DT_example: Broad sense heritability calculation.

In enhancer: Mixed-Effects Models Enhancing Functions

Broad sense heritability calculation.

Description

This dataset contains phenotpic data for 41 potato lines evaluated in 3 environments in an RCBD design. The phenotypic trait is tuber quality and we show how to obtain an estimate of DT_example for the trait.

Usage

data("DT_example")

Format

The format is: chr "DT_example"

Source

This data was generated by a potato study.

References

Covarrubias-Pazaran G (2016) Genome assisted prediction of quantitative traits using the R package sommer. PLoS ONE 11(6): doi:10.1371/journal.pone.0156744

Giovanny Covarrubias-Pazaran (2024). lme4breeding: enabling genetic evaluation in the age of genomic data. To be submitted to Bioinformatics.

Douglas Bates, Martin Maechler, Ben Bolker, Steve Walker (2015). Fitting Linear Mixed-Effects Models Using lme4. Journal of Statistical Software, 67(1), 1-48.

Examples

data(DT_example)
DT <- DT_example
A <- A_example
head(DT)



################## sommer #####################

if(requireNamespace("sommer")){
library(sommer)
## Compound simmetry (CS) model
ans1 <- mmes(Yield~Env,
             random= ~ Name + Env:Name,
             rcov= ~ units,
             data=DT)
summary(ans1)$varcomp

####===========================================####
#### Univariate heterogeneous variance models  ####
####===========================================####

## Compound simmetry (CS) + Diagonal (DIAG) model
DT=DT[with(DT, order(Env)), ]
ans2 <- mmes(Yield~Env,
             random= ~Name + vsm(dsm(Env),ism(Name)),
             rcov= ~ vsm(dsm(Env),ism(units)),
             data=DT)
summary(ans2)

####===========================================####
#### Multi-trait variance models               ####
####===========================================####

# stack traits
traits <- c("Yield","Weight")
DT[,traits] <- apply(DT[,traits],2,scale)
DTL <- reshape(DT[,c("Name","Env","Block", traits)],
               idvar = c("Name","Env","Block"),
               varying = traits,
               v.names = "value", direction = "long",
               timevar = "trait", times = traits )
DTL <- DTL[with(DTL, order(trait,Env)), ]
head(DTL)

## model
ans1 <- mmes(value~ trait,
             random= ~ vsm(usm(trait), ism(Name)),
             rcov= ~ vsm(dsm(trait), ism(units)),
             data=DTL)
summary(ans1)$varcomp
cov2cor(ans1$theta$`vsm(usm(trait), ism(Name`)

}

################## lme4breeding #####################

if(requireNamespace("lme4breeding")){
library(lme4breeding)
## Compound simmetry (CS) model
ans1 <- lmeb(Yield~Env + (1|Name) + (1|Env:Name),
             data=DT)
vc <- VarCorr(ans1); print(vc,comp=c("Variance"))

BLUP <- ranef(ans1, condVar=TRUE)
condVAR <- lapply(BLUP, function(x){attr(x, which="postVar")}) # take sqrt() for SEs

## Main (M) + Diagonal (DIAG) model
## with relationship matrix
ansCSDG <- lmeb(Yield ~ Env + (Env||Name),
                    relmat = list(Name = A ),
                    data=DT)
vc <- VarCorr(ansCSDG); print(vc,comp=c("Variance"))

## Main (M) + Diagonal (DIAG) model
## with diagonal residuals
## with relationship matrix
ansCSDG <- lmeb(Yield ~ Env + (Env||Name) + (0+Env||unitsR),
                    relmat = list(Name = A ),
                    data=DT)
vc <- VarCorr(ansCSDG); print(vc,comp=c("Variance"))
sigma(ansCSDG)^2 # error variance

}

enhancer documentation built on April 12, 2026, 9:07 a.m.