Rust_Expression_Browser/Prepare_Figure_2.R at main · SaundersLab/Rust_Expression_Browser · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
#!/usr/local/bin/Rscript

#Prepares four bar plots from a combined metadata file in preparation for paper
#The metadata file must contain the fields: country, date collected,
#host variety and source

#Import required libraries

library("ggplot2")
library("optparse")
library("gridExtra")
library("dplyr")
library("stringr")
library("sf")
library("rnaturalearth")
library("rnaturalearthdata")
library("rgeos")
library("extrafont")

#When using extrafont for the first time
#run font_import() and loadfonts() in an interactive R session

#Parse command line arguments

opt_list <- list(
    make_option("--metadata_all", type = "character",
    help = "tab separated file of all metadata used to
    build expression browser"),
    make_option("--variety_count", type = "character",
    help = "tab separated file of the number of confirmed host
    varities in each country"),
    make_option("--out", type = "character", help = "output plot in pdf format")
)

opt <- parse_args(OptionParser(option_list = opt_list))
f_all <- opt$metadata_all
f_variety <- opt$variety_count
o <- opt$out

#Create dataframe of metadata

metadata_all <- read.delim(f_all,
    header = TRUE, stringsAsFactors = FALSE, quote = "", sep = "\t")

metadata_field <- metadata_all %>% filter(Source == "Field")

variety_count <- read.delim(f_variety, header = TRUE, stringsAsFactors = FALSE,
    quote = "", sep = "\t")

#Prepare country plot

#Pull in country information

world <- ne_countries(scale = "medium", returnclass = "sf")
world_mod <- subset(world, name_long != "Antarctica")

#Prepare country data

countries <- count(metadata_field, country)
countries_merged <- merge(x = world_mod, y = countries,
    by.x = "name_long", by.y = "country", all.x = TRUE)

#Prepare map

country_plot <- ggplot(data = countries_merged) +
geom_sf(aes(fill = n), size = 0.2) +
scale_fill_viridis_c(option = "viridis", name = "Number of
Samples", direction = -1, na.value = "white") + labs(tag = "A") +
theme(panel.grid.major = element_blank(), panel.grid.minor =
element_blank(), panel.background = element_blank(),
panel.border = element_rect(colour = "black", fill = NA, size =
1), axis.text = element_blank(),
axis.ticks = element_blank(),
axis.title = element_text(family = "Arial", size = 7),
legend.text = element_text(family = "Arial", size = 7),
legend.title = element_text(family = "Arial", size = 7),
plot.tag = element_text(family = "Arial", size = 10))

#Prepare variety plot

variety_plot <- ggplot(variety_count,
    aes(x = reorder(Variety, -Count), y = Count)) +
xlab("Wheat Variety") + ylab("Frequency") +
geom_bar(stat = "identity", fill = "navy") + labs(tag = "D") +
theme(panel.grid.major = element_blank(), panel.grid.minor =
element_blank(), panel.background = element_blank(),
panel.border = element_rect(colour = "black", fill = NA, size =
1), axis.text = element_text(family = "Arial", size = 6, colour = "black"),
axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1),
axis.title = element_text(family = "Arial", size = 7),
plot.tag = element_text(family = "Arial", size = 10))

#Prepare dates plot

dates <- as.data.frame(metadata_field$Date.Isolated)
split_dates <- as.data.frame(str_split_fixed(
    as.character(dates$"metadata_field$Date.Isolated"), "/", 3))
split_date_counts <- count(split_dates, V1)
reduced_count <- split_date_counts %>% filter(V1 >= 2013)

dates_plot <- ggplot(reduced_count, aes(x = V1, y = n)) +
xlab("Year Collected") + ylab("Frequency") +
geom_bar(stat = "identity", fill = "navy") + labs(tag = "B") +
theme(panel.grid.major = element_blank(), panel.grid.minor =
element_blank(), panel.background = element_blank(),
panel.border = element_rect(colour = "black", fill = NA, size =
1), axis.text = element_text(family = "Arial", size = 6, colour = "black"),
axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1),
axis.title = element_text(family = "Arial", size = 7),
plot.tag = element_text(family = "Arial", size = 10))

#Prepare sample plot

type_of_sample <- count(metadata_all, Source)

sample_plot <- ggplot(type_of_sample, aes(x = reorder(Source, -n), y = n)) +
xlab("Source of Sample") + ylab("Frequency") +
geom_bar(stat = "identity", fill = "navy") + labs(tag = "C") +
theme(panel.grid.major = element_blank(), panel.grid.minor =
element_blank(), panel.background = element_blank(),
panel.border = element_rect(colour = "black", fill = NA, size =
1), axis.text = element_text(family = "Arial", size = 6, colour = "black"),
axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1),
axis.title = element_text(family = "Arial", size = 7),
plot.tag = element_text(family = "Arial", size = 10))

#Save Plots

plot_list <- list(country_plot, dates_plot, variety_plot, sample_plot)

pdf(o, onefile = FALSE)
layout <- rbind(c(1, 1, 1, 1), c(1, 1, 1, 1), c(3, 3, 4, 4), c(2, 2, 2, 2))
grid.arrange(country_plot, variety_plot, dates_plot, sample_plot,
    layout_matrix = layout)
dev.off()