Explore DITP WastewaterSCAN data

Show code

library(tidyverse)
library(googlesheets4)
library(fs)
library(here)

library(knitr)

library(broom)

# plotting helpers
library(cowplot)
library(patchwork)
library(ggbeeswarm)

theme_set(theme_cowplot())

# Okabe Ito color scheme with amber for yellow; see https://easystats.github.io/see/reference/scale_color_okabeito.html
colors_oi <- grDevices::palette.colors()  
colors_oi['yellow'] <- "#F5C710"

Show code

x <- here('_data/wastewaterscan/wwscan_ditp_all_targets_20230911.csv') %>%
  read_csv

Relative abundance of Influenza A to PMMoV

The WastewaterSCAN Dashboard seems to be showing a smoothed version of the ratio of 1e6 * Influenza_A_gc_g_dry_weight/PMMoV_gc_g_dry_weight,

Show code

x %>%
  ggplot(aes(collection_date, 1e6 * Influenza_A_gc_g_dry_weight/PMMoV_gc_g_dry_weight)) +
  labs(y = '1e6 * Influenza A / PMMoV') +
  geom_line()

I’m interested in the ratio of Flu A to PMMoV in genome copies, since we can use this to get a sence of the fraction of Flu A sequencing reads we could expect (by multiplying this ratio by the fraction of PMMoV reads).

Show code

p1 <- x %>%
  ggplot(aes(collection_date, Influenza_A_gc_g_dry_weight/PMMoV_gc_g_dry_weight)) +
  labs(y = 'Influenza A / PMMoV', x = 'Collection date') +
  scale_x_date(date_labels = '%Y %b') +
  geom_line()
p2 <- x %>%
  ggplot(aes(1e-6 + Influenza_A_gc_g_dry_weight/PMMoV_gc_g_dry_weight)) +
  labs(x = 'Influenza A / PMMoV', y = 'Count') +
  geom_histogram() +
  scale_x_log10(limits = c(NA, 1e-3))
p1 / p2 +
  plot_annotation(title = 'Ratio of Influenza A to PMMoV (genome copies) at DITP')