Repository files navigation

install.packages("FielDHub")

remotes::install_github("DidierMurilloF/FielDHub")

A shiny design of experiments (DOE) app that aids in the creation oftraditional, un-replicated, augmented and partially-replicated designsapplied to agriculture, plant breeding, forestry, animal and biologicalsciences.

For more details and examples of all functions present in the FielDHubpackage. Please, go tohttps://didiermurillof.github.io/FielDHub/articles/diagonal_arrangement.html.

This is a basic example which shows you how to launch the app:

library(FielDHub)run_app()

A project needs to test 280 genotypes in a field containing 16 rows and20 columns of plots. In this example, these 280 genotypes are dividedamong three different experiments. In addition, four checks are includedin a systematic diagonal arrangement across experiments to fill 40 plotsrepresenting 12.5% of the total number of experimental plots. An optionto include filler plots is also available for fields where the number ofexperimental plots does not equal the number of available field plots.

The figure above shows a map of an experiment randomized along withmultiple experiments (three) and checks on diagonals. Distinctivelycolored check plots are replicated throughout the field in a systematicdiagonal arrangement.

The figure above shows the layout for the three experiments in thefield.

To illustrate using FielDHub to build experimental designs through Rcode, the design produced in the R Shiny interface described above canalso be created using the functiondiagonal_arrangement() in the Rscript below. Note, that to obtain identical results, users must includethe same random seed in the script as was used in the Shiny app. In thiscase, the random seed is 1249.

diagonal<- diagonal_arrangement(nrows=16,ncols=20,lines=280,checks=4,plotNumber=101,splitBy="row",seed=1249,kindExpt="DBUDC",blocks= c(100,100,80),exptName= c("Expt1","Expt2","Expt3"))

Users can print the returned values fromdiagonal_arrangement() asfollow,

print(diagonal)Un-replicatedDiagonalArrangementDesignInformationonthedesignparameters:Listof11$rows:num16$columns:num20$treatments:num [1:3]10010080$checks:int4$entry_checks:int [1:4]1234$rep_checks:num [1:4]119911$locations:num1$planter:chr"serpentine"$percent_checks:chr"12.5%"$fillers:num0$seed:num124910Firstobservationsofthedataframewiththediagonal_arrangementfieldbook:IDEXPTLOCATIONYEARPLOTROWCOLUMNCHECKSENTRYTREATMENT11Expt11202310111051Gen-5122Expt11202310212067Gen-6733Expt11202310313050Gen-5044Expt11202310414029Gen-2955Expt11202310515039Gen-3966Expt11202310616092Gen-9277Expt1120231071711Check-188Expt11202310818058Gen-5899Expt11202310919023Gen-231010Expt112023110110054Gen-54

First 12 rows of the field book,

head(diagonal$fieldBook,12)IDEXPTLOCATIONYEARPLOTROWCOLUMNCHECKSENTRYTREATMENT11Expt11202310111051Gen-5122Expt11202310212067Gen-6733Expt11202310313050Gen-5044Expt11202310414029Gen-2955Expt11202310515039Gen-3966Expt11202310616092Gen-9277Expt1120231071711Check-188Expt11202310818058Gen-5899Expt11202310919023Gen-231010Expt112023110110054Gen-541111Expt112023111111055Gen-551212Expt11202311211209Gen-9

Users can plot the layout design fromdiagonal_arrangement() using thefunctionplot() as follows,

plot(diagonal)

In the figure, salmon, green, and blue shade the blocks of unreplicatedexperiments, while distinctively colored check plots are replicatedthroughout the field in a systematic diagonal arrangement.

The main difference between using the FielDHub Shiny app and using thestandalone functiondiagonal_arrangement() is that the standalonefunction will allocate filler only if it is necessary, while in ShinyApp, users can customize the number of fillers if it is needed. In caseswhere users include fillers, either between or after experiments, theShiny app is preferable for filling and visualizing all field plots.

To see more examples, go tohttps://didiermurillof.github.io/FielDHub/articles/diagonal_arrangement.html

Partially replicated designs are commonly employed in early generationfield trials. This type of design is characterized by replication of aportion of the entries, with the remaining entries only appearing oncein the experiment. As an example, considered a field trial with 288plots containing 75 entries appearing two times each, and 138 entriesonly appearing once. This field trials is arranged in a field of 16 rowsby 18 columns.

In the figure above, green plots contain replicated entries, and theother plots contain entries that only appear once.

Instead of using the Shiny FielDHub app, users can use the standaloneFielDHub functionpartially_replicated(). The partially replicatedlayout described above can be produced through scripting as follows. Asnoted in the previous example, to obtain identical results between thescript and the Shiny app, users need to use the same random seed, which,in this case, is 77.

pREP<- partially_replicated(nrows=16,ncols=18,repGens= c(138,75),repUnits= c(1,2),planter="serpentine",plotNumber=1,exptName="ExptA",locationNames="FARGO",seed=77)

Users can print returned values frompartially_replicated() asfollows,

print(pREP)PartiallyReplicatedDesignInformationonthedesignparameters:Listof7$rows:num16$columns:num18$treatments_with_reps:int75$treatments_with_no_reps:int138$locations:num1$planter:chr"serpentine"$seed:num7710Firstobservationsofthedataframewiththepartially_replicatedfieldbook:IDEXPTLOCATIONYEARPLOTROWCOLUMNCHECKSENTRYTREATMENT11ExptAFARGO2023111080G8022ExptAFARGO20232124949G4933ExptAFARGO20233131515G1544ExptAFARGO20234144444G4455ExptAFARGO20235150185G18566ExptAFARGO202361699G977ExptAFARGO20237170133G13388ExptAFARGO20238185858G5899ExptAFARGO202391944G41010ExptAFARGO2023101100113G113

First 12 rows of the fieldbook,

head(pREP$fieldBook,12)IDEXPTLOCATIONYEARPLOTROWCOLUMNCHECKSENTRYTREATMENT11ExptAFARGO2023111080G8022ExptAFARGO20232124949G4933ExptAFARGO20233131515G1544ExptAFARGO20234144444G4455ExptAFARGO20235150185G18566ExptAFARGO202361699G977ExptAFARGO20237170133G13388ExptAFARGO20238185858G5899ExptAFARGO202391944G41010ExptAFARGO2023101100113G1131111ExptAFARGO2023111110190G1901212ExptAFARGO2023121120148G148

Users can plot the layout design frompartially_replicated() using thefunctionplot() as follows,

plot(pREP)

To see more examples, please go tohttps://didiermurillof.github.io/FielDHub/articles/partially_replicated.html