Limits...
Evaluating a linear k-mer model for protein-DNA interactions using high-throughput SELEX data.

Kähärä J, Lähdesmäki H - BMC Bioinformatics (2013)

Bottom Line: We implemented the standard cross-validation scheme to reduce the number of k-mers in the model and observed that the number of k-mers can often be reduced significantly without a great negative effect on prediction accuracy.We also found that the later SELEX enrichment cycles provide a much better discrimination between bound and unbound sequences as model prediction accuracies increased for all proteins together with the cycle number.Consistent with previous results on PBM data, performance of the k-mer model was on average 9%-units better.

View Article: PubMed Central - HTML - PubMed

ABSTRACT
Transcription factor (TF) binding to DNA can be modeled in a number of different ways. It is highly debated which modeling methods are the best, how the models should be built and what can they be applied to. In this study a linear k-mer model proposed for predicting TF specificity in protein binding microarrays (PBM) is applied to a high-throughput SELEX data and the question of how to choose the most informative k-mers to the binding model is studied. We implemented the standard cross-validation scheme to reduce the number of k-mers in the model and observed that the number of k-mers can often be reduced significantly without a great negative effect on prediction accuracy. We also found that the later SELEX enrichment cycles provide a much better discrimination between bound and unbound sequences as model prediction accuracies increased for all proteins together with the cycle number. We compared prediction performance of k-mer and position specific weight matrix (PWM) models derived from the same SELEX data. Consistent with previous results on PBM data, performance of the k-mer model was on average 9%-units better. For the 15 proteins in the SELEX data set with medium enrichment cycles, classification accuracies were on average 71% and 62% for k-mer and PWMs, respectively. Finally, the k-mer model trained with SELEX data was evaluated on ChIP-seq data demonstrating substantial improvements for some proteins. For protein GATA1 the model can distinquish between true ChIP-seq peaks and negative peaks. For proteins RFX3 and NFATC1 the performance of the model was no better than chance.

Show MeSH
Illustration of classification accuracy using the CV-scheme when starting with greater number of k-mers. The test set classification accuracy as a function of number of k-mers, when the k-mers are chosen with the CV-scheme. The CV is started from 450 and 600 most frequent k-mers for proteins HSF2 and FOXJ3. The 95% normal approximation confidence intervals are plotted around the curves.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3750486&req=5

Figure 4: Illustration of classification accuracy using the CV-scheme when starting with greater number of k-mers. The test set classification accuracy as a function of number of k-mers, when the k-mers are chosen with the CV-scheme. The CV is started from 450 and 600 most frequent k-mers for proteins HSF2 and FOXJ3. The 95% normal approximation confidence intervals are plotted around the curves.

Mentions: Cross-validation starting with higher number of k-mers yields similar results (Figure 4). Sometimes the most frequent k-mers yield equal or even slightly better results than cross-validation scheme, but for some proteins the cross-validation introduces great advantages. For example for HSF2 the cross-validation clearly improves results as the classification accuracy is maximized around 150 k-mers and difference between the cross-validated and the enrichment method increases even more for lower smaller number of k-mers. Moreover, especially for smaller number of k-mers the cross-validated feature selection provides significantly better results than the standard approach (Figures 3 and 4).


Evaluating a linear k-mer model for protein-DNA interactions using high-throughput SELEX data.

Kähärä J, Lähdesmäki H - BMC Bioinformatics (2013)

Illustration of classification accuracy using the CV-scheme when starting with greater number of k-mers. The test set classification accuracy as a function of number of k-mers, when the k-mers are chosen with the CV-scheme. The CV is started from 450 and 600 most frequent k-mers for proteins HSF2 and FOXJ3. The 95% normal approximation confidence intervals are plotted around the curves.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3750486&req=5

Figure 4: Illustration of classification accuracy using the CV-scheme when starting with greater number of k-mers. The test set classification accuracy as a function of number of k-mers, when the k-mers are chosen with the CV-scheme. The CV is started from 450 and 600 most frequent k-mers for proteins HSF2 and FOXJ3. The 95% normal approximation confidence intervals are plotted around the curves.
Mentions: Cross-validation starting with higher number of k-mers yields similar results (Figure 4). Sometimes the most frequent k-mers yield equal or even slightly better results than cross-validation scheme, but for some proteins the cross-validation introduces great advantages. For example for HSF2 the cross-validation clearly improves results as the classification accuracy is maximized around 150 k-mers and difference between the cross-validated and the enrichment method increases even more for lower smaller number of k-mers. Moreover, especially for smaller number of k-mers the cross-validated feature selection provides significantly better results than the standard approach (Figures 3 and 4).

Bottom Line: We implemented the standard cross-validation scheme to reduce the number of k-mers in the model and observed that the number of k-mers can often be reduced significantly without a great negative effect on prediction accuracy.We also found that the later SELEX enrichment cycles provide a much better discrimination between bound and unbound sequences as model prediction accuracies increased for all proteins together with the cycle number.Consistent with previous results on PBM data, performance of the k-mer model was on average 9%-units better.

View Article: PubMed Central - HTML - PubMed

ABSTRACT
Transcription factor (TF) binding to DNA can be modeled in a number of different ways. It is highly debated which modeling methods are the best, how the models should be built and what can they be applied to. In this study a linear k-mer model proposed for predicting TF specificity in protein binding microarrays (PBM) is applied to a high-throughput SELEX data and the question of how to choose the most informative k-mers to the binding model is studied. We implemented the standard cross-validation scheme to reduce the number of k-mers in the model and observed that the number of k-mers can often be reduced significantly without a great negative effect on prediction accuracy. We also found that the later SELEX enrichment cycles provide a much better discrimination between bound and unbound sequences as model prediction accuracies increased for all proteins together with the cycle number. We compared prediction performance of k-mer and position specific weight matrix (PWM) models derived from the same SELEX data. Consistent with previous results on PBM data, performance of the k-mer model was on average 9%-units better. For the 15 proteins in the SELEX data set with medium enrichment cycles, classification accuracies were on average 71% and 62% for k-mer and PWMs, respectively. Finally, the k-mer model trained with SELEX data was evaluated on ChIP-seq