library("tidyverse")

counts <- read.csv("data/GSE60450_GeneLevel_Normalized(CPM.and.TMM)_data.csv")

sampleinfo <- read.csv("data/GSE60450_filtered_metadata.csv")


colnames(counts)[1] <- "gene_id"
colnames(sampleinfo)[1] <- "sample_id"

view(counts)
view(sampleinfo)


seqdata <- pivot_longer(counts, cols = starts_with("GSM"),
                        names_to = "Sample", values_to = "Count")


seqdata <- pivot_longer(counts, cols = GSM1480291:GSM1480302,
                        names_to = "Sample", values_to = "Count")

seqdata <- pivot_longer(counts, cols = -c("gene_id", "gene_symbol"),
                        names_to = "Sample", values_to = "Count")


view(seqdata)



allinfo <- full_join(seqdata, sampleinfo, by = c("Sample"="sample_id"))


view(allinfo)


ggplot(data = allinfo, mapping = aes(x = Sample, y = Count)) +
  geom_boxplot()

ggplot(data = allinfo, mapping = aes(x = Sample, y = log2(Count))) +
  geom_boxplot()


ggplot(data = allinfo, mapping = aes(x = Sample, y = log2(Count + 1))) +
  geom_boxplot()


ggplot(data = allinfo, mapping = aes(x = Sample, y = log2(Count + 1))) +
  geom_violin()



ggplot(data = allinfo, mapping = aes(x = Sample, y = log2(Count + 1), colour = Sample)) +
  geom_boxplot()

ggplot(data = allinfo, mapping = aes(x = Sample, y = log2(Count + 1), colour = Sample)) +
  geom_violin()



ggplot(data = allinfo, mapping = aes(x = Sample, y = log2(Count + 1), 
  fill = Sample)) +
  geom_boxplot()


ggplot(data = allinfo, mapping = aes(x = Sample, weight = log2(Count + 1), 
                                     fill = Sample)) +
  geom_bar()




data("women")

view(women)


ggplot(data = women, mapping = aes(x = height, y = weight))+
  geom_point()

ggplot(data = women, mapping = aes(x = height, y = weight))+
  geom_path()



ggplot(data = allinfo, mapping = aes(x = log2(Count+1)))+
  geom_density()


ggplot(data = women, mapping = aes(x = weight))+
  geom_density()



ggplot(data = allinfo, mapping = aes(x = log2(Count+1), fill = Sample ))+
  geom_density()



ggplot(data = allinfo, mapping = aes(x = log2(Count+1), colour = Sample ))+
  geom_density()


pdf("myplot.pdf")
ggplot(data = allinfo, mapping = aes(x = log2(Count+1), colour = Sample ))+
  geom_density()
dev.off()