Limits...
Bioprocess data mining using regularized regression and random forests.

Hassan S, Farhan M, Mangayil R, Huttunen H, Aho T - BMC Syst Biol (2013)

Bottom Line: In bioprocess development, the needs of data analysis include (1) getting overview to existing data sets, (2) identifying primary control parameters, (3) determining a useful control direction, and (4) planning future experiments.They are capable, e.g., in handling small number of samples with respect to the number of variables, feature selection, and the visualization of response surfaces in order to present the prediction results in an illustrative way.In this case, the modeling was still successful with Lasso (correlation between the observed and predicted yield was 0.69) and RF (0.91).

View Article: PubMed Central - HTML - PubMed

ABSTRACT

Background: In bioprocess development, the needs of data analysis include (1) getting overview to existing data sets, (2) identifying primary control parameters, (3) determining a useful control direction, and (4) planning future experiments. In particular, the integration of multiple data sets causes that these needs cannot be properly addressed by regression models that assume linear input-output relationship or unimodality of the response function. Regularized regression and random forests, on the other hand, have several properties that may appear important in this context. They are capable, e.g., in handling small number of samples with respect to the number of variables, feature selection, and the visualization of response surfaces in order to present the prediction results in an illustrative way.

Results: In this work, the applicability of regularized regression (Lasso) and random forests (RF) in bioprocess data mining was examined, and their performance was benchmarked against multiple linear regression. As an example, we used data from a culture media optimization study for microbial hydrogen production. All the three methods were capable in providing a significant model when the five variables of the culture media optimization were linearly included in modeling. However, multiple linear regression failed when also the multiplications and squares of the variables were included in modeling. In this case, the modeling was still successful with Lasso (correlation between the observed and predicted yield was 0.69) and RF (0.91).

Conclusion: We found that both regularized regression and random forests were able to produce feasible models, and the latter was efficient in capturing the non-linearity in the data. In this kind of a data mining task of bioprocess data, both methods outperform multiple linear regression.

Show MeSH

Related in: MedlinePlus

Yield predictions using the regularized regression model. The yields are presented by different colors according to the colorbar. The plots in the diagonal (i.e., variables are plotted against themselves) are left empty.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3750505&req=5

Figure 1: Yield predictions using the regularized regression model. The yields are presented by different colors according to the colorbar. The plots in the diagonal (i.e., variables are plotted against themselves) are left empty.

Mentions: In the case of transformed polynomial regression model, the estimated value for correlation was found to be 0.69 which is higher than the case of the simple model. This clearly indicates the non-linear behavior of the original dataset. Table S1 shows the resulting coefficients in the constructed model where regularization has forced 5 out of 21 coefficients to zero [see Additional file 1]. Although, the same number of non-zero coefficients were obtained from the multiple linear regression as well but the main difference is the regularized coefficients. That is, the non-zero coefficients from regularized regression were also shrunk towards zero. This results in generalized models with higher overall prediction accuracy [3]. The yield predictions are visualized in Figure 1 as a response surface. In addition, the significant variables for the model and their corresponding coefficients are listed in Table 1.


Bioprocess data mining using regularized regression and random forests.

Hassan S, Farhan M, Mangayil R, Huttunen H, Aho T - BMC Syst Biol (2013)

Yield predictions using the regularized regression model. The yields are presented by different colors according to the colorbar. The plots in the diagonal (i.e., variables are plotted against themselves) are left empty.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3750505&req=5

Figure 1: Yield predictions using the regularized regression model. The yields are presented by different colors according to the colorbar. The plots in the diagonal (i.e., variables are plotted against themselves) are left empty.
Mentions: In the case of transformed polynomial regression model, the estimated value for correlation was found to be 0.69 which is higher than the case of the simple model. This clearly indicates the non-linear behavior of the original dataset. Table S1 shows the resulting coefficients in the constructed model where regularization has forced 5 out of 21 coefficients to zero [see Additional file 1]. Although, the same number of non-zero coefficients were obtained from the multiple linear regression as well but the main difference is the regularized coefficients. That is, the non-zero coefficients from regularized regression were also shrunk towards zero. This results in generalized models with higher overall prediction accuracy [3]. The yield predictions are visualized in Figure 1 as a response surface. In addition, the significant variables for the model and their corresponding coefficients are listed in Table 1.

Bottom Line: In bioprocess development, the needs of data analysis include (1) getting overview to existing data sets, (2) identifying primary control parameters, (3) determining a useful control direction, and (4) planning future experiments.They are capable, e.g., in handling small number of samples with respect to the number of variables, feature selection, and the visualization of response surfaces in order to present the prediction results in an illustrative way.In this case, the modeling was still successful with Lasso (correlation between the observed and predicted yield was 0.69) and RF (0.91).

View Article: PubMed Central - HTML - PubMed

ABSTRACT

Background: In bioprocess development, the needs of data analysis include (1) getting overview to existing data sets, (2) identifying primary control parameters, (3) determining a useful control direction, and (4) planning future experiments. In particular, the integration of multiple data sets causes that these needs cannot be properly addressed by regression models that assume linear input-output relationship or unimodality of the response function. Regularized regression and random forests, on the other hand, have several properties that may appear important in this context. They are capable, e.g., in handling small number of samples with respect to the number of variables, feature selection, and the visualization of response surfaces in order to present the prediction results in an illustrative way.

Results: In this work, the applicability of regularized regression (Lasso) and random forests (RF) in bioprocess data mining was examined, and their performance was benchmarked against multiple linear regression. As an example, we used data from a culture media optimization study for microbial hydrogen production. All the three methods were capable in providing a significant model when the five variables of the culture media optimization were linearly included in modeling. However, multiple linear regression failed when also the multiplications and squares of the variables were included in modeling. In this case, the modeling was still successful with Lasso (correlation between the observed and predicted yield was 0.69) and RF (0.91).

Conclusion: We found that both regularized regression and random forests were able to produce feasible models, and the latter was efficient in capturing the non-linearity in the data. In this kind of a data mining task of bioprocess data, both methods outperform multiple linear regression.

Show MeSH
Related in: MedlinePlus