moved to new filenames, added genome size vs CDS plot

1KFG · Aug 10, 2015 · b8b25a0 · b8b25a0
1 parent 3b85ac7
commit b8b25a0
Show file tree

Hide file tree

Showing 7 changed files with 378 additions and 345 deletions.
diff --git a/summary_stats/genome.lens.dat b/summary_stats/genome.lens.dat
diff --git a/summary_stats/genome_size.pdf → summary_stats/genome_size_gene_stat.pdf b/summary_stats/genome_size.pdf → summary_stats/genome_size_gene_stat.pdf
diff --git a/summary_stats/genome_size_gene_stat.png b/summary_stats/genome_size_gene_stat.png
diff --git a/summary_stats/genome_stat_plot.R b/summary_stats/genome_stat_plot.R
@@ -0,0 +1,17 @@
+# datasets from 1KFG genomes  - http://1000.fungalgenomes.org
+dat <-read.csv("genome_stats.csv",header=T,sep=",",row.names=1)
+summary(dat)
+pdf("genome_size_gene_stat.pdf")
+
+#boxplot(dat$genome,main="Genome Size")
+#boxplot(dat$CDS,main="CDS count")
+plot(dat$genome,dat$CDS,main="Fungal genome size vs CDS count (N=338)",xlab="Genome Size",ylab="Gene count")
+
+png("genome_size_gene_stat.png")
+plot(dat$genome,dat$CDS,main="Fungal genome size vs CDS count (N=338)",xlab="Genome Size",ylab="Gene count")
+
+fit <- lm(formula = dat$genome ~ dat$CDS)
+summary(fit)
+summary(fit)$r.squared
+cor(dat$genome, dat$CDS)**2
+summary(dat)