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.hippocampus <- log.tdata.FPKM.sample.info.subset %>% rownames_to_column() %>% filter(Tissue == "Hippocampus") %>% column_to_rownames()

Wrangle Data

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.hippocampus) <- paste0(rownames(log.tdata.FPKM.sample.info.subset.hippocampus),":", log.tdata.FPKM.sample.info.subset.hippocampus$Time, ":", log.tdata.FPKM.sample.info.subset.hippocampus$Treatment)

# Discard covariates from columns 17333-17336
log.tdata.FPKM.sample.info.subset.hippocampus <- log.tdata.FPKM.sample.info.subset.hippocampus[,-(17333:17336)]

head(log.tdata.FPKM.sample.info.subset.hippocampus[,1:5])
##                 ENSMUSG00000000001 ENSMUSG00000000028 ENSMUSG00000000031
## A008:4 wks:None           2.889816          0.7129498          0.2776317
## A017:96 hrs:2DG           2.731115          1.1847900          0.1133287
## A026:4 wks:2DG            2.915606          1.1662709          0.1397619
## A035:4 wks:2DG            2.683758          0.5128236          0.1222176
## A044:4 wks:None           2.933325          0.8329091          0.2070142
## A053:4 wks:None           2.584752          0.5877867          0.2926696
##                 ENSMUSG00000000037 ENSMUSG00000000049
## A008:4 wks:None          0.3148107          0.6471032
## A017:96 hrs:2DG          0.2468601          0.3364722
## A026:4 wks:2DG           0.6780335          0.8109302
## A035:4 wks:2DG           0.5364934          0.3646431
## A044:4 wks:None          0.3506569          0.0000000
## A053:4 wks:None          0.6151856          0.2926696

Check Data for Missing Values

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.hippocampus.missing <- missing(log.tdata.FPKM.sample.info.subset.hippocampus)
cat("logFPKM: ", goodSamplesGenes(log.tdata.FPKM.sample.info.subset.hippocampus.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.hippocampus.missing)

saveRDS(log.tdata.FPKM.sample.info.subset.hippocampus.missing, here("Data","Hippocampus","log.tdata.FPKM.sample.info.subset.hippocampus.missing.WGCNA.RData"))

Analysis performed by Ann Wells

The Carter Lab The Jackson Laboratory 2023

ann.wells@jax.org