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.spleen <- log.tdata.FPKM.sample.info.subset %>% rownames_to_column() %>% filter(Tissue == "Spleen") %>% 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.spleen) <- paste0(rownames(log.tdata.FPKM.sample.info.subset.spleen),":", log.tdata.FPKM.sample.info.subset.spleen$Time, ":", log.tdata.FPKM.sample.info.subset.spleen$Treatment)
# Discard covariates from columns 17333-17336
log.tdata.FPKM.sample.info.subset.spleen <- log.tdata.FPKM.sample.info.subset.spleen[,-(17333:17335)]
head(log.tdata.FPKM.sample.info.subset.spleen[,1:5])
## ENSMUSG00000000001 ENSMUSG00000000028 ENSMUSG00000000031
## A001:4 wks:None 3.819688 2.177022 0.34358970
## A010:96 hrs:2DG 3.756071 1.560248 0.41871033
## A019:4 wks:2DG 3.758639 3.150597 0.04879016
## A028:4 wks:2DG 3.834278 3.017494 0.10436002
## A037:4 wks:None 3.359333 3.205182 0.54812141
## A046:4 wks:None 3.857778 2.494032 0.34358970
## ENSMUSG00000000037 ENSMUSG00000000049
## A001:4 wks:None 0.07696104 0.7701082
## A010:96 hrs:2DG 0.08617770 0.6365768
## A019:4 wks:2DG 0.45107562 1.2527630
## A028:4 wks:2DG 0.85866162 0.2546422
## A037:4 wks:None 0.30010459 0.1823216
## A046:4 wks:None 0.12221763 1.4085450
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.spleen.missing <- missing(log.tdata.FPKM.sample.info.subset.spleen)
cat("logFPKM: ", goodSamplesGenes(log.tdata.FPKM.sample.info.subset.spleen.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.spleen.missing)
saveRDS(log.tdata.FPKM.sample.info.subset.spleen.missing, here("Data","Spleen","log.tdata.FPKM.sample.info.subset.spleen.missing.WGCNA.RData"))
Analysis performed by Ann Wells
The Carter Lab The Jackson Laboratory 2023
ann.wells@jax.org