Introduction

The data plotted below is an analysis of the proportion of participants in genome-wide association studies (GWAS) in 2009 and in 2016. The data from the 2009 analysis was collected by Need and Goldstein by analyzing the sample descriptions in the GWAS catalog at the time. The process was repeated in 2016 by Popejoy and Fullerton to update the 2009 analysis (which showed that 96% of the population in GWAS was of european ancestry) using the same method of data collection. The main goal was to measure how far GWAS’s are advanced in including participants of other ancestries to help produce genomic medicine that is of benefit to everyone and not just the ‘privileged few’.

Create data

study_labels <- c('European\n','\nAsian', '\nOther')
data_2009 <- c(96,3,1)
data_2016 <- c(81,14,5)

Pie graphs

# set up par()
par(mfrow = c(1,2), mar = c(2,3,1,5))

#pie graphs 1
# add main, init.angle, radius, and col
pie(x = data_2009, 
    labels = study_labels,
    main = 2009, 
    init.angle = -82,
    radius = 1,
    col = c(1,2,3))

# pie graph 2
# add main, init.angle, radius, and col
pie(x = data_2016, 
    labels = study_labels,
    main = 2016, 
    init.angle = -82,
    radius = 1,
    col = c(1,2,3))

Bar graphs

# data
dat2016 <- c(14, 3,1,0.54,0.28,0.08,0.05)
dat2016_rev <- rev(dat2016)
barplotdata2016 <- matrix(c(dat2016_rev))

# labels
labels_x <- rev(c("Asian","African","Mixed", "Hispanic &\nLatin American",
                        "Pacific Islander","Arab & Middle East","Native peoples"))

par(mfrow = c(1,1))

barplot(barplotdata2016,
        width = 0.01, 
        xlim = c(0,0.1),
         axes = F,
        col = c(1,2,3,4,5,6,7),
        legend.text = labels_x)