# Simulated phenotypic records for a set of 100 environments and 200 entries. This is a simulated dataset that aims to show how to pick the most representative locations and how to optimize sparse testing allocation. data ```r data("DT_envs") ``` ## Format The format is: chr "DT_envs" ## Source This data was simulated for experimental design applications. ## References Giovanny Covarrubias-Pazaran (2024). evola: a simple evolutionary algorithm for complex problems. To be submitted to Bioinformatics. Gaynor, R. Chris, Gregor Gorjanc, and John M. Hickey. 2021. AlphaSimR: an R package for breeding program simulations. G3 Gene|Genomes|Genetics 11(2):jkaa017. https://doi.org/10.1093/g3journal/jkaa017. Chen GK, Marjoram P, Wall JD (2009). Fast and Flexible Simulation of DNA Sequence Data. Genome Research, 19, 136-142. http://genome.cshlp.org/content/19/1/136. ## Examples ```r data(DT_envs) # scale passport data for environments S=scale(W) # build a relationship matrix between environments G=tcrossprod(S)/ncol(S) G[1:4,1:4] # build the dataset for the genetic algorithm DT <- data.frame(cov=rnorm(nrow(G)), occ=1, id=rownames(G)) nLocs=10 # desired number of representative locations if(requireNamespace("evola")){ library(evola) res<-evolafit(formula=cbind(cov, occ)~id, dt= DT, # constraints: if sum is greater than this ignore constraintsUB = c(Inf, Inf), # constraints: if sum is smaller than this ignore constraintsLB= c(-Inf, nLocs), # weight the traits for the selection b = c(1,0), # population parameters nCrosses = 100, nProgeny = 20, recombGens=1, nChr=1, mutRateAllele=0, # coancestry parameters D=G, lambda= 0 , nQtlStart = nLocs, # selection parameters fitnessf = inbFun, selectTop = FALSE, # fixNumQtlPerInd = TRUE, # propSelBetween = 0.5, propSelWithin =0.5, nGenerations = 50, verbose = TRUE) Q <- pullQtlGeno(res$pop, simParam = res$simParam, trait=1); Q <- Q/2 best <- bestSol(res$pop, selectTop = FALSE)[,"fitness"] solution <- Q[best,] sum(solution) # total # of inds selected names(solution[which(solution>0)]) evolmonitor(res) pareto(res) svdW <- svd(G, nu = 2, nv = 2) PCW <- G %*% svdW$v rownames(PCW) <- rownames(G) plot(PCW[,1], PCW[,2], col = (solution*2)+2, pch=(solution*14)+4, xlab = "pc1", ylab = "pc2") labs <- rownames(PCW) labs[which(solution==0)]="" text(x=PCW[,1], y=PCW[,2], labels=labs, cex=0.5, pos=3) } ```

DT_envs dataset