In saketkc/covmuller: A tool to model COVID19 variant prevalence using data from GISAID

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  gganimate = list(
    nframes = 0
  ),
  out.width = "100%"
)
knitr::opts_chunk$set(echo = TRUE, warning = FALSE, message = FALSE, fig.dim = c(12, 5))

suppressPackageStartupMessages({
  library(covmuller)
  library(COVID19)
  library(tidyverse)
})
theme_set(CovmullerTheme())

Get variants data for Germany

gisaid_metadata <- qs::qread("~/data/epicov/metadata_tsv_2024_04_11.qs")
gisaid_germany <- gisaid_metadata %>%
  filter(Country == "Germany") %>%
  filter(Host == "Human")
# format metadata
gisaid_germany <- FormatGISAIDMetadata(gisaid_germany)
gisaid_germany <- gisaid_germany %>%
  arrange(State, MonthYearCollected) %>%
  filter(pangolin_lineage != "Unknown")

vocs <- GetVOCs()
custom_voc_mapping <- list(
  `JN.1` = "JN.1",
  `JN.1.*` = "JN.1",
  `HV.1` = "HV.1",
  `HV.1.*` = "HV.1",
  `B.1` = "B.1",
  `B.1.1.306` = "B.1",
  `B.1.1.306.*` = "B.1",
  `B.1.1.326` = "B.1",
  `B.1.36.29` = "B.1",
  `B.1.560` = "B.1",
  `B.1.1` = "B.1",
  `B.1.210` = "B.1",
  `B.1.36.8` = "B.1",
  `B.1.36` = "B.1",
  `B.1.36.*` = "B.1"
)
gisaid_germany <- gisaid_germany %>% filter(pangolin_lineage != "None")

gisaid_germany <- CollapseLineageToVOCs(
  variant_df = gisaid_germany,
  vocs = vocs,
  custom_voc_mapping = custom_voc_mapping,
  summarize = FALSE
)

Get weekly cases for Germany

GetCases <- function() {
  data <- read.csv("https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/cases_deaths/new_cases.csv")
  confirmed <- data %>% select(date, Germany)
  colnames(confirmed)[2] <- c("cases")
  confirmed$MonthYear <- GetMonthYear(confirmed$date)
  confirmed$WeekYear <- tsibble::yearweek(confirmed$date)
  return(confirmed)
}


GetCasesLong <- function() {
  data <- read.csv("https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/cases_deaths/new_cases.csv")
  confirmed <- data %>% select(date, Germany)
  colnames(confirmed)[2] <- c("cases")
  confirmed$MonthYear <- GetMonthYear(confirmed$date)
  confirmed$WeekYear <- tsibble::yearweek(confirmed$date)
  confirmed_subset_weekwise <- confirmed %>%
    group_by(WeekYear) %>%
    summarise(cases = mean(cases, na.rm = T)) %>%
    arrange(WeekYear)
  confirmed_subset_weekwise$cases <- ceiling(confirmed_subset_weekwise$cases)
  confirmed_subset_dateweekwise_long_india <- confirmed_subset_weekwise %>%
    rename(n = cases) %>%
    rename(WeekYearCollected = WeekYear)
}


confirmed <- GetCases()
confirmed_subset_dateweekwise_long <- GetCasesLong()
gisaid_germany_weekwise <- SummarizeVariantsWeekwise(gisaid_germany)

Distribution of variants

state_month_counts <- SummarizeVariantsMonthwise(gisaid_germany)
state_month_counts$State <- "Germany"
state_month_prevalence <- CountsToPrevalence(state_month_counts)
vocs <- GetVOCs()

state_month_prevalence <- CollapseLineageToVOCs(
  variant_df = state_month_prevalence,
  vocs = vocs,
  custom_voc_mapping = custom_voc_mapping, summarize = FALSE
)

p5 <- StackedBarPlotPrevalence(state_month_prevalence)
p5

Project weekly cases to variant prevalence data from GISAID

voc_to_keep <- gisaid_germany_weekwise %>%
  group_by(lineage_collapsed) %>%
  summarise(n_sum = sum(n)) %>%
  filter(n_sum > 50) %>%
  pull(lineage_collapsed) %>%
  unique()
gisaid_germany_weekwise <- gisaid_germany_weekwise %>% filter(lineage_collapsed %in% voc_to_keep)

germany_cases_pred_prob_sel_long <- FitMultinomWeekly(gisaid_germany_weekwise, confirmed_subset_dateweekwise_long)
the_anim <- PlotVariantPrevalenceAnimated(germany_cases_pred_prob_sel_long, title = "Estimated cases (weekly average) in Germany by variant", caption = "**Source: gisaid.org and ourworldindata.org/coronavirus**<br>", date_breaks = "100 days")
gganimate::anim_save(filename = here::here("docs/articles/Germany_animated.gif"), animation = the_anim)

