VSGFS {DoE.base}

VSGFS: an experiment using an optimized orthogonal array in 72 runs

Description

VSGFS: an experiment using an optimized orthogonal array in 72 runs

Usage

VSGFS

Format

VSGFS is a data frame of class design with seven experimental factors and three response variables. The data have been published in Vasilev et al. (2014).

The experimental factors, all stored as R factors, with their levels are

[,1]	Light	Lght-, Lght+
[,2]	ShakFreq	SF-, SF+
[,3]	InocSize	IS-, IS+
[,4]	FilledVol	FV-, FV0, FV+
[,5]	CM	CM-, CM+
[,6]	Carbo	Suc, Gluc, Mannit (Sucrose, Glucose, Mannitol)
[,7]	Cyclodextrin	CD1, CD2, CD3, CD4 (beta, methyl-beta, triacetyl-beta, none)

The response variables, all stored as numerical variables, are

[,8]	Biomass	fresh weight in g
[,9]	Content	geraniol content in \mug per g fresh weight
[,10]	Yield	geraniol yield in \mug per flask

Details

The data set comes from an experiment that was created with function oa.design using the array L72.2.43.3.8.4.1.6.1. Column selection within the array was done with option columns="min34" that picks the first set of columns obtained by function oa.min34. (Optimization takes quite a while, so that the design was reconstructed later by explicitly requesting the optimum set of columns.)

Design creation and the experiment itself were conducted at the Fraunhofer IME in Aachen by Nikolay Vasilev and colleagues. More detail on the experiment and the variables can be found in Vasilev et al. (2014).

The design was created under an R version before 3.6.0. For reproducing its creation under R 3.6.0 and later, it is therefore necessary to switch to the previous version of random number generation (using the RNGkind function, see examples section). Note that the previous discrete random uniform random number generator was not perfectly uniform, especially for very large samples; for randomizing experiments of typical sizes (like this one), this problem can be neglected.

Author(s)

Ulrike Groemping

References

Vasilev, N., Schmidt, C., Groemping, U., Fischer, R. and Schillberg, S. (2014). Assessment of Cultivation Factors that Affect Biomass and Geraniol Production in Transgenic Tobacco Cell Suspension Cultures. PLoS ONE 9(8): e104620. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0104620.

See Also

See also oacat, show.oas, oa.min34, oa.design

Examples

## code used for creating the data frame
## option levordold is needed, because the level ordering 
## changed (improved) with version 0.27 
## and the design was originally created with an earlier version
## Not run: 
  if (getRversion()>='3.6.0') RNGkind(sample.kind="Rounding")
  VSGFS <- oa.design(ID=L72.2.43.3.8.4.1.6.1, 
   nlevels=c(2,2,2,3,2,3,4), 
   columns=c(4,22,37,46,41,48,52), 
   factor.names=list(Light=c("Lght-","Lght+"),
      ShakFreq=c("SF-","SF+"),
      InocSize=c("IS-","IS+"),
      FilledVol=c("FV-","FV0", "FV+"), 
      CM=c("CM-","CM+"),
      Sugar=c("Suc", "Gluc", "Mannit"),
      CDs=c("CD1","CD2","CD3","CD4")),
   seed = 9, randomize=TRUE, levordold=TRUE)
  if (getRversion()>='3.6.0') RNGkind(sample.kind="default")

response <- as.data.frame(scan(what=list(Biomass=0, Content=0, Yield=0), sep=" ")) 
5.80 24.13 139.98
4.97 16.96 84.28
1.28 21.08 26.99
6.83 17.71 120.95
0.86 21.28 18.30
4.09 18.86 77.14
2.39 17.08 40.81
4.05 17.84 72.23
5.84 17.74 103.61
3.38 18.08 61.11
0.40 24.82 9.93
3.86 18.10 69.88
4.58 21.29 97.49
6.29 17.32 108.91
4.85 15.50 75.17
1.25 23.14 28.92
2.09 18.43 38.51
4.26 17.75 75.62
4.78 18.53 88.57
6.63 17.82 118.14
0.77 18.79 14.47
4.89 18.23 89.15
4.53 17.69 80.11
4.27 18.05 77.07
3.90 15.84 61.77
4.15 18.73 77.74
3.95 17.12 67.63
6.92 16.86 116.68
5.00 16.96 84.80
0.37 21.79 8.06
2.36 19.57 46.18
5.11 18.13 92.66
4.69 17.38 81.50
1.20 19.57 23.49
1.76 17.98 31.65
6.21 17.03 105.76
5.63 15.71 88.43
3.98 18.42 73.32
2.31 19.38 44.76
1.86 18.41 34.25
4.22 17.93 75.68
2.77 17.17 47.55
0.40 23.10 9.24
1.42 18.89 26.83
1.54 17.44 26.86
5.03 17.40 87.53
8.70 14.41 125.38
3.21 19.29 61.92
5.36 18.46 98.93
3.87 16.89 65.35
7.70 18.60 143.20
1.71 17.67 30.22
4.38 16.79 73.54
2.24 19.61 43.92
3.79 19.35 73.35
3.09 18.67 57.70
1.57 17.64 27.70
5.43 18.45 100.19
3.86 17.09 65.96
7.44 19.07 141.85
5.87 17.13 100.53
2.65 17.51 46.39
6.14 15.85 97.34
6.32 14.80 93.56
5.19 16.53 85.78
5.09 17.30 88.04
4.40 17.52 77.08
1.68 21.89 36.78
0.93 23.06 21.45
1.79 22.88 40.95
2.64 18.38 48.52
7.78 16.22 126.19


VSGFS <- add.response(VSGFS, response)
VSGFS$Sugar <- relevel(VSGFS$Sugar, "Suc")
VSGFS$FilledVol <- relevel(VSGFS$FilledVol, "FV0")
VSGFS$FilledVol <- relevel(VSGFS$FilledVol, "FV-")

## End(Not run)