Limits...
Validation and selection of ODE based systems biology models: how to arrive at more reliable decisions.

Hasdemir D, Hoefsloot HC, Smilde AK - BMC Syst Biol (2015)

Bottom Line: However, drawbacks associated with this approach are usually under-estimated.The hold-out validation strategy leads to biased conclusions, since it can lead to different validation and selection decisions when different partitioning schemes are used.Therefore, it proves to be a promising alternative to the standard hold-out validation strategy.

View Article: PubMed Central - PubMed

Affiliation: Biosystems Data Analysis Group, Swammerdam Institute for Life Sciences, University of Amsterdam, Amsterdam, The Netherlands. D.Hasdemir@uva.nl.

ABSTRACT

Background: Most ordinary differential equation (ODE) based modeling studies in systems biology involve a hold-out validation step for model validation. In this framework a pre-determined part of the data is used as validation data and, therefore it is not used for estimating the parameters of the model. The model is assumed to be validated if the model predictions on the validation dataset show good agreement with the data. Model selection between alternative model structures can also be performed in the same setting, based on the predictive power of the model structures on the validation dataset. However, drawbacks associated with this approach are usually under-estimated.

Results: We have carried out simulations by using a recently published High Osmolarity Glycerol (HOG) pathway from S.cerevisiae to demonstrate these drawbacks. We have shown that it is very important how the data is partitioned and which part of the data is used for validation purposes. The hold-out validation strategy leads to biased conclusions, since it can lead to different validation and selection decisions when different partitioning schemes are used. Furthermore, finding sensible partitioning schemes that would lead to reliable decisions are heavily dependent on the biology and unknown model parameters which turns the problem into a paradox. This brings the need for alternative validation approaches that offer flexible partitioning of the data. For this purpose, we have introduced a stratified random cross-validation (SRCV) approach that successfully overcomes these limitations.

Conclusions: SRCV leads to more stable decisions for both validation and selection which are not biased by underlying biological phenomena. Furthermore, it is less dependent on the specific noise realization in the data. Therefore, it proves to be a promising alternative to the standard hold-out validation strategy.

No MeSH data available.


Related in: MedlinePlus

Number of wrong decisions in scenario 1. Bars show the number of realizations in which the simplified model gave lower residuals than the true model structure and therefore, was wrongly selected over the true model structure. Blue, green and black bars refer to Sln1, Sho1, and WT schemes. Each row in the figure corresponds to a single scheme. The labels on the x-axis show the specific dose and the cell type of the data on which the validation was performed. a Number of wrong decisions using Sho1 validation subsets in the Sln1 scheme. b Number of wrong decisions using WT validation subsets in the Sln1 scheme. c Number of wrong decisions using Sln1 validation subsets in the Sho1 scheme. d Number of wrong decisions using WT validation subsets in the Sho1 scheme. e Number of wrong decisions using Sln1 validation subsets in the WT scheme. f Number of wrong decisions using Sho1 validation subsets in the WT scheme
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4493957&req=5

Fig11: Number of wrong decisions in scenario 1. Bars show the number of realizations in which the simplified model gave lower residuals than the true model structure and therefore, was wrongly selected over the true model structure. Blue, green and black bars refer to Sln1, Sho1, and WT schemes. Each row in the figure corresponds to a single scheme. The labels on the x-axis show the specific dose and the cell type of the data on which the validation was performed. a Number of wrong decisions using Sho1 validation subsets in the Sln1 scheme. b Number of wrong decisions using WT validation subsets in the Sln1 scheme. c Number of wrong decisions using Sln1 validation subsets in the Sho1 scheme. d Number of wrong decisions using WT validation subsets in the Sho1 scheme. e Number of wrong decisions using Sln1 validation subsets in the WT scheme. f Number of wrong decisions using Sho1 validation subsets in the WT scheme

Mentions: The asymmetry in the contribution of the Sln1 and the Sho1 branches to the phosphorylation of the Hog1 protein also has consequences for model selection. Figure 11 shows the number of wrong decisions given on each validation subset in each of these three partitioning schemes. We see that in a high number of realizations, the simplified model structure was selected over the true model structure when the Sho1 data was used for validation (Fig. 11a and f). On the other hand, using only the Sho1 data for training also resulted in an increased number of wrong decisions on the Sln1 data compared to the WT scheme (minimum number of wrong decisions 12 vs. 1 in Fig. 11c and e).Fig. 11


Validation and selection of ODE based systems biology models: how to arrive at more reliable decisions.

