590 ucsc = paste("<a href=\'http://genome.ucsc.edu/cgi-bin/hgTracks?db=",org,sep='') | |
| 591 testreg = str_match(allgenes,reg) | |
| 592 if (sum(!is.na(testreg[,1]))/length(testreg[,1]) > 0.8) # is ucsc style string | |
| 593 { | |
| 594 print("@@ using ucsc substitution for urls") | |
| 595 contigurls = paste0(ucsc,"&position=chr",testreg[,2],":",testreg[,3],"-",testreg[,4],"\'>",allgenes,"</a>") | |
| 596 } else { | |
| 597 print("@@ using genecards substitution for urls") | |
| 598 contigurls = paste0(genecards,allgenes,"\'>",allgenes,"</a>") | |
| 599 } | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
600 print.noquote(paste("@@ Total low count contigs per sample = ",paste(table(lo),collapse=','))) |
| 146 | 601 cmrowsums = rowSums(workCM) |
| 602 TName=unique(group)[1] | |
| 603 CName=unique(group)[2] | |
| 604 if (is.null(mydesign)) { | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
605 if (length(subjects) == 0) |
| 146 | 606 { |
| 607 mydesign = model.matrix(~group) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
608 } |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
609 else { |
| 146 | 610 subjf = factor(subjects) |
| 611 mydesign = model.matrix(~subjf+group) # we block on subject so make group last to simplify finding it | |
| 612 } | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
613 } |
| 146 | 614 print.noquote(paste('Using samples:',paste(colnames(workCM),collapse=','))) |
| 615 print.noquote('Using design matrix:') | |
| 616 print.noquote(mydesign) | |
| 617 normData = cpm(workCM)*1e6 | |
| 618 colnames(normData) = paste( colnames(workCM),'N',sep="_") | |
| 619 print(paste('Raw sample read totals',paste(colSums(nonzerod,na.rm=T),collapse=','))) | |
| 620 | |
| 621 if (doedgeR == T) { | |
| 622 eres = run_edgeR(workCM,pdata,subjects,group,priordf,robust_meth,mydesign,mt,cmrowsums,out_edgeR,nonzerod) | |
| 623 myDGEList = eres\$myDGEList | |
| 624 edgeRcounts = eres\$edgeRcounts | |
| 625 #### Plot MDS | |
| 626 sample_colors = match(group,levels(group)) | |
| 627 sampleTypes = levels(factor(group)) | |
| 628 print.noquote(sampleTypes) | |
| 629 pdf(paste("edgeR",mt,"MDSplot.pdf",sep='_')) | |
| 630 plotMDS.DGEList(myDGEList,main=paste("MDS for",myTitle),cex=0.5,col=sample_colors,pch=sample_colors) | |
| 631 legend(x="topleft", legend = sampleTypes,col=c(1:length(sampleTypes)), pch=19) | |
| 632 grid(col="blue") | |
| 633 dev.off() | |
| 634 scale <- myDGEList\$samples\$lib.size*myDGEList\$samples\$norm.factors | |
| 635 normCounts <- round(t(t(myDGEList\$counts)/scale)*mean(scale)) | |
| 636 try({boxPlot(rawrs=nzd,cleanrs=log2(normCounts+1),maint='Effects of TMM size normalisation',myTitle=myTitle,pdfname=paste("edgeR",mt,"raw_norm_counts_box.pdf",sep='_'))},T) | |
| 637 } | |
| 638 if (doDESeq2 == T) { DESeqcounts = run_DESeq2(workCM,pdata,subjects,group,out_DESeq2,mt,DESeq_fitType) } | |
| 639 if (doVoom == T) { voomcounts = run_Voom(workCM,pdata,subjects,group,mydesign,mt,out_Voom) } | |
| 640 | |
| 641 | |
| 642 if (doCamera) { | |
| 643 doGSEA(y=myDGEList,design=mydesign,histgmt=histgmt,bigmt=bigmt,ntest=20,myTitle=myTitle, | |
| 644 outfname=paste("GSEA_Camera",mt,"table.xls",sep="_"),fdrthresh=fdrthresh,fdrtype=fdrtype) | |
| 645 } | |
| 646 counts.dataframe = c() | |
| 647 vennmain = 'no venn' | |
| 648 if ((doDESeq2==T) || (doVoom==T) || (doedgeR==T)) { | |
| 649 if ((doVoom==T) && (doDESeq2==T) && (doedgeR==T)) { | |
| 650 vennmain = paste(mt,'Voom,edgeR and DESeq2 overlap at FDR=',fdrthresh) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
651 counts.dataframe = data.frame(edgeR = edgeRcounts, DESeq2 = DESeqcounts, |
| 146 | 652 VOOM_limma = voomcounts, row.names = allgenes) |
| 653 } else if ((doDESeq2==T) && (doedgeR==T)) { | |
| 654 vennmain = paste(mt,'DESeq2 and edgeR overlap at FDR=',fdrthresh) | |
| 655 counts.dataframe = data.frame(edgeR = edgeRcounts, DESeq2 = DESeqcounts, row.names = allgenes) | |
| 656 } else if ((doVoom==T) && (doedgeR==T)) { | |
| 657 vennmain = paste(mt,'Voom and edgeR overlap at FDR=',fdrthresh) | |
| 658 counts.dataframe = data.frame(edgeR = edgeRcounts, VOOM_limma = voomcounts, row.names = allgenes) | |
| 659 } | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
660 |
| 146 | 661 if (nrow(counts.dataframe > 1)) { |
| 662 counts.venn = vennCounts(counts.dataframe) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
663 vennf = paste("Differential_venn",mt,"significant_genes_overlap.pdf",sep="_") |
| 146 | 664 pdf(vennf) |
| 665 vennDiagram(counts.venn,main=vennmain,col="maroon") | |
| 666 dev.off() | |
| 667 } | |
| 668 } #### doDESeq2 or doVoom | |
