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

Scenario 2 partitioning schemes. Light gray colored boxes show parts of the data which we used as the training set (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). Different background colors represent different partitioning schemes and are consistent with the colors used in the graphs in the Results and discussion section. Each partitioning scheme offered the use of three subsets of the Hog1PP data as the training set. These are the lowest dose subset of each cell type in the lowest dose scheme and the highest of each in the highest dose scheme. The remaining fifteen subsets of the Hog1PP data could be used for validation, separately. These are the lowest dose subset of each cell type in (a) the lowest dose scheme and the highest of each in (b) the highest dose scheme
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Fig4: Scenario 2 partitioning schemes. Light gray colored boxes show parts of the data which we used as the training set (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). Different background colors represent different partitioning schemes and are consistent with the colors used in the graphs in the Results and discussion section. Each partitioning scheme offered the use of three subsets of the Hog1PP data as the training set. These are the lowest dose subset of each cell type in the lowest dose scheme and the highest of each in the highest dose scheme. The remaining fifteen subsets of the Hog1PP data could be used for validation, separately. These are the lowest dose subset of each cell type in (a) the lowest dose scheme and the highest of each in (b) the highest dose scheme

Mentions: Our second scenario mimics the dose-response strategy. In this scenario, the training set is composed of one dose from each cell type. In the lowest dose scheme, only the data following a 0.07 M. NaCl shock are used for training (Fig. 4). In the highest dose scheme, only the data following a 0.8 M. NaCl shock are used for training. The remaining five doses from each cell type can be used as validation data. Similar to the first scenario, the outcomes of model validation and selection are determined based on each of these fifteen subsets of validation data, separately.Fig. 4


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)

Scenario 2 partitioning schemes. Light gray colored boxes show parts of the data which we used as the training set (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). Different background colors represent different partitioning schemes and are consistent with the colors used in the graphs in the Results and discussion section. Each partitioning scheme offered the use of three subsets of the Hog1PP data as the training set. These are the lowest dose subset of each cell type in the lowest dose scheme and the highest of each in the highest dose scheme. The remaining fifteen subsets of the Hog1PP data could be used for validation, separately. These are the lowest dose subset of each cell type in (a) the lowest dose scheme and the highest of each in (b) the highest dose scheme
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Fig4: Scenario 2 partitioning schemes. Light gray colored boxes show parts of the data which we used as the training set (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). Different background colors represent different partitioning schemes and are consistent with the colors used in the graphs in the Results and discussion section. Each partitioning scheme offered the use of three subsets of the Hog1PP data as the training set. These are the lowest dose subset of each cell type in the lowest dose scheme and the highest of each in the highest dose scheme. The remaining fifteen subsets of the Hog1PP data could be used for validation, separately. These are the lowest dose subset of each cell type in (a) the lowest dose scheme and the highest of each in (b) the highest dose scheme
Mentions: Our second scenario mimics the dose-response strategy. In this scenario, the training set is composed of one dose from each cell type. In the lowest dose scheme, only the data following a 0.07 M. NaCl shock are used for training (Fig. 4). In the highest dose scheme, only the data following a 0.8 M. NaCl shock are used for training. The remaining five doses from each cell type can be used as validation data. Similar to the first scenario, the outcomes of model validation and selection are determined based on each of these fifteen subsets of validation data, separately.Fig. 4

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