Hasdemir D, Hoefsloot HC, Smilde AK - BMC Syst Biol (2015)

Number of wrong decisions in scenario 1. Bars show the number of realizations in which the simplified model gave lower residuals than the true model structure and therefore, was wrongly selected over the true model structure. Blue, green and black bars refer to Sln1, Sho1, and WT schemes. Each row in the figure corresponds to a single scheme. The labels on the x-axis show the specific dose and the cell type of the data on which the validation was performed. a Number of wrong decisions using Sho1 validation subsets in the Sln1 scheme. b Number of wrong decisions using WT validation subsets in the Sln1 scheme. c Number of wrong decisions using Sln1 validation subsets in the Sho1 scheme. d Number of wrong decisions using WT validation subsets in the Sho1 scheme. e Number of wrong decisions using Sln1 validation subsets in the WT scheme. f Number of wrong decisions using Sho1 validation subsets in the WT scheme
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4493957&req=5

Fig11: Number of wrong decisions in scenario 1. Bars show the number of realizations in which the simplified model gave lower residuals than the true model structure and therefore, was wrongly selected over the true model structure. Blue, green and black bars refer to Sln1, Sho1, and WT schemes. Each row in the figure corresponds to a single scheme. The labels on the x-axis show the specific dose and the cell type of the data on which the validation was performed. a Number of wrong decisions using Sho1 validation subsets in the Sln1 scheme. b Number of wrong decisions using WT validation subsets in the Sln1 scheme. c Number of wrong decisions using Sln1 validation subsets in the Sho1 scheme. d Number of wrong decisions using WT validation subsets in the Sho1 scheme. e Number of wrong decisions using Sln1 validation subsets in the WT scheme. f Number of wrong decisions using Sho1 validation subsets in the WT scheme
Mentions: The asymmetry in the contribution of the Sln1 and the Sho1 branches to the phosphorylation of the Hog1 protein also has consequences for model selection. Figure 11 shows the number of wrong decisions given on each validation subset in each of these three partitioning schemes. We see that in a high number of realizations, the simplified model structure was selected over the true model structure when the Sho1 data was used for validation (Fig. 11a and f). On the other hand, using only the Sho1 data for training also resulted in an increased number of wrong decisions on the Sln1 data compared to the WT scheme (minimum number of wrong decisions 12 vs. 1 in Fig. 11c and e).Fig. 11

Bottom Line: However, drawbacks associated with this approach are usually under-estimated.The hold-out validation strategy leads to biased conclusions, since it can lead to different validation and selection decisions when different partitioning schemes are used.Therefore, it proves to be a promising alternative to the standard hold-out validation strategy.

View Article: PubMed Central - PubMed

Affiliation: Biosystems Data Analysis Group, Swammerdam Institute for Life Sciences, University of Amsterdam, Amsterdam, The Netherlands. D.Hasdemir@uva.nl.

ABSTRACT

Background: Most ordinary differential equation (ODE) based modeling studies in systems biology involve a hold-out validation step for model validation. In this framework a pre-determined part of the data is used as validation data and, therefore it is not used for estimating the parameters of the model. The model is assumed to be validated if the model predictions on the validation dataset show good agreement with the data. Model selection between alternative model structures can also be performed in the same setting, based on the predictive power of the model structures on the validation dataset. However, drawbacks associated with this approach are usually under-estimated.

Results: We have carried out simulations by using a recently published High Osmolarity Glycerol (HOG) pathway from S.cerevisiae to demonstrate these drawbacks. We have shown that it is very important how the data is partitioned and which part of the data is used for validation purposes. The hold-out validation strategy leads to biased conclusions, since it can lead to different validation and selection decisions when different partitioning schemes are used. Furthermore, finding sensible partitioning schemes that would lead to reliable decisions are heavily dependent on the biology and unknown model parameters which turns the problem into a paradox. This brings the need for alternative validation approaches that offer flexible partitioning of the data. For this purpose, we have introduced a stratified random cross-validation (SRCV) approach that successfully overcomes these limitations.

Conclusions: SRCV leads to more stable decisions for both validation and selection which are not biased by underlying biological phenomena. Furthermore, it is less dependent on the specific noise realization in the data. Therefore, it proves to be a promising alternative to the standard hold-out validation strategy.

No MeSH data available.


Related in: MedlinePlus