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

Stratified random cross-validation scheme (SRCV). Light gray colored boxes show parts of the data which we used as training sets (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). In each of the three runs, the training and the validation sets change as indicated in these graphs
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Fig6: Stratified random cross-validation scheme (SRCV). Light gray colored boxes show parts of the data which we used as training sets (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). In each of the three runs, the training and the validation sets change as indicated in these graphs

Mentions: In a random cross-validation scheme, there are no pre-defined partitions, unlike the hold-out partitioning schemes. Here, we implement stratified random cross-validation which is a specific type of cross-validation in which the training sets can be forced to follow a certain structure. We randomly partition the data into training and validation sets, in three different runs. In each run, we force the training sets to include the same amount of data from each cell type and dose level. We estimate the parameters and also calculate the measures we that we use for the analysis of the simulations (further explained in the next subsection), at each run. Later, we make consensus decisions using the average of these measures that were evaluated at each run. The different partitioning schemes applied in each run can be seen in Fig. 6.Fig. 6


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)

Stratified random cross-validation scheme (SRCV). Light gray colored boxes show parts of the data which we used as training sets (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). In each of the three runs, the training and the validation sets change as indicated in these graphs
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Fig6: Stratified random cross-validation scheme (SRCV). Light gray colored boxes show parts of the data which we used as training sets (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). In each of the three runs, the training and the validation sets change as indicated in these graphs
Mentions: In a random cross-validation scheme, there are no pre-defined partitions, unlike the hold-out partitioning schemes. Here, we implement stratified random cross-validation which is a specific type of cross-validation in which the training sets can be forced to follow a certain structure. We randomly partition the data into training and validation sets, in three different runs. In each run, we force the training sets to include the same amount of data from each cell type and dose level. We estimate the parameters and also calculate the measures we that we use for the analysis of the simulations (further explained in the next subsection), at each run. Later, we make consensus decisions using the average of these measures that were evaluated at each run. The different partitioning schemes applied in each run can be seen in Fig. 6.Fig. 6

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