| 669 sink() | |
| 670 } | |
| 671 #### Done | |
| 672 ]]> | |
| 673 builtin_gmt = "" | |
| 674 history_gmt = "" | |
| 675 history_gmt_name = "" | |
| 676 out_edgeR = F | |
| 677 out_DESeq2 = F | |
| 678 out_Voom = "$out_VOOM" | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
679 edgeR_robust_meth = "ordinary" |
| 146 | 680 doDESeq2 = $DESeq2.doDESeq2 |
| 681 doVoom = $doVoom | |
| 682 doCamera = F | |
| 683 doedgeR = $edgeR.doedgeR | |
| 684 edgeR_priordf = 10 | |
| 685 | |
| 686 | |
| 687 #if $doVoom == "T": | |
| 688 out_Voom = "$out_VOOM" | |
| 689 #end if | |
| 690 | |
| 691 #if $DESeq2.doDESeq2 == "T": | |
| 692 out_DESeq2 = "$out_DESeq2" | |
| 693 doDESeq2 = T | |
| 694 DESeq_fitType = "$DESeq2.DESeq_fitType" | |
| 695 #end if | |
| 696 | |
| 697 #if $edgeR.doedgeR == "T": | |
| 698 out_edgeR = "$out_edgeR" | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
699 edgeR_priordf = $edgeR.edgeR_priordf |
| 146 | 700 edgeR_robust_meth = "$edgeR.edgeR_robust_method" |
| 701 #end if | |
| 702 | |
| 703 | |
| 704 if (sum(c(doedgeR,doVoom,doDESeq2)) == 0) | |
| 705 { | |
| 706 write("No methods chosen - nothing to do! Please try again after choosing one or more methods", stderr()) | |
| 707 quit(save="no",status=2) | |
| 708 } | |
| 709 | |
| 710 Out_Dir = "$html_file.files_path" | |
| 711 Input = "$input1" | |
| 712 TreatmentName = "$treatment_name" | |
| 713 TreatmentCols = "$Treat_cols" | |
| 714 ControlName = "$control_name" | |
| 715 ControlCols= "$Control_cols" | |
| 716 org = "$input1.dbkey" | |
| 717 if (org == "") { org = "hg19"} | |
| 718 fdrtype = "$fdrtype" | |
| 719 fdrthresh = $fdrthresh | |
| 720 useNDF = $useNDF | |
| 721 fQ = $fQ # non-differential centile cutoff | |
| 722 myTitle = "$title" | |
| 723 sids = strsplit("$subjectids",',') | |
| 724 subjects = unlist(sids) | |
| 725 nsubj = length(subjects) | |
| 726 TCols = as.numeric(strsplit(TreatmentCols,",")[[1]])-1 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
727 CCols = as.numeric(strsplit(ControlCols,",")[[1]])-1 |
| 146 | 728 cat('Got TCols=') |
| 729 cat(TCols) | |
| 730 cat('; CCols=') | |
| 731 cat(CCols) | |
| 732 cat('\n') | |
| 733 <![CDATA[ | |
| 734 useCols = c(TCols,CCols) | |
| 735 if (file.exists(Out_Dir) == F) dir.create(Out_Dir) | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
736 Count_Matrix = read.table(Input,header=T,row.names=1,sep='\t') |
| 146 | 737 snames = colnames(Count_Matrix) |
| 738 nsamples = length(snames) | |
| 739 if (nsubj > 0 & nsubj != nsamples) { | |
| 740 options("show.error.messages"=T) | |
| 741 mess = paste('Fatal error: Supplied subject id list',paste(subjects,collapse=','), | |
| 742 'has length',nsubj,'but there are',nsamples,'samples',paste(snames,collapse=',')) | |
| 743 write(mess, stderr()) | |
| 744 quit(save="no",status=4) | |
| 745 } | |
| 746 if (length(subjects) != 0) {subjects = subjects[useCols]} | |
| 747 Count_Matrix = Count_Matrix[,useCols] ### reorder columns | |
| 748 rn = rownames(Count_Matrix) | |
| 749 islib = rn %in% c('librarySize','NotInBedRegions') | |
| 750 LibSizes = Count_Matrix[subset(rn,islib),][1] # take first | |
| 751 Count_Matrix = Count_Matrix[subset(rn,! islib),] | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
752 group = c(rep(TreatmentName,length(TCols)), rep(ControlName,length(CCols)) ) |
| 146 | 753 group = factor(group, levels=c(ControlName,TreatmentName)) |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
754 colnames(Count_Matrix) = paste(group,colnames(Count_Matrix),sep="_") |
| 146 | 755 results = edgeIt(Count_Matrix=Count_Matrix,group=group, out_edgeR=out_edgeR, out_Voom=out_Voom, out_DESeq2=out_DESeq2, |
| 756 fdrtype='BH',mydesign=NULL,priordf=edgeR_priordf,fdrthresh=fdrthresh,outputdir='.', | |
| 757 myTitle=myTitle,useNDF=F,libSize=c(),filterquantile=fQ,subjects=subjects,TreatmentName=TreatmentName,ControlName=ControlName, | |
| 758 doDESeq2=doDESeq2,doVoom=doVoom,doCamera=doCamera,doedgeR=doedgeR,org=org, | |
| 759 histgmt=history_gmt,bigmt=builtin_gmt,DESeq_fitType=DESeq_fitType,robust_meth=edgeR_robust_meth) | |
| 760 sessionInfo() | |
| 761 | |
| 762 sink() | |
| 763 ]]> | |
| 764 </configfile> | |
| 765 </configfiles> | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
766 <inputs> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
767 <param name="input1" type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample" help="Use the HTSeq based count matrix preparation tool to create these matrices from BAM/SAM files and a GTF file of genomic features"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
