EL 3 new figures

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.1     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

hai <- read_csv("sera_hai.csv")

## Rows: 684 Columns: 9
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (5): UniqueID, collect_time_group, cohort, data_source, target
## dbl  (3): sample_id, replicate, titer
## date (1): date_collect
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

elisa <- read_csv("sera_elisa_auc.csv")

## Rows: 57 Columns: 9
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (4): UniqueID, collect_time_group, cohort, data_source
## dbl  (4): sample_id, A/Victoria/22, A/Darwin/21, B/Phuket/13
## date (1): date_collect
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

# HAI IDs
length(unique(hai$UniqueID))

## [1] 16

head(unique(hai$UniqueID))

## [1] "R24b-Ctl1" "R24b-Ctl2" "R24b-Ctl3" "R24b-Ctl4" "R24b-Ctl5" "R24b-Int1"

# ELISA IDs
length(unique(elisa$UniqueID))

## [1] 16

head(unique(elisa$UniqueID))

## [1] "R24b-Ctl1" "R24b-Ctl2" "R24b-Ctl3" "R24b-Ctl4" "R24b-Ctl5" "R24b-Int1"

unique(hai$collect_time_group)

## [1] "screening" "admission" "discharge" "followup"

unique(elisa$collect_time_group)

## [1] "T0" "T1" "T2" "T3"

elisa_fixed <- elisa %>%
  mutate(collect_time_group = case_when(
    collect_time_group == "T0" ~ "screening",
    collect_time_group == "T1" ~ "admission",
    collect_time_group == "T2" ~ "discharge",
    collect_time_group == "T3" ~ "followup"
  ))

hai_clean <- hai %>%
  filter(collect_time_group == "screening") %>%
  group_by(UniqueID, target) %>%
  summarize(titer = mean(titer, na.rm = TRUE), .groups = "drop") %>%
  pivot_wider(names_from = target, values_from = titer)

names(hai_clean) <- make.names(names(hai_clean))

elisa_clean <- elisa_fixed %>%
  filter(collect_time_group == "screening")

names(elisa_clean) <- make.names(names(elisa_clean))

merged <- inner_join(hai_clean, elisa_clean, by = "UniqueID")

nrow(merged)

## [1] 11

p1 = ggplot(merged, aes(x = A.Darwin.21.y, y = A.Darwin.21.x)) +
  geom_point(size = 3, alpha = 0.7) +
  geom_smooth(method = "lm", linewidth = 1) +
  scale_x_log10() +
  scale_y_log10() +
  labs(
    title = "A/Darwin/21",
    x = "ELISA AUC (log scale)",
    y = "HAI Titer (log scale)"
  ) +
  theme_minimal(base_size = 12)

p1

## `geom_smooth()` using formula = 'y ~ x'

 ggsave("plot.png", plot = p1,, width = 7, height = 4)

## `geom_smooth()` using formula = 'y ~ x'

p2 = ggplot(merged, aes(x = B.Phuket.13.y, y = B.Phuket.13.x)) +
  geom_point(size = 3, alpha = 0.7) +
  geom_smooth(method = "lm") +
  scale_x_log10() +
  scale_y_log10() +
  labs(
    title = "B/Phuket/13",
    x = "ELISA AUC (log scale)",
    y = "HAI Titer (log scale)"
  ) +
  theme_minimal(base_size = 12)

p3 = ggplot(merged, aes(x = A.Victoria.22.y, y = A.Victoria.22.x)) +
  geom_point(size = 3, alpha = 0.7) +
  geom_smooth(method = "lm") +
  scale_x_log10() +
  scale_y_log10() +
  labs(
    title = "A/Victoria/22",
    x = "ELISA AUC (log scale)",
    y = "HAI Titer (log scale)"
  ) +
  theme_minimal(base_size = 12)

install.packages("patchwork")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)

library(patchwork)

graph = p1 | p2 | p3

 graph = (graph) +
  plot_annotation(
    title = "Relationship Between ELISA AUC and HAI Titer Across Influenza Strains"
  )

ggsave("allthree.png", plot = graph, width = 12, height = 5)

## `geom_smooth()` using formula = 'y ~ x'

## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'