Limits...
Biomarker discovery and redundancy reduction towards classification using a multi-factorial MALDI-TOF MS T2DM mouse model dataset.

Bauer C, Kleinjung F, Smith CJ, Towers MW, Tiss A, Chadt A, Dreja T, Beule D, Al-Hasani H, Reinert K, Schuchhardt J, Cramer R - BMC Bioinformatics (2011)

Bottom Line: The combination of ANOVA and redundancy exploitation allows for identification of biomarker candidates in multi-dimensional MALDI-TOF MS profiling studies with complex experimental design.With respect to feature selection our method provides a fast and intuitive alternative to global optimization strategies with comparable performance.The method is implemented in R and the scripts are available by contacting the corresponding author.

View Article: PubMed Central - HTML - PubMed

Affiliation: MicroDiscovery GmbH, Marienburger Str, 1, 10405 Berlin, Germany. chris.bauer@microdiscovery.de

ABSTRACT

Background: Diabetes like many diseases and biological processes is not mono-causal. On the one hand multi-factorial studies with complex experimental design are required for its comprehensive analysis. On the other hand, the data from these studies often include a substantial amount of redundancy such as proteins that are typically represented by a multitude of peptides. Coping simultaneously with both complexities (experimental and technological) makes data analysis a challenge for Bioinformatics.

Results: We present a comprehensive work-flow tailored for analyzing complex data including data from multi-factorial studies. The developed approach aims at revealing effects caused by a distinct combination of experimental factors, in our case genotype and diet. Applying the developed work-flow to the analysis of an established polygenic mouse model for diet-induced type 2 diabetes, we found peptides with significant fold changes exclusively for the combination of a particular strain and diet. Exploitation of redundancy enables the visualization of peptide correlation and provides a natural way of feature selection for classification and prediction. Classification based on the features selected using our approach performs similar to classifications based on more complex feature selection methods.

Conclusions: The combination of ANOVA and redundancy exploitation allows for identification of biomarker candidates in multi-dimensional MALDI-TOF MS profiling studies with complex experimental design. With respect to feature selection our method provides a fast and intuitive alternative to global optimization strategies with comparable performance. The method is implemented in R and the scripts are available by contacting the corresponding author.

Show MeSH

Related in: MedlinePlus

Error Plot to ensure homoscedasticity. Error plot after log transformation to ensure homoscedasticity including linear fit (orange line) and lowess fit (black line). The different colors reflect different genotypes (red: B6, green: NZO, blue: SJL).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3116487&req=5

Figure 3: Error Plot to ensure homoscedasticity. Error plot after log transformation to ensure homoscedasticity including linear fit (orange line) and lowess fit (black line). The different colors reflect different genotypes (red: B6, green: NZO, blue: SJL).

Mentions: The effects of log transformation, baseline correction and peak matching are depicted in Figure 2. After applying logarithmic transformation to the spectra the correlation between variance and intensity is still strong. However even the combination of log transformation, baseline correction and peak mapping does not lead to a stabilization of the variance which is necessary for applying our statistical analysis methods. Hence, in order to assure homoscedasticity additional steps were required. Obviously, there is still a linear dependency between variance and intensity indicating a multiplicative error model (see Figure 2). In order to account for this, we applied another log transformation. We added a pseudo-count of 0.1 to avoid the singularity at 0. Finally we added an offset for convenience. After this transformation the data are homoscedastic (see Figure 3).


Biomarker discovery and redundancy reduction towards classification using a multi-factorial MALDI-TOF MS T2DM mouse model dataset.

Bauer C, Kleinjung F, Smith CJ, Towers MW, Tiss A, Chadt A, Dreja T, Beule D, Al-Hasani H, Reinert K, Schuchhardt J, Cramer R - BMC Bioinformatics (2011)

Error Plot to ensure homoscedasticity. Error plot after log transformation to ensure homoscedasticity including linear fit (orange line) and lowess fit (black line). The different colors reflect different genotypes (red: B6, green: NZO, blue: SJL).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3116487&req=5

Figure 3: Error Plot to ensure homoscedasticity. Error plot after log transformation to ensure homoscedasticity including linear fit (orange line) and lowess fit (black line). The different colors reflect different genotypes (red: B6, green: NZO, blue: SJL).
Mentions: The effects of log transformation, baseline correction and peak matching are depicted in Figure 2. After applying logarithmic transformation to the spectra the correlation between variance and intensity is still strong. However even the combination of log transformation, baseline correction and peak mapping does not lead to a stabilization of the variance which is necessary for applying our statistical analysis methods. Hence, in order to assure homoscedasticity additional steps were required. Obviously, there is still a linear dependency between variance and intensity indicating a multiplicative error model (see Figure 2). In order to account for this, we applied another log transformation. We added a pseudo-count of 0.1 to avoid the singularity at 0. Finally we added an offset for convenience. After this transformation the data are homoscedastic (see Figure 3).

Bottom Line: The combination of ANOVA and redundancy exploitation allows for identification of biomarker candidates in multi-dimensional MALDI-TOF MS profiling studies with complex experimental design.With respect to feature selection our method provides a fast and intuitive alternative to global optimization strategies with comparable performance.The method is implemented in R and the scripts are available by contacting the corresponding author.

View Article: PubMed Central - HTML - PubMed

Affiliation: MicroDiscovery GmbH, Marienburger Str, 1, 10405 Berlin, Germany. chris.bauer@microdiscovery.de

ABSTRACT

Background: Diabetes like many diseases and biological processes is not mono-causal. On the one hand multi-factorial studies with complex experimental design are required for its comprehensive analysis. On the other hand, the data from these studies often include a substantial amount of redundancy such as proteins that are typically represented by a multitude of peptides. Coping simultaneously with both complexities (experimental and technological) makes data analysis a challenge for Bioinformatics.

Results: We present a comprehensive work-flow tailored for analyzing complex data including data from multi-factorial studies. The developed approach aims at revealing effects caused by a distinct combination of experimental factors, in our case genotype and diet. Applying the developed work-flow to the analysis of an established polygenic mouse model for diet-induced type 2 diabetes, we found peptides with significant fold changes exclusively for the combination of a particular strain and diet. Exploitation of redundancy enables the visualization of peptide correlation and provides a natural way of feature selection for classification and prediction. Classification based on the features selected using our approach performs similar to classifications based on more complex feature selection methods.

Conclusions: The combination of ANOVA and redundancy exploitation allows for identification of biomarker candidates in multi-dimensional MALDI-TOF MS profiling studies with complex experimental design. With respect to feature selection our method provides a fast and intuitive alternative to global optimization strategies with comparable performance. The method is implemented in R and the scripts are available by contacting the corresponding author.

Show MeSH
Related in: MedlinePlus