768 <param name="title" type="text" value="Differential Counts" size="80" label="Title for job outputs" help="Supply a meaningful name here to remind you what the outputs contain"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
769 <sanitizer invalid_char=""> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
770 <valid initial="string.letters,string.digits"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
771 <add value="_"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
772 </valid> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
773 </sanitizer> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
774 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
775 <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
776 <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
777 <validator type="no_options" message="Please select at least one column."/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
778 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
779 <param name="control_name" type="text" value="Control" size="50" label="Control Name"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
780 <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
781 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
782 <param name="subjectids" type="text" optional="true" size="120" value="" label="IF SUBJECTS NOT ALL INDEPENDENT! Enter comma separated strings to indicate sample labels for (eg) pairing - must be one for every column in input" help="Leave blank if no pairing, but eg if data from sample id A99 is in columns 2,4 and id C21 is in 3,5 then enter 'A99,C21,A99,C21'"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
783 <sanitizer> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
784 <valid initial="string.letters,string.digits"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
785 <add value=","/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
786 </valid> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
787 </sanitizer> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
788 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
789 <param name="fQ" type="float" value="0.3" size="5" label="Non-differential contig count quantile threshold - zero to analyze all non-zero read count contigs" help="May be a good or a bad idea depending on the biology and the question. EG 0.3 = sparsest 30% of contigs with at least one read are removed before analysis"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
790 <param name="useNDF" type="boolean" truevalue="T" falsevalue="F" checked="false" size="1" label="Non differential filter - remove contigs below a threshold (1 per million) for half or more samples" help="May be a good or a bad idea depending on the biology and the question. This was the old default. Quantile based is available as an alternative"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
791 <conditional name="edgeR"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
792 <param name="doedgeR" type="select" label="Run this model using edgeR" help="edgeR uses a negative binomial model and seems to be powerful, even with few replicates"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
793 <option value="F">Do not run edgeR</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
794 <option value="T" selected="true">Run edgeR</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
795 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
796 <when value="T"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
797 <param name="edgeR_priordf" type="integer" value="10" size="3" label="prior.df for tagwise dispersion - larger value = more squeezing of tag dispersions to common dispersion. Replaces prior.n and prior.df = prior.n * residual.df" help="10 = edgeR default. Use a larger value to 'smooth' small samples. See edgeR docs and note below"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
798 <param name="edgeR_robust_method" type="select" value="20" size="3" label="Use robust dispersion method" help="Use ordinary, anscombe or deviance robust deviance estimates"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
799 <option value="ordinary" selected="true">Use ordinary deviance estimates</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
800 <option value="deviance">Use robust deviance estimates</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
801 <option value="anscombe">use Anscombe robust deviance estimates</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
802 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
803 </when> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
804 <when value="F"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
