Calculate and assign flags based on infection history

Usage

cg_annotate_antigenic_history(
  cg,
  episode_number = episode_number,
  dose_number = dose_number,
  episode_variant_summarised = episode_variant_summarised,
  ag_col = antigenic_history
)

Arguments

cg: a chronogram
episode_number: a character vector to identify the episode_number column. Default is "episode_number".
dose_number: a character vector to identify the column containing the number of doses received on that day. Default is "dose_number".
episode_variant_summarised: a character vector to identify the column summarising the variant call. Default is "episode_variant_summarised".
ag_col: column with infection flag

Value

A chronogram

Examples

library(dplyr)

data("built_smallstudy")
cg <- built_smallstudy$chronogram

## add infections to chronogram ##
cg <- cg_add_experiment(
  cg,
  built_smallstudy$infections_to_add
)

## annotate infections ## 
cg <- cg_annotate_episodes_find(
   cg,
   infection_cols = c("LFT", "PCR", "symptoms"),
   infection_present = c("pos", "Post", "^severe")
)
#> Parsed: infection_cols and infection_present
#>           
#> Searching in the [[column]], for the "text": 
#> 
#> Loading required namespace: stringr
#> stringr::str_detect(.data[["LFT"]], "pos") ~ "yes"
#> 
#> stringr::str_detect(.data[["PCR"]], "Post") ~ "yes"
#> 
#> stringr::str_detect(.data[["symptoms"]], "^severe") ~ "yes"
#> 
#> 
#> ...detecting will be exact.
#>           Capitals, spelling etc must be precise
#> 
#> Joining with `by = join_by(calendar_date, elig_study_id)`

## annotate vaccines ## 
cg <- cg %>% cg_annotate_vaccines_count(
 ## the prefix to the dose columns: ##
 dose = dose,
 ## the output column name: ##
 dose_counter = dose_number,
 ## the prefix to the date columns: ##
 vaccine_date_stem = date_dose,
 ## use 14d to 'star' after a dose ##
 intermediate_days = 14)
#> Using stem: date_dose
#> Found vaccine dates
#> date_dose_1
#> 
#> date_dose_2

## annotate exposures ##
cg <- cg %>% cg_annotate_exposures_count(
 episode_number = episode_number,
 dose_number = dose_number,
 ## we have not considered episodes of seroconversion
 N_seroconversion_episode_number = NULL
 )
 
## assign variants ##
cg <- cg %>%
mutate(
episode_variant =
case_when(
    # "is an episode" & "PCR positive" -> Delta #
    (!is.na(episode_number)) & PCR == "Pos" ~ "Delta",
    # "is an episode" & "PCR unavailable" -> Anc/Delta #
    (!is.na(episode_number)) & PCR == "not tested" ~ "Anc/Alpha"
)
)
## ^ this gives a variant call on a SINGLE row of each episode

## fill the variant call ##
cg <- cg %>% cg_annotate_episodes_fill(
 col_to_fill = episode_variant,
 col_to_return = episode_variant_filled,
 .direction = "updown",
 episode_numbers_col = episode_number
 )
#> Joining with `by = join_by(elig_study_id, episode_number)`
 
 cg <- cg %>% 
 mutate(
 episode_variant_summarised =    episode_variant_filled
 ) %>%
 cg_annotate_antigenic_history(
     episode_number = episode_number,
         dose_number = dose_number,
         episode_variant_summarised = episode_variant_summarised,
             ag_col = antigenic_history
             )

 ## and finally:
 summary(factor(cg$antigenic_history))
#>          D0_Anc/Alpha D2_Anc/Alpha,D2_Delta       D2_not_infected 
#>                   649                   649                   649