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.hypothalamus <- log.tdata.FPKM.sample.info.subset %>% rownames_to_column() %>% filter(Tissue == "Hypothanamus") %>% 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.hypothalamus) <- paste0(rownames(log.tdata.FPKM.sample.info.subset.hypothalamus),":", log.tdata.FPKM.sample.info.subset.hypothalamus$Time, ":", log.tdata.FPKM.sample.info.subset.hypothalamus$Treatment)

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

head(log.tdata.FPKM.sample.info.subset.hypothalamus[,1:5])
##                 ENSMUSG00000000001 ENSMUSG00000000028 ENSMUSG00000000031
## A007:4 wks:None           2.474856          0.7608058          0.1222176
## A016:96 hrs:2DG           2.819592          0.4762342          0.6881346
## A025:4 wks:2DG            2.945491          0.6471032          0.9242589
## A034:4 wks:2DG            2.596001          0.5653138          0.3435897
## A043:4 wks:None           2.709383          0.7793249          0.3784364
## A052:4 wks:None           2.824944          0.6523252          0.5709795
##                 ENSMUSG00000000037 ENSMUSG00000000049
## A007:4 wks:None          0.3435897          0.5128236
## A016:96 hrs:2DG          0.9360934          0.2700271
## A025:4 wks:2DG           0.8960880          0.8020016
## A034:4 wks:2DG           0.4252677          0.3784364
## A043:4 wks:None          1.0043016          0.1906204
## A052:4 wks:None          0.7839015          0.3148107

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

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

Analysis performed by Ann Wells

The Carter Lab The Jackson Laboratory 2023

ann.wells@jax.org