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

# Discard covariates from columns 17333-17336
log.tdata.FPKM.sample.info.subset.skeletal.muscle <- log.tdata.FPKM.sample.info.subset.skeletal.muscle[,-(17333:17335)]

head(log.tdata.FPKM.sample.info.subset.skeletal.muscle[,1:5])
##                 ENSMUSG00000000001 ENSMUSG00000000028 ENSMUSG00000000031
## A005:4 wks:None           1.921325          0.7371641           4.210200
## A014:96 hrs:2DG           1.993339          0.5306283           4.190261
## A023:4 wks:2DG            2.016235          0.8837675           5.375602
## A032:4 wks:2DG            2.267994          0.7466879           6.806542
## A041:4 wks:None           1.458615          0.8415672           5.477216
## A050:4 wks:None           1.873339          0.7793249           4.869916
##                 ENSMUSG00000000037 ENSMUSG00000000049
## A005:4 wks:None        0.009950331          0.3074847
## A014:96 hrs:2DG        0.048790164          0.7080358
## A023:4 wks:2DG         0.039220713          0.7419373
## A032:4 wks:2DG         0.000000000          0.3646431
## A041:4 wks:None        0.009950331          0.3784364
## A050:4 wks:None        0.029558802          0.5306283

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

saveRDS(log.tdata.FPKM.sample.info.subset.skeletal.muscle.missing, here("Data","Skeletal Muscle","log.tdata.FPKM.sample.info.subset.skeletal.muscle.missing.WGCNA.RData"))

Analysis performed by Ann Wells

The Carter Lab The Jackson Laboratory 2023

ann.wells@jax.org