tdata.FPKM.sample.info <- readRDS(here("Data","20190406_RNAseq_B6_4wk_2DG_counts_phenotypes.RData"))
tdata.FPKM <- readRDS(here("Data","20190406_RNAseq_B6_4wk_2DG_counts_numeric.RData"))
log.tdata.FPKM <- log(tdata.FPKM + 1)
log.tdata.FPKM <- as.data.frame(log.tdata.FPKM)
log.tdata.FPKM.sample.info <- cbind(log.tdata.FPKM, tdata.FPKM.sample.info[,27238:27240])
log.tdata.FPKM.sample.info <- log.tdata.FPKM.sample.info %>% rownames_to_column() %>% filter(rowname != "A113") %>% column_to_rownames()
log.tdata.FPKM.subset <- log.tdata.FPKM[,colMeans(log.tdata.FPKM != 0) > 0.5]
log.tdata.FPKM.sample.info.subset <- cbind(log.tdata.FPKM.subset,tdata.FPKM.sample.info[,27238:27240])
log.tdata.FPKM.sample.info.subset <- log.tdata.FPKM.sample.info.subset %>% rownames_to_column() %>% filter(rowname != "A113") %>% column_to_rownames()
log.tdata.FPKM.sample.info.subset.liver <- log.tdata.FPKM.sample.info.subset %>% rownames_to_column() %>% filter(Tissue == "Liver") %>% column_to_rownames()
I will use Mouse IDs Treatment, and Time to keep track of the values in the matrices. All other covariates will be discarded.
# Set rownames by mouse ID and tissue
rownames(log.tdata.FPKM.sample.info.subset.liver) <- paste0(rownames(log.tdata.FPKM.sample.info.subset.liver),":", log.tdata.FPKM.sample.info.subset.liver$Time, ":", log.tdata.FPKM.sample.info.subset.liver$Treatment)
# Discard covariates from columns 17333-17336
log.tdata.FPKM.sample.info.subset.liver <- log.tdata.FPKM.sample.info.subset.liver[,-(17333:17335)]
head(log.tdata.FPKM.sample.info.subset.liver[,1:5])
## ENSMUSG00000000001 ENSMUSG00000000028 ENSMUSG00000000031
## A003:4 wks:None 3.076390 0.2468601 0.0000000
## A012:96 hrs:2DG 3.438493 0.2151114 0.1222176
## A021:4 wks:2DG 3.344274 0.5007753 0.0000000
## A030:4 wks:2DG 3.364879 0.3576744 0.3074847
## A039:4 wks:None 3.264996 0.6097656 0.0000000
## A048:4 wks:None 3.117507 0.6780335 0.0861777
## ENSMUSG00000000037 ENSMUSG00000000049
## A003:4 wks:None 0.00000000 7.162832
## A012:96 hrs:2DG 0.00000000 7.396998
## A021:4 wks:2DG 0.00000000 7.198714
## A030:4 wks:2DG 0.00000000 7.169211
## A039:4 wks:None 0.03922071 7.104045
## A048:4 wks:None 0.01980263 7.074328
WGCNA will have poor results if the data have too many missing values. I checked if any metabolites fall into this category.
log.tdata.FPKM.sample.info.subset.liver.missing <- missing(log.tdata.FPKM.sample.info.subset.liver)
cat("logFPKM: ", goodSamplesGenes(log.tdata.FPKM.sample.info.subset.liver.missing, verbose=0)$allOK, "\n")
## logFPKM: TRUE
WGCNA reports that all data are good! I now use hierarchical clustering to detect any obvious outliers. I did not see any particularly egregious outliers.
sampleclustering(log.tdata.FPKM.sample.info.subset.liver.missing)
saveRDS(log.tdata.FPKM.sample.info.subset.liver.missing, here("Data","Liver","log.tdata.FPKM.sample.info.subset.liver.missing.WGCNA.RData"))
Analysis performed by Ann Wells
The Carter Lab The Jackson Laboratory 2023
ann.wells@jax.org