805 </conditional> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
806 <conditional name="DESeq2"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
807 <param name="doDESeq2" type="select" label="Run the same model with DESeq2 and compare findings" help="DESeq2 is an update to the DESeq package. It uses different assumptions and methods to edgeR"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
808 <option value="F" selected="true">Do not run DESeq2</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
809 <option value="T">Run DESeq2</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
810 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
811 <when value="T"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
812 <param name="DESeq_fitType" type="select"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
813 <option value="parametric" selected="true">Parametric (default) fit for dispersions</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
814 <option value="local">Local fit - this will automagically be used if parametric fit fails</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
815 <option value="mean">Mean dispersion fit- use this if you really understand what you're doing - read the fine manual linked below in the documentation</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
816 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
817 </when> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
818 <when value="F"> </when> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
819 </conditional> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
820 <param name="doVoom" type="select" label="Run the same model with Voom/limma and compare findings" help="Voom uses counts per million and a precise transformation of variance so count data can be analysed using limma"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
821 <option value="F" selected="true">Do not run VOOM</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
822 <option value="T">Run VOOM</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
823 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
824 <param name="fdrthresh" type="float" value="0.05" size="5" label="P value threshold for FDR filtering for amily wise error rate control" help="Conventional default value of 0.05 recommended"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
825 <param name="fdrtype" type="select" label="FDR (Type II error) control method" help="Use fdr or bh typically to control for the number of tests in a reliable way"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
826 <option value="fdr" selected="true">fdr</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
827 <option value="BH">Benjamini Hochberg</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
828 <option value="BY">Benjamini Yukateli</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
829 <option value="bonferroni">Bonferroni</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
830 <option value="hochberg">Hochberg</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
831 <option value="holm">Holm</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
832 <option value="hommel">Hommel</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
833 <option value="none">no control for multiple tests</option> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
834 </param> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
835 </inputs> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
836 <outputs> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
837 <data format="tabular" name="out_edgeR" label="${title}_topTable_edgeR.xls"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
838 <filter>edgeR['doedgeR'] == "T"</filter> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
839 </data> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
840 <data format="tabular" name="out_DESeq2" label="${title}_topTable_DESeq2.xls"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
841 <filter>DESeq2['doDESeq2'] == "T"</filter> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
842 </data> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
843 <data format="tabular" name="out_VOOM" label="${title}_topTable_VOOM.xls"> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
844 <filter>doVoom == "T"</filter> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
845 </data> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
846 <data format="html" name="html_file" label="${title}.html"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
