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

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

head(log.tdata.FPKM.sample.info.subset.heart[,1:5])
##                 ENSMUSG00000000001 ENSMUSG00000000028 ENSMUSG00000000031
## A004:4 wks:None           1.771557          0.8415672           2.373044
## A013:96 hrs:2DG           2.118662          0.7080358           2.210470
## A022:4 wks:2DG            1.997418          0.6471032           1.688249
## A031:4 wks:2DG            2.129421          0.8878913           2.581731
## A040:4 wks:None           1.893112          0.8415672           2.037317
## A049:4 wks:None           1.589235          0.6575200           1.680828
##                 ENSMUSG00000000037 ENSMUSG00000000049
## A004:4 wks:None         0.05826891          0.1310283
## A013:96 hrs:2DG         0.08617770          0.1484200
## A022:4 wks:2DG          0.04879016          0.5653138
## A031:4 wks:2DG          0.05826891          0.0000000
## A040:4 wks:None         0.05826891          0.0000000
## A049:4 wks:None         0.04879016          1.4469190

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

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

Analysis performed by Ann Wells

The Carter Lab The Jackson Laboratory 2023

ann.wells@jax.org