Collection statistics

The collection by numbers (01/01/2024):

• 4143 samples across the Eastern Australian coastline

• Subtropical to tropical collections, spanning 20° of latitude (-11.4°S to -30.94°S)

• 54 host families

• 279 host species

library(tidyverse)
library(lubridate)
library(ggplot2)
library(plotly)

data_pie_latitude <- read.csv("https://raw.githubusercontent.com/symbiobase/symbioID/main/Symbiobase.csv") |> 
  dplyr::select(sample_id, collection_date, location, site, longitude, latitude, host_family, host_genus, host_species) |> 
  mutate(latitude=round(latitude,3), longitude=round(longitude,3), collection_date=ymd(collection_date)) |> 
  mutate(location = gsub("_", " ", location),
         site = gsub("_", " ", site),
         host_genus = gsub("_", " ", host_genus),
         host_species = gsub("_", " ", host_species)) |> 
  # drop_na(lat) %>%
  mutate(latitude_groups = cut(latitude, breaks = seq(-34, -13, by = 1), include.lowest = TRUE)) %>%
  filter(!latitude_groups=="NA") |> 
  mutate(latitude_groups = gsub(",", " to ", latitude_groups) %>%
                           gsub("\\]", ")", .) %>%
                           gsub("(-?\\d+)", "\\1°S", .)) |> 
  group_by(latitude_groups) |> 
  summarise(count=n())

plot_lat <- ggplot() + theme_void() +
  ggtitle("Samples by latitude") + ylab("") + xlab("") +
  geom_bar(data=data_pie_latitude, aes(x="", y=count, fill=latitude_groups), linewidth=0.1, color="black", stat="identity", width=1) +
  coord_polar("y", start=0) +
  #geom_text(data=data_pie_latitude, aes(x="", y=count, label = count), size=6, position = position_stack(vjust = 0.5)) +
  scale_fill_brewer(palette="RdBu")  + theme(legend.text = element_text(size=8), legend.title=element_blank())




data_pie_species <- read.csv("https://raw.githubusercontent.com/symbiobase/symbioID/main/Symbiobase.csv") %>%
  dplyr::select(sample_id, collection_date, location, site, longitude, latitude, host_family, host_genus, host_species) %>%
  mutate(
    latitude = round(latitude, 3),
    longitude = round(longitude, 3),
    collection_date = ymd(collection_date),
    location = gsub("_", " ", location),
    site = gsub("_", " ", site),
    host_genus = gsub("_", " ", host_genus),
    host_species = gsub("_", " ", host_species),
    latitudinal_band = as.character(cut(latitude, breaks = seq(-34, -13, by = 1), include.lowest = TRUE))
  ) %>%
  mutate(latitudinal_band = gsub(",", " to ", latitudinal_band) %>%
                           gsub("\\]", ")", .) %>%
                           gsub("(-?\\d+)", "\\1°S", .)) %>%
  filter(!host_species %in% c("sp1", "sp2")) %>%
  mutate(host_species = factor(host_species, levels = sort(unique(host_species), decreasing = FALSE))) %>%
  drop_na(host_species) %>%
  group_by(host_species) %>%
  summarise(count = n()) %>%
  slice_max(order_by = count, n = 10) 



plot_species <- ggplot() + theme_void() +
  ggtitle("Samples by most common host species") + ylab("") + xlab("") +
  geom_bar(data=data_pie_species, aes(x="", y=count, fill=host_species), 
           show.legend=TRUE, linewidth=0.1, color="black", stat="identity", width=1) +
  coord_polar("y", start=0) +
  scale_fill_brewer(palette="PiYG") + theme(legend.text = element_text(size=8), legend.title=element_blank())



data_pie_family <- read.csv("https://raw.githubusercontent.com/symbiobase/symbioID/main/Symbiobase.csv") |>
  dplyr::select(sample_id, collection_date, location, site, longitude, latitude, host_family, host_genus, host_species) |> 
  mutate(latitude=round(latitude,3), longitude=round(longitude,3), collection_date=ymd(collection_date)) |> 
  mutate(location = gsub("_", " ", location),
         site = gsub("_", " ", site),
         host_genus = gsub("_", " ", host_genus),
         host_species = gsub("_", " ", host_species)) |> 
  mutate(latitudinal_band = as.character(cut(latitude, breaks = seq(-34, -13, by = 1), include.lowest = TRUE))) %>%
  mutate(latitudinal_band = gsub(",", " to ", latitudinal_band) %>%
                           gsub("\\]", ")", .) %>%
                           gsub("(-?\\d+)", "\\1°S", .)) %>%
  filter(!host_species %in% c("sp1", "sp2")) %>%
  mutate(host_family = factor(host_family, levels = sort(unique(host_family), decreasing = FALSE))) |> 
  drop_na(host_family) |> 
  group_by(host_family) %>%
  summarise(count = n()) %>%
  slice_max(order_by = count, n = 10) 



plot_family <- ggplot() + theme_void() +
  ggtitle("Samples by most common host species") + ylab("") + xlab("") +
  geom_bar(data=data_pie_family, aes(x="", y=count, fill=host_family), 
           show.legend=TRUE, linewidth=0.1, color="black", stat="identity", width=1) +
  coord_polar("y", start=0) +
  scale_fill_brewer(palette="Spectral") + theme(legend.text = element_text(size=8), legend.title=element_blank())


  
library(patchwork)
  
(plot_lat + plot_species) / (plot_spacer()+plot_family)