847 </outputs> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
848 <tests> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
849 <test> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
850 <param name="input1" value="test_bams2mx.xls" ftype="tabular"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
851 <param name="treatment_name" value="liver"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
852 <param name="title" value="edgeRtest"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
853 <param name="useNDF" value=""/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
854 <param name="doedgeR" value="T"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
855 <param name="doVoom" value="T"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
856 <param name="doDESeq2" value="T"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
857 <param name="fdrtype" value="fdr"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
858 <param name="edgeR_priordf" value="8"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
859 <param name="edgeR_robust" value="ordinary"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
860 <param name="fdrthresh" value="0.05"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
861 <param name="control_name" value="heart"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
862 <param name="subjectids" value=""/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
863 <param name="Control_cols" value="3,4,5,9"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
864 <param name="Treat_cols" value="2,6,7,8"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
865 <output name="out_edgeR" file="edgeRtest1out.xls" compare="diff" lines_diff="20"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
866 <output name="html_file" file="edgeRtest1out.html" compare="diff" lines_diff="20"/> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
867 </test> |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
868 </tests> |
| 146 | 869 <help> |
| 870 | |
| 871 **What it does** | |
| 872 | |
| 873 Allows short read sequence counts from controlled experiments to be analysed for differentially expressed genes. | |
| 874 Optionally adds a term for subject if not all samples are independent or if some other factor needs to be blocked in the design. | |
| 875 | |
| 876 **Input** | |
| 877 | |
| 878 Requires a count matrix as a tabular file. These are best made using the companion HTSeq_ based counter Galaxy wrapper | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
879 and your fave gene model to generate inputs. Each row is a genomic feature (gene or exon eg) and each column the |
| 146 | 880 non-negative integer count of reads from one sample overlapping the feature. |
| 881 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
882 The matrix must have a header row uniquely identifying the source samples, and unique row names in |
| 146 | 883 the first column. Typically the row names are gene symbols or probe ids for downstream use in GSEA and other methods. |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
884 They must be unique and R names or they will be mangled - please read the fine R docs for the rules on identifiers. |
| 146 | 885 |
| 886 **Specifying comparisons** | |
| 887 | |
| 888 This is basically dumbed down for two factors - case vs control. | |
| 889 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
890 More complex interfaces are possible but painful at present. |
| 146 | 891 Probably need to specify a phenotype file to do this better. |
| 892 Work in progress. Send code. | |
| 893 | |
| 894 If you have (eg) paired samples and wish to include a term in the GLM to account for some other factor (subject in the case of paired samples), | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
895 put a comma separated list of indicators for every sample (whether modelled or not!) indicating (eg) the subject number or |
| 146 | 896 A list of integers, one for each subject or an empty string if samples are all independent. |
| 897 If not empty, there must be exactly as many integers in the supplied integer list as there are columns (samples) in the count matrix. | |
| 898 Integers for samples that are not in the analysis *must* be present in the string as filler even if not used. | |
| 899 | |
| 900 So if you have 2 pairs out of 6 samples, you need to put in unique integers for the unpaired ones | |
| 901 eg if you had 6 samples with the first two independent but the second and third pairs each being from independent subjects. you might use | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
902 8,9,1,1,2,2 |