Look at cases from 2022,

confirmed_subset_dateweekwise_long <- GetCasesLong() %>%
  filter(WeekYearCollected >= tsibble::yearweek("2021 W35"))

gisaid_germany_subset <- gisaid_germany %>% filter(MonthYearCollected > "Oct 2021")
gisaid_germany_weekwise <- SummarizeVariantsWeekwise(gisaid_germany_subset)

voc_to_keep <- gisaid_germany_weekwise %>%
  group_by(lineage_collapsed) %>%
  summarise(n_sum = sum(n)) %>%
  filter(n_sum > 50) %>%
  pull(lineage_collapsed) %>%
  unique()
gisaid_germany_weekwise <- gisaid_germany_weekwise %>% filter(lineage_collapsed %in% voc_to_keep)

germany_cases_pred_prob_sel_long <- FitMultinomWeekly(gisaid_germany_weekwise, confirmed_subset_dateweekwise_long)
the_anim <- PlotVariantPrevalenceAnimated(germany_cases_pred_prob_sel_long, title = "Estimated cases (weekly average) in Germany by variant", caption = "**Source: gisaid.org and ourworldindata.org/coronavirus**<br>", date_breaks = "100 days")
gganimate::anim_save(filename = here::here("docs/articles/Germany_animated_2021.gif"), animation = the_anim)

Look at cases from 2023

confirmed_subset_dateweekwise_long <- GetCasesLong() %>%
  filter(WeekYearCollected >= tsibble::yearweek("2022 W35"))

gisaid_germany_subset <- gisaid_germany %>% filter(MonthYearCollected > "October 2022")
gisaid_germany_weekwise <- SummarizeVariantsWeekwise(gisaid_germany_subset)

voc_to_keep <- gisaid_germany_weekwise %>%
  group_by(lineage_collapsed) %>%
  summarise(n_sum = sum(n)) %>%
  filter(n_sum > 50) %>%
  pull(lineage_collapsed) %>%
  unique()
gisaid_germany_weekwise <- gisaid_germany_weekwise %>% filter(lineage_collapsed %in% voc_to_keep)

germany_cases_pred_prob_sel_long <- FitMultinomWeekly(gisaid_germany_weekwise, confirmed_subset_dateweekwise_long)
the_anim <- PlotVariantPrevalenceAnimated(germany_cases_pred_prob_sel_long, title = "Estimated cases (weekly average) in Germany by variant", caption = "**Source: gisaid.org and ourworldindata.org/coronavirus**<br>")
gganimate::anim_save(filename = here::here("docs/articles/Germany_animated_2023.gif"), animation = the_anim)

Look at cases in the past few weeks

confirmed_subset_dateweekwise_long <- GetCasesLong() %>%
  filter(WeekYearCollected >= tsibble::yearweek("2023 W23"))

gisaid_germany_subset <- gisaid_germany %>% filter(MonthYearCollected > "June 2023")
gisaid_germany_weekwise <- SummarizeVariantsWeekwise(gisaid_germany_subset)

voc_to_keep <- gisaid_germany_weekwise %>%
  group_by(lineage_collapsed) %>%
  summarise(n_sum = sum(n)) %>%
  filter(n_sum > 50) %>%
  pull(lineage_collapsed) %>%
  unique()
gisaid_germany_weekwise <- gisaid_germany_weekwise %>% filter(lineage_collapsed %in% voc_to_keep)

germany_cases_pred_prob_sel_long <- FitMultinomWeekly(gisaid_germany_weekwise, confirmed_subset_dateweekwise_long)
the_anim <- PlotVariantPrevalenceAnimated(germany_cases_pred_prob_sel_long, title = "Estimated cases (weekly average) in Germany by variant", caption = "**Source: gisaid.org and ourworldindata.org/coronavirus**<br>")
gganimate::anim_save(filename = here::here("docs/articles/Germany_animated_2024.gif"), animation = the_anim)

saketkc/covmuller documentation built on April 19, 2024, 10:14 a.m.