[BioC] edgeR annotation mission from topTags output

R [guest] guest at bioconductor.org
Sun Aug 25 22:25:41 CEST 2013


after updating R and edgeR I lost the annotations in the final Diff.Expressed matrix (toptags) when running the edgeR pipeline. How do I get the row.names from the data matrix into the topTag-matrix?

data <- read.table("KO_and_WT_Summary_miRNA_Expression.csv", row.names=1, sep="", header=T)


head(data)
                  T0h T0.25h T0.5h   T1h   T2h   T3h   T6h  T12h  T24h  T48h   C0h C0.25h
mmu-let-7a-1-3p   450    329   395   300   469   320   245   281   300   376   166    242
mmu-let-7a-5p   93070  62871 65013 69714 73983 60836 49885 63788 62161 65595 48525  32111
mmu-let-7c-2-3p   436    325   391   295   466   314   243   278   300   376   152    220
mmu-let-7c-5p     544    367   350   492   331   266   323   309   403   613   255    219
mmu-let-7d-3p    7397   5854  5280  6883  5021  5117  5327  6137  5649  5197  6460   3951
mmu-let-7d-5p    8893   7584  7082  8062  6258  6423  6120  7053  7000  6998  7265   3712

keep <- rowSums(cpm(data)>2) >=2
data <- data[keep, ]
table(keep)
y <- DGEList(counts=data[,1:18], genes=data[,0:1])
y <- calcNormFactors(y)
y$samples
plotMDS(y,main="")
Time=c("0.25h","0.5h","1h","2h","3h","6h","12h","24h","48h","0.25h","0.5h","1h","2h","3h","6h","12h","24h","48h")
Condition=c("KO","KO","KO","KO","KO","KO","KO","KO","KO","WT","WT","WT","WT","WT","WT","WT","WT","WT")
design <- model.matrix(~0+Time+Condition)
rownames(design) <- colnames(y)
y <- estimateGLMCommonDisp(y, design, verbose=TRUE, method="deviance",robust=TRUE, subset=NULL)
y <- estimateGLMTrendedDisp(y, design)
y <- estimateGLMTagwiseDisp(y, design)
fit <- glmFit(y, design)
lrt <- glmLRT(fit)
topTags(lrt)

Coefficient:  ConditionWT
     genes      logFC    logCPM        LR PValue FDR
189   5128 -11.028422  7.905804  4456.297      0   0
188  12271 -10.582267  9.061326  5232.075      0   0
167 121120  -9.831894 12.475576  5957.104      0   0
34  255235  -9.771266 13.592968  7355.592      0   0
168 311906  -9.597952 13.907951 10710.111      0   0
166 631262  -9.592550 14.932018 11719.222      0   0
79      79   9.517226 11.466696  7964.269      0   0
169   2512  -8.946429  6.758584  2502.548      0   0
448   3711  -7.650068  7.764682  2914.784      0   0
32  260769  -7.412197 13.633352  4906.198      0   0

 -- output of sessionInfo(): 

> sessionInfo()
R version 3.0.1 (2013-05-16)
Platform: x86_64-pc-linux-gnu (64-bit)

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=en_US.UTF-8       
 [4] LC_COLLATE=en_US.UTF-8     LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=C                 LC_NAME=C                  LC_ADDRESS=C              
[10] LC_TELEPHONE=C             LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] splines   stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] reshape2_1.2.2  ggplot2_0.9.3.1 edgeR_3.2.4     limma_3.16.7   

loaded via a namespace (and not attached):
 [1] colorspace_1.2-2   dichromat_2.0-0    digest_0.6.3       grid_3.0.1        
 [5] gtable_0.1.2       labeling_0.2       MASS_7.3-26        munsell_0.4.2     
 [9] plyr_1.8           proto_0.3-10       RColorBrewer_1.0-5 scales_0.2.3      
[13] stringr_0.6.2      tools_3.0.1

--
Sent via the guest posting facility at bioconductor.org.



More information about the Bioconductor mailing list