SMUT (version 1.1)

SMUT: Multi-SNP Mediation Intersection-Union Test

Description

Testing the mediation effect of multiple SNPs on an outcome through a mediator.

Usage

SMUT(G, mediator, outcome, 
outcome_type="continuous", method="score",approxi=TRUE, debug=FALSE)

Arguments

G

n by p matrix (n rows and p columns). Each row is one individual; each column is one SNP.

mediator

a vector length of n. It is the mediator variable.

outcome

a vector length of n. It is the outcome variable.

outcome_type

Type of the outcome variable. For now, this package only deals with continuous outcome. Default is "continuous".

method

The method of testing coefficient of mediator in the outcome model. The score test is used. Default is "score".

approxi

a boolean value. This is an indicator whether the approximation of the score statistic is applied to save computing time. Default is TRUE.

debug

a boolean value. If TRUE a lot of computing details is printed; otherwise the function is completely silent. Default is FALSE.

Value

p_value_IUT

The p value for testing the mediation effect (theta*beta) based on intersection-union test.

p_value_theta

The p value for testing theta in the outcome model. The outcome model is the following. outcome ~ intercept + G*gamma + mediator*theta + error.

p_value_beta

The p value for testing beta in the mediator model. The mediator model is the following. mediator ~ intercept + G*beta + error

References

Zhong, W., Spracklen, C. N., Mohlke, K. L., Zheng, X., Fine, J., & Li, Y. (2019). Multi-SNP mediation intersection-union test. Bioinformatics.

Examples

# NOT RUN {
library(SMUT)
# load the Genotype data included in this R package
data("Genotype_data")

# generate one mediator and one outcome

# first example, the mediation effect is significant
set.seed(1)
beta=rnorm(ncol(Genotype_data),1,2)
e1 = rnorm(nrow(Genotype_data), 0, 1)
mediator = 1 + eigenMapMatMult(Genotype_data,beta) + e1

theta=0.8
gamma=rnorm(ncol(Genotype_data),0.5,2)
e2 = rnorm(nrow(Genotype_data), 0, 1)
outcome = 2 + eigenMapMatMult(Genotype_data,gamma) + theta*mediator + e2

p_value=SMUT(G=Genotype_data,mediator=mediator,outcome=outcome)
print(p_value)

# p_value_IUT is the p value for the mediation effect.
# we have significant(at alpha level 0.05) mediation effects (p_value_IUT = 0.001655787).

# second example, the mediation effect is non-significant
set.seed(1)
beta=rnorm(ncol(Genotype_data),1,2)
e1 = rnorm(nrow(Genotype_data), 0, 1)
mediator = 1 + eigenMapMatMult(Genotype_data,beta) + e1

theta=0
gamma=rnorm(ncol(Genotype_data),0.5,2)
e2 = rnorm(nrow(Genotype_data), 0, 1)
outcome = 2 + eigenMapMatMult(Genotype_data,gamma) + theta*mediator + e2

p_value=SMUT(G=Genotype_data,mediator=mediator,outcome=outcome)
print(p_value)

# p_value_IUT is the p value for the mediation effect.
# we have non-significant(at alpha level 0.05) mediation effects (p_value_IUT = 0.3281677).

# third example, the mediation effect is non-significant
set.seed(1)
beta=rep(0,ncol(Genotype_data))
e1 = rnorm(nrow(Genotype_data), 0, 1)
mediator = 1 + eigenMapMatMult(Genotype_data,beta) + e1

theta=0.8
gamma=rnorm(ncol(Genotype_data),0.5,2)
e2 = rnorm(nrow(Genotype_data), 0, 1)
outcome = 2 + eigenMapMatMult(Genotype_data,gamma) + theta*mediator + e2

p_value=SMUT(G=Genotype_data,mediator=mediator,outcome=outcome)
print(p_value)

# p_value_IUT is the p value for the mediation effect.
# we have non-significant(at alpha level 0.05) mediation effects (p_value_IUT = 0.5596977).

# Thanks for using our R package SMUT 
# }