In ZhaotongL/mixIE: Mendelian randomization method with a mixture of regressions

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

mixIE

R package for Mendelian randomization with mixIE methods proposed in this paper: Lin, Z., Deng, Y., & Pan, W. (2021). Combining the strengths of inverse-variance weighting and Egger regression in Mendelian randomization using a mixture of regressions model. PLoS genetics, 17(11), e1009922..

Installation

Install the development version from GitHub with:

# install.packages("devtools")
devtools::install_github("ZhaotongL/mixIE")

Example

Here is an example which shows how to apply mixIE methods to make inference about the causal effect from Fast Glucose (FG) to Type-2 Diabetes (T2D)

library(mixIE)
library(ggpubr)
head(FG_T2D)

Now we perform mixIE-MA with the outcome sample size 69033 and reorientating IVs with all positive associations with the exposure.

set.seed(1)
mixIE_MA_result = mixIE_MA(b_exp=FG_T2D$beta_hat_1,b_out=FG_T2D$beta_hat_2,
                           se_exp=FG_T2D$seb1,se_out = FG_T2D$seb2,
                           n=69033,flip=1)
mixIE_MA_result

We can also obtain the results for mixIE-MA when directly implementing mixIE-MA-DP:

set.seed(1)
mixIE_MA_DP_result = mixIE_MA_DP(b_exp=FG_T2D$beta_hat_1,b_out=FG_T2D$beta_hat_2,
                           se_exp=FG_T2D$seb1,se_out = FG_T2D$seb2,
                           n=69033,flip=1)
mixIE_MA_DP_result

We can obtain the diagnostic plots of mixIE-MA-DP by setting diagnostic_plot=TRUE:

set.seed(1)
mixIE_MA_DP_result = mixIE_MA_DP(b_exp=FG_T2D$beta_hat_1,b_out=FG_T2D$beta_hat_2,
                           se_exp=FG_T2D$seb1,se_out = FG_T2D$seb2,
                           n=69033,flip=1,
                           diagnostic_plot = TRUE, point_size = 1.3) 
g1=ggarrange(mixIE_MA_DP_result$scatter_og.plot, mixIE_MA_DP_result$scatter_dp.plot,labels =c("A:mixIE-MA", "B:mixIE-MA-DP"),
            common.legend=TRUE,legend = 'bottom',font.label = list(size = 8))
g2=ggarrange(mixIE_MA_DP_result$iv_barplot, mixIE_MA_DP_result$est_hist,labels =c("C", "D"),
               legend = 'bottom',font.label = list(size = 8))
ggarrange(g1,g2,nrow = 2)