| 146 | 903 as subject IDs to indicate two paired samples from the same subject in columns 3/4 and 5/6 |
| 904 | |
| 905 **Methods available** | |
| 906 | |
| 907 You can run 3 popular Bioconductor packages available for count data. | |
| 908 | |
| 909 edgeR - see edgeR_ for details | |
| 910 | |
| 911 VOOM/limma - see limma_VOOM_ for details | |
| 912 | |
| 913 DESeq2 - see DESeq2_ for details | |
| 914 | |
| 915 and optionally camera in edgeR which works better if MSigDB is installed. | |
| 916 | |
| 917 **Outputs** | |
| 918 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
919 Some helpful plots and analysis results. Note that most of these are produced using R code |
| 146 | 920 suggested by the excellent documentation and vignettes for the Bioconductor |
| 921 packages invoked. The Tool Factory is used to automatically lay these out for you to enjoy. | |
| 922 | |
| 923 **Note on Voom** | |
| 924 | |
| 925 The voom from limma version 3.16.6 help in R includes this from the authors - but you should read the paper to interpret this method. | |
| 926 | |
| 927 This function is intended to process RNA-Seq or ChIP-Seq data prior to linear modelling in limma. | |
| 928 | |
| 929 voom is an acronym for mean-variance modelling at the observational level. | |
| 930 The key concern is to estimate the mean-variance relationship in the data, then use this to compute appropriate weights for each observation. | |
| 931 Count data almost show non-trivial mean-variance relationships. Raw counts show increasing variance with increasing count size, while log-counts typically show a decreasing mean-variance trend. | |
| 932 This function estimates the mean-variance trend for log-counts, then assigns a weight to each observation based on its predicted variance. | |
| 933 The weights are then used in the linear modelling process to adjust for heteroscedasticity. | |
| 934 | |
| 935 In an experiment, a count value is observed for each tag in each sample. A tag-wise mean-variance trend is computed using lowess. | |
| 936 The tag-wise mean is the mean log2 count with an offset of 0.5, across samples for a given tag. | |
| 937 The tag-wise variance is the quarter-root-variance of normalized log2 counts per million values with an offset of 0.5, across samples for a given tag. | |
| 938 Tags with zero counts across all samples are not included in the lowess fit. Optional normalization is performed using normalizeBetweenArrays. | |
| 939 Using fitted values of log2 counts from a linear model fit by lmFit, variances from the mean-variance trend were interpolated for each observation. | |
| 940 This was carried out by approxfun. Inverse variance weights can be used to correct for mean-variance trend in the count data. | |
| 941 | |
| 942 | |
| 943 Author(s) | |
| 944 | |
| 945 Charity Law and Gordon Smyth | |
| 946 | |
| 947 References | |
| 948 | |
| 949 Law, CW (2013). Precision weights for gene expression analysis. PhD Thesis. University of Melbourne, Australia. | |
| 950 | |
| 951 Law, CW, Chen, Y, Shi, W, Smyth, GK (2013). Voom! Precision weights unlock linear model analysis tools for RNA-seq read counts. | |
| 952 Technical Report 1 May 2013, Bioinformatics Division, Walter and Eliza Hall Institute of Medical Reseach, Melbourne, Australia. | |
| 953 http://www.statsci.org/smyth/pubs/VoomPreprint.pdf | |
| 954 | |
| 955 See Also | |
| 956 | |
| 957 A voom case study is given in the edgeR User's Guide. | |
| 958 | |
| 959 vooma is a similar function but for microarrays instead of RNA-seq. | |
| 960 | |
| 961 | |
| 962 ***old rant on changes to Bioconductor package variable names between versions*** | |
| 963 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
964 The edgeR authors made a small cosmetic change in the name of one important variable (from p.value to PValue) |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
965 breaking this and all other code that assumed the old name for this variable, |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
966 between edgeR2.4.4 and 2.4.6 (the version for R 2.14 as at the time of writing). |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
967 This means that all code using edgeR is sensitive to the version. I think this was a very unwise thing |
| 146 | 968 to do because it wasted hours of my time to track down and will similarly cost other edgeR users dearly |
| 969 when their old scripts break. This tool currently now works with 2.4.6. | |
| 970 | |
| 971 **Note on prior.N** | |
| 972 | |
| 973 http://seqanswers.com/forums/showthread.php?t=5591 says: | |
| 974 | |
| 975 *prior.n* | |
| 976 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
977 The value for prior.n determines the amount of smoothing of tagwise dispersions towards the common dispersion. |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
978 You can think of it as like a "weight" for the common value. (It is actually the weight for the common likelihood |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
979 in the weighted likelihood equation). The larger the value for prior.n, the more smoothing, i.e. the closer your |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
980 tagwise dispersion estimates will be to the common dispersion. If you use a prior.n of 1, then that gives the |
| 146 | 981 common likelihood the weight of one observation. |
| 982 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
983 In answer to your question, it is a good thing to squeeze the tagwise dispersions towards a common value, |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
984 or else you will be using very unreliable estimates of the dispersion. I would not recommend using the value that |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
985 you obtained from estimateSmoothing()---this is far too small and would result in virtually no moderation |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
986 (squeezing) of the tagwise dispersions. How many samples do you have in your experiment? |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
987 What is the experimental design? If you have few samples (less than 6) then I would suggest a prior.n of at least 10. |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
988 If you have more samples, then the tagwise dispersion estimates will be more reliable, |
|
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
989 so you could consider using a smaller prior.n, although I would hesitate to use a prior.n less than 5. |
| 146 | 990 |
| 991 | |
| 992 From Bioconductor Digest, Vol 118, Issue 5, Gordon writes: | |
| 993 | |
| 994 Dear Dorota, | |
| 995 | |
| 996 The important settings are prior.df and trend. | |
| 997 | |
| 998 prior.n and prior.df are related through prior.df = prior.n * residual.df, | |
| 999 and your experiment has residual.df = 36 - 12 = 24. So the old setting of | |
| 1000 prior.n=10 is equivalent for your data to prior.df = 240, a very large | |
| 1001 value. Going the other way, the new setting of prior.df=10 is equivalent | |
| 1002 to prior.n=10/24. | |
| 1003 | |
| 1004 To recover old results with the current software you would use | |
| 1005 | |
| 1006 estimateTagwiseDisp(object, prior.df=240, trend="none") | |
| 1007 | |
| 1008 To get the new default from old software you would use | |
| 1009 | |
| 1010 estimateTagwiseDisp(object, prior.n=10/24, trend=TRUE) | |
| 1011 | |
| 1012 Actually the old trend method is equivalent to trend="loess" in the new | |
| 1013 software. You should use plotBCV(object) to see whether a trend is | |
| 1014 required. | |
| 1015 | |
| 1016 Note you could also use | |
| 1017 | |
| 1018 prior.n = getPriorN(object, prior.df=10) | |
| 1019 | |
| 1020 to map between prior.df and prior.n. | |
| 1021 | |
| 1022 ---- | |
| 1023 | |
| 1024 **Attributions** | |
| 1025 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
1026 edgeR - edgeR_ |
| 146 | 1027 |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
1028 VOOM/limma - limma_VOOM_ |
| 146 | 1029 |
| 1030 DESeq2 - DESeq2_ for details | |
| 1031 | |
| 1032 See above for Bioconductor package documentation for packages exposed in Galaxy by this tool and app store package. | |
| 1033 | |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
1034 Galaxy_ (that's what you are using right now!) for gluing everything together |
| 146 | 1035 |
|
149
3107df74056e
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
iuc
parents:
146
diff
changeset
|
1036 Otherwise, all code and documentation comprising this tool was written by Ross Lazarus and is |
| 146 | 1037 licensed to you under the LGPL_ like other rgenetics artefacts |
| 1038 | |
| 1039 .. _LGPL: http://www.gnu.org/copyleft/lesser.html | |
| 1040 .. _HTSeq: http://www-huber.embl.de/users/anders/HTSeq/doc/index.html | |
| 1041 .. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html | |
| 1042 .. _DESeq2: http://www.bioconductor.org/packages/release/bioc/html/DESeq2.html | |
| 1043 .. _limma_VOOM: http://www.bioconductor.org/packages/release/bioc/html/limma.html | |
| 1044 .. _Galaxy: http://getgalaxy.org | |
| 1045 </help> | |
| 1046 <citations> | |
| 1047 <citation type="doi">doi: 10.1093/bioinformatics/btp616</citation> | |
| 1048 </citations> | |
| 1049 </tool> |