Minor updates to the slide deck and scripts

intermediate-r-rna-seq/Analysis.R

@@ -1,5 +1,5 @@
 #setwd()
-setwd("~/Dropbox (Gladstone)/Bioinformatics/Training_Workshops/Gladstone-internal/Intermediate_RNA-seq_Fall_2019")
+setwd("~/Dropbox (Gladstone)/Gladstone chapters/Workshops/2020/intermediate-r-rna-seq")
 
 library(magrittr)
 library(edgeR)
@@ -34,7 +34,7 @@ colnames(GenewiseCounts) %<>% substring(.,1,7)
 #Concept 1: MA plots
 #------------------------
 
-two_samples <- GenewiseCounts[, c(2, 3)] %>% #Replicate samples
+two_samples <- GenewiseCounts[, c(2, 13)] %>% #Replicate samples
   add(., 1) %>%
   log2()
 
@@ -125,7 +125,7 @@ legend("top", legend=levels(group) %>% substr(., 1, 3),
        pch=pch, col=colors, ncol=2, cex = 0.5)
 
 #PCA plot
-cpm <- cpm(y, log = TRUE, prior.count = 0.01)
+cpm <- cpm(y, log = TRUE)
 rv <- apply(cpm,1,var) 
 
 #Select genes with highest variance.

intermediate-r-rna-seq/tbd.R

@@ -0,0 +1,39 @@
+cnts_casein <- cpm(y)[y$genes$Symbol == "Csn1s2b", ]
+cnts_rndm <- cpm(y)[100, ]
+
+df <- data.frame(Casein = cnts_casein,
+                 Random = cnts_rndm,
+                 targets[, c("CellType", "Status")])
+
+p <- ggplot(df, aes(x=Random, y=1, 
+               color=CellType, shape=Status)) + 
+  geom_point(size=2.5) + 
+  scale_x_log10() +
+  scale_y_log10() +
+  theme_classic() +
+  theme(axis.title.y = element_blank(), 
+        axis.text.y = element_blank(),
+        axis.ticks.y = element_blank(),
+        axis.line.y = element_blank(),
+        legend.position = "top",
+        legend.box = "vertical",
+        plot.margin = margin(0.5, 0.5, 0.5, 0.5, "cm"))
+ggsave("Random.png",
+       p,
+       width = 3,
+       height = 3)
+
+p <- ggplot(df, aes(x=1, y=Random, 
+               color=CellType, shape=Status)) + 
+  geom_point(size=2.5) + 
+  scale_x_log10() +
+  scale_y_log10()  +
+  theme(axis.title.x = element_blank(), 
+        axis.text.x = element_blank(),
+        axis.ticks.x = element_blank())
+
+ggsave("Random.png",
+       p)
+
+  xlab(paste("PC1:", pc1_var, "% variance")) + 
+  ylab(paste("PC2:", pc2_var, "% variance"))