Figure 1: Phylogeny
Load ggplot library for graphics. Also used for later figures.
library(ggplot2)
Load phylogenetic abundances. Data created using calc_phylum_bp.py script from PhymmBL and RDP classified Metaxa data.
phy_data <- read.csv("/data/supplemental_data_code/DatasetS6_phylogeny_comparison_bp.tsv",
sep = "\t")
Plot stacked bar chart.
library(grid)
ggplot(phy_data, aes(x = Program, y = bp, fill = Phylum, order = -as.numeric(Phylum))) +
geom_bar(position = "fill", stat = "identity") + geom_bar(position = "fill",
colour = "#262626", show_guide = FALSE, stat = "identity") + ylab("bp Fraction") +
xlab("Program") + theme(panel.border = element_blank(), plot.margin = unit(c(0.1,
0.1, 0.1, 0.1), "in"), axis.title.x = element_text(size = "16"), axis.title.y = element_text(size = "16"),
axis.text.x = element_text(colour = "black", size = "16"), legend.title = element_text(size = "16"))
Figure 2: Subsystems Bar Chart
Load subsystems abundance data. Data is from MG-RAST, with abundance counts converted to relative abundance.
subsystems_data <- read.csv("/data/supplemental_data_code/DatasetS1_subsystems.tsv",
sep = "\t")
Reorder subsystems from most abundant to least.
subsystems_data$reorderL1 <- reorder(subsystems_data$level.1, subsystems_data$percent)
Plot the subsystems abundance.
ggplot(data = subsystems_data, aes(x = reorderL1, y = percent)) + geom_bar(stat = "identity",
fill = "#06a4ff") + coord_flip() + ylab("Percent") + xlab("Subsystems Level 1") +
theme(legend.position = "none", axis.text.x = element_text(colour = "black"),
axis.text.y = element_text(colour = "black", face = "bold"), axis.ticks.y = element_blank())
Figure 3: PCA
Load Resistance to Antibiotics and Toxic Compounds Subsystem relative abundance data. Raw data from MGRAST.
RATCdata <- read.csv("/data/supplemental_data_code/DatasetS7_RATC.csv")
Perform PCA. Only rows with abundance data selected.
pc <- prcomp(RATCdata[4:34])
Extract principle component values, and merge with main dataset.
pc2 <- data.frame(pc$x)
pc2$Metagenome <- RATCdata$Metagenome
pc3 <- merge(RATCdata, pc2, by = "Metagenome")
Plot.
ggplot(pc3, aes(PC1, PC2, colour = Type, label = Description)) + geom_point(size = 3) +
geom_text(hjust = 0, vjust = 0)
Session Info
sessionInfo()
## R version 3.0.0 (2013-04-03)
## Platform: x86_64-unknown-linux-gnu (64-bit)
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=C LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] grid stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] ggplot2_0.9.3.1 knitr_1.2
##
## loaded via a namespace (and not attached):
## [1] colorspace_1.2-2 dichromat_2.0-0 digest_0.6.3
## [4] evaluate_0.4.3 formatR_0.7 gtable_0.1.2
## [7] labeling_0.1 MASS_7.3-26 munsell_0.4
## [10] plyr_1.8 proto_0.3-10 RColorBrewer_1.0-5
## [13] reshape2_1.2.2 scales_0.2.3 stringr_0.6.2
## [16] tools_3.0.0