COVID GLUE datasets
cov_glue_lineage_data()a data.frame
{
\@article{VANDORP2020104351,
title = "Emergence of genomic diversity and recurrent mutations in SARS-CoV-2",
journal = "Infection, Genetics and Evolution",
pages = "104351",
year = "2020",
issn = "1567-1348",
doi = "https://doi.org/10.1016/j.meegid.2020.104351",
url = "http://www.sciencedirect.com/science/article/pii/S1567134820301829",
author = "Lucy [van Dorp] and Mislav Acman and Damien Richard and Liam P. Shaw and Charlotte E. Ford and Louise Ormond and Christopher J. Owen and Juanita Pang and Cedric C.S. Tan and Florencia A.T. Boshier and Arturo Torres Ortiz and François Balloux"
}
}
cov_glue_newick_data(), cov_glue_snp_lineage()
Other lineage:
cov_glue_newick_data(),
cov_glue_snp_lineage()
Other data-import:
acaps_government_measures_data(),
acaps_secondary_impact_data(),
apple_mobility_data(),
beoutbreakprepared_data(),
cci_us_vaccine_data(),
cdc_aggregated_projections(),
cdc_excess_deaths(),
cdc_social_vulnerability_index(),
coronadatascraper_data(),
coronanet_government_response_data(),
cov_glue_newick_data(),
cov_glue_snp_lineage(),
covidtracker_data(),
descartes_mobility_data(),
ecdc_data(),
econ_tracker_consumer_spending,
econ_tracker_employment,
econ_tracker_unemp_data,
economist_excess_deaths(),
financial_times_excess_deaths(),
google_mobility_data(),
government_policy_timeline(),
jhu_data(),
jhu_us_data(),
kff_icu_beds(),
nytimes_county_data(),
oecd_unemployment_data(),
owid_data(),
param_estimates_published(),
test_and_trace_data(),
us_county_geo_details(),
us_county_health_rankings(),
us_healthcare_capacity(),
us_hospital_details(),
us_state_distancing_policy(),
usa_facts_data(),
who_cases()
Other individual-cases:
beoutbreakprepared_data(),
cov_glue_newick_data()
res = cov_glue_lineage_data()
head(res)
#> # A tibble: 6 × 10
#> `GISAID ID` name country travel_history date epiweek lineage
#> <chr> <chr> <chr> <chr> <date> <dbl> <chr>
#> 1 EPI_ISL_420793 USA/NY_2929/… USA NA 2020-03-02 10 B.1
#> 2 EPI_ISL_417142 USA/WA-S89/2… USA NA 2020-02-29 9 A.1
#> 3 EPI_ISL_420792 USA/NH_0008/… USA NA 2020-03-02 10 B.1
#> 4 EPI_ISL_420795 USA/RI_0556/… USA NA 2020-03-01 10 B.1.5
#> 5 EPI_ISL_417140 USA/WA-S87/2… USA NA 2020-03-01 10 A.1
#> 6 EPI_ISL_420794 USA/OR_5430/… USA NA 2020-03-01 10 B.2
#> # … with 3 more variables: representative <dbl>, iso3c <chr>, iso2c <chr>
colnames(res)
#> [1] "GISAID ID" "name" "country" "travel_history"
#> [5] "date" "epiweek" "lineage" "representative"
#> [9] "iso3c" "iso2c"
dplyr::glimpse(res)
#> Rows: 27,763
#> Columns: 10
#> $ `GISAID ID` <chr> "EPI_ISL_420793", "EPI_ISL_417142", "EPI_ISL_420792", "…
#> $ name <chr> "USA/NY_2929/2020", "USA/WA-S89/2020", "USA/NH_0008/202…
#> $ country <chr> "USA", "USA", "USA", "USA", "USA", "USA", "USA", "USA",…
#> $ travel_history <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
#> $ date <date> 2020-03-02, 2020-02-29, 2020-03-02, 2020-03-01, 2020-0…
#> $ epiweek <dbl> 10, 9, 10, 10, 10, 10, 9, 9, 10, 9, 9, 9, 10, 10, 10, 1…
#> $ lineage <chr> "B.1", "A.1", "B.1", "B.1.5", "A.1", "B.2", "A.1", "B.1…
#> $ representative <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1…
#> $ iso3c <chr> "USA", "USA", "USA", "USA", "USA", "USA", "USA", "USA",…
#> $ iso2c <chr> "US", "US", "US", "US", "US", "US", "US", "US", "US", "…