Dear all, I am receiving an error when running the topTable function within the limma package, and I am having trouble deciphering its meaning. I would appreciate any feedback that could be provided! My data set is stored in a matrix called "exprSet_entrez", with these details and sample values (no missing data): > dim(exprSet_entrez) [1] 25528 24 > exprSet_entrez[1:10,] entrez X577.ga.cel X578.ga.cel X579.ga.cel X580.ga.cel X583.ga.cel 1 100038431 3.482030 3.517921 3.429582 3.471463 3.368129 2 100038431 5.994481 6.136057 6.065544 6.144734 5.965864 3 18777 9.286540 9.378587 9.347815 9.285812 9.236086 4 21399 9.281334 9.164668 9.277620 9.210111 9.246223 5 108664 8.444451 8.516510 8.449924 8.434129 8.372296 6 18387 3.653424 3.547419 3.493820 3.726097 3.463435 7 12421 7.730113 7.670693 7.571302 7.688184 7.605875 8 620393 3.391134 3.400358 3.424306 3.304937 3.367195 9 240690 4.063018 3.979794 4.163925 4.082816 3.985831 10 319263 9.110032 9.169712 9.105135 9.080157 9.148936 X584.ga.cel X585.ga.cel X588.ga.cel X590.ga.cel X591.ga.cel X593.ga.cel 1 3.511509 3.534144 3.425228 3.648801 3.512385 3.373739 2 5.766239 6.015806 5.999773 6.190905 6.229489 6.188441 3 8.972189 9.356392 9.300335 9.329950 9.378346 9.326097 4 9.321111 9.352220 9.406007 9.508528 9.305394 9.313589 5 8.377022 8.371282 8.386898 8.465536 8.466654 8.546152 6 3.950703 3.433874 3.734620 3.746484 3.442888 3.531611 7 7.065636 7.722109 7.579347 7.690983 7.681199 7.726777 8 3.718955 3.449373 3.564055 3.587321 3.389434 3.383427 9 4.388968 4.193013 4.502328 4.296238 4.020287 4.033473 10 8.894222 9.107174 8.982389 8.986460 9.234685 9.167963 X594.ga.cel X596.ga.cel X597.ga.cel X598.ga.cel X599.ga.cel X601.ga.cel 1 3.654531 3.516786 3.488017 3.465478 3.471159 3.481133 2 6.342066 6.286220 6.228640 6.313395 6.025776 5.848678 3 9.349673 9.367497 9.326966 9.339992 9.335472 9.285127 4 9.461578 9.309374 9.317105 9.211384 9.366058 9.245989 5 8.514357 8.462649 8.471525 8.436176 8.322131 8.456860 6 3.735984 3.602093 3.457239 3.643317 3.592110 3.490955 7 7.787006 7.869115 7.820069 7.752202 7.599940 7.646468 8 3.465870 3.527124 3.494260 3.465870 3.536719 3.540971 9 4.051419 4.087084 4.103557 4.028897 4.125522 3.911318 10 9.185123 9.228618 9.231650 9.228426 9.046149 9.179135 X605.ga.cel X606.ga.cel X607.ga.cel X608.ga.cel X610.ga.cel X611.ga.cel 1 3.593981 3.457572 3.659534 3.483897 3.488017 3.481450 2 6.207318 6.322827 6.113176 5.912394 5.947696 5.850750 3 9.376264 9.370653 9.281247 9.288041 9.444991 9.311493 4 9.326719 9.282408 9.346006 9.367484 9.310837 9.345151 5 8.512225 8.482284 8.395395 8.208786 8.301569 8.341434 6 3.483677 3.668495 3.410698 3.823439 3.514624 3.654546 7 7.863490 7.711175 7.655057 7.319929 7.768672 7.760662 8 3.395674 3.440786 3.395949 3.492032 3.511352 3.489662 9 3.905314 4.057490 4.275029 4.299711 4.062283 4.087084 10 9.406058 9.183311 9.227215 9.029998 9.206172 9.151521 I followed the limma guide to conduct an analysis and was successful with the following analysis (79 significant genes): > design<-cbind(con=c(rep(1,4),rep(0,19)),pa=c(rep(0,4),rep(1,4),rep(0 ,15)),pma=c(rep(0,8),rep(1,4),rep(0,11)),sa=c(rep(0,12),rep(1,4),rep(0 ,7)),oa=c(rep(0,16),rep(1,3),rep(0,4)),na=c(rep(0,19),rep(1,4))) > colnames(design)<-c("con","pa","pma","sa","oa","na") > fit_entrez<-lmFit(exprSet_entrez[,2:24],design) > contrast_sa<-makeContrasts(sa1=sa-con,levels=design) > fit2_sa<-contrasts.fit(fit_entrez,contrast_sa) > fit2_sa<-eBayes(fit2_sa) > top_sa<-topTable(fit2_sa, p.value=0.05, number=500) But I get an error running a similar analysis on another set of columns as described below: > contrast_pma<-makeContrasts(pma1=pma-con,levels=design) > fit2_pma<-contrasts.fit(fit_entrez,contrast_pma) > fit2_pma<-eBayes(fit2_pma) > top_pma<toptable(fit2_pma, p.value="0.05," number="500)" error="" in="" ops.data.frame(top_pma,="" toptable(fit2_pma,="" p.value="0.05," number="500))" :="" <="" only="" defined="" for="" equally-sized="" data="" frames="" i="" am="" not="" sure="" what="" is="" causing="" the="" error="" since="" the="" data="" is="" just="" coming="" from="" different="" columns="" of="" the="" same="" matrix.="" below="" is="" my="" r="" info:=""> sessionInfo() R version 2.14.1 (2011-12-22) Platform: x86_64-pc-mingw32/x64 (64-bit) locale: [1] LC_COLLATE=English_Canada.1252 LC_CTYPE=English_Canada.1252 [3] LC_MONETARY=English_Canada.1252 LC_NUMERIC=C [5] LC_TIME=English_Canada.1252 attached base packages: [1] tcltk tools stats graphics grDevices utils datasets [8] methods base other attached packages: [1] limma_3.10.2 SciViews_0.9-4 ellipse_0.3-5 MASS_7.3-16 svGUI_0.9-50 [6] svMisc_0.9-63 Hopefully I have provided enough information for troubleshooting purposes. Thanks in advance! Regards, Monica Wong Monica Wong, M.Sc. Bioinformatics Ph.D. Statistics Student University of Guelph http://www.uoguelph.ca/~mwong09/ [[alternative HTML version deleted]]

This looks like a simple syntax error. See below On Mon, Mar 5, 2012 at 9:07 PM, Monica Wong <mwong09@uoguelph.ca> wrote: > > Dear all, > > I am receiving an error when running the topTable function within the > limma package, and I am having trouble deciphering its meaning. I would > appreciate any feedback that could be provided! > > My data set is stored in a matrix called "exprSet_entrez", with these > details and sample values (no missing data): > > > dim(exprSet_entrez) > [1] 25528 24 > > exprSet_entrez[1:10,] > entrez X577.ga.cel X578.ga.cel X579.ga.cel X580.ga.cel X583.ga.cel > 1 100038431 3.482030 3.517921 3.429582 3.471463 3.368129 > 2 100038431 5.994481 6.136057 6.065544 6.144734 5.965864 > 3 18777 9.286540 9.378587 9.347815 9.285812 9.236086 > 4 21399 9.281334 9.164668 9.277620 9.210111 9.246223 > 5 108664 8.444451 8.516510 8.449924 8.434129 8.372296 > 6 18387 3.653424 3.547419 3.493820 3.726097 3.463435 > 7 12421 7.730113 7.670693 7.571302 7.688184 7.605875 > 8 620393 3.391134 3.400358 3.424306 3.304937 3.367195 > 9 240690 4.063018 3.979794 4.163925 4.082816 3.985831 > 10 319263 9.110032 9.169712 9.105135 9.080157 9.148936 > X584.ga.cel X585.ga.cel X588.ga.cel X590.ga.cel X591.ga.cel X593.ga.cel > 1 3.511509 3.534144 3.425228 3.648801 3.512385 3.373739 > 2 5.766239 6.015806 5.999773 6.190905 6.229489 6.188441 > 3 8.972189 9.356392 9.300335 9.329950 9.378346 9.326097 > 4 9.321111 9.352220 9.406007 9.508528 9.305394 9.313589 > 5 8.377022 8.371282 8.386898 8.465536 8.466654 8.546152 > 6 3.950703 3.433874 3.734620 3.746484 3.442888 3.531611 > 7 7.065636 7.722109 7.579347 7.690983 7.681199 7.726777 > 8 3.718955 3.449373 3.564055 3.587321 3.389434 3.383427 > 9 4.388968 4.193013 4.502328 4.296238 4.020287 4.033473 > 10 8.894222 9.107174 8.982389 8.986460 9.234685 9.167963 > X594.ga.cel X596.ga.cel X597.ga.cel X598.ga.cel X599.ga.cel X601.ga.cel > 1 3.654531 3.516786 3.488017 3.465478 3.471159 3.481133 > 2 6.342066 6.286220 6.228640 6.313395 6.025776 5.848678 > 3 9.349673 9.367497 9.326966 9.339992 9.335472 9.285127 > 4 9.461578 9.309374 9.317105 9.211384 9.366058 9.245989 > 5 8.514357 8.462649 8.471525 8.436176 8.322131 8.456860 > 6 3.735984 3.602093 3.457239 3.643317 3.592110 3.490955 > 7 7.787006 7.869115 7.820069 7.752202 7.599940 7.646468 > 8 3.465870 3.527124 3.494260 3.465870 3.536719 3.540971 > 9 4.051419 4.087084 4.103557 4.028897 4.125522 3.911318 > 10 9.185123 9.228618 9.231650 9.228426 9.046149 9.179135 > X605.ga.cel X606.ga.cel X607.ga.cel X608.ga.cel X610.ga.cel X611.ga.cel > 1 3.593981 3.457572 3.659534 3.483897 3.488017 3.481450 > 2 6.207318 6.322827 6.113176 5.912394 5.947696 5.850750 > 3 9.376264 9.370653 9.281247 9.288041 9.444991 9.311493 > 4 9.326719 9.282408 9.346006 9.367484 9.310837 9.345151 > 5 8.512225 8.482284 8.395395 8.208786 8.301569 8.341434 > 6 3.483677 3.668495 3.410698 3.823439 3.514624 3.654546 > 7 7.863490 7.711175 7.655057 7.319929 7.768672 7.760662 > 8 3.395674 3.440786 3.395949 3.492032 3.511352 3.489662 > 9 3.905314 4.057490 4.275029 4.299711 4.062283 4.087084 > 10 9.406058 9.183311 9.227215 9.029998 9.206172 9.151521 > > I followed the limma guide to conduct an analysis and was successful with > the following analysis (79 significant genes): > > > > design<-cbind(con=c(rep(1,4),rep(0,19)),pa=c(rep(0,4),rep(1,4),rep(0 ,15)),pma=c(rep(0,8),rep(1,4),rep(0,11)),sa=c(rep(0,12),rep(1,4),rep(0 ,7)),oa=c(rep(0,16),rep(1,3),rep(0,4)),na=c(rep(0,19),rep(1,4))) > > colnames(design)<-c("con","pa","pma","sa","oa","na") > > fit_entrez<-lmFit(exprSet_entrez[,2:24],design) > > contrast_sa<-makeContrasts(sa1=sa-con,levels=design) > > fit2_sa<-contrasts.fit(fit_entrez,contrast_sa) > > fit2_sa<-eBayes(fit2_sa) > > top_sa<-topTable(fit2_sa, p.value=0.05, number=500) > > But I get an error running a similar analysis on another set of columns as > described below: > > > contrast_pma<-makeContrasts(pma1=pma-con,levels=design) > > fit2_pma<-contrasts.fit(fit_entrez,contrast_pma) > > fit2_pma<-eBayes(fit2_pma) > > top_pma<toptable(fit2_pma, p.value="0.05," number="500)"> You are using the comparison operator "<" instead of assignment "<-" > Error in Ops.data.frame(top_pma, topTable(fit2_pma, p.value = 0.05, number > = 500)) : > < only defined for equally-sized data frames > > I am not sure what is causing the error since the data is just coming from > different columns of the same matrix. Below is my R info: > > > sessionInfo() > R version 2.14.1 (2011-12-22) > Platform: x86_64-pc-mingw32/x64 (64-bit) > > locale: > [1] LC_COLLATE=English_Canada.1252 LC_CTYPE=English_Canada.1252 > [3] LC_MONETARY=English_Canada.1252 LC_NUMERIC=C > [5] LC_TIME=English_Canada.1252 > > attached base packages: > [1] tcltk tools stats graphics grDevices utils datasets > [8] methods base > > other attached packages: > [1] limma_3.10.2 SciViews_0.9-4 ellipse_0.3-5 MASS_7.3-16 svGUI_0.9-50 > [6] svMisc_0.9-63 > > Hopefully I have provided enough information for troubleshooting purposes. > Thanks in advance! > > Regards, > Monica Wong > > > Monica Wong, M.Sc. Bioinformatics > Ph.D. Statistics Student > University of Guelph > http://www.uoguelph.ca/~mwong09/ > > > [[alternative HTML version deleted]] > > _______________________________________________ > Bioconductor mailing list > Bioconductor@r-project.org > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: > http://news.gmane.org/gmane.science.biology.informatics.conductor > [[alternative HTML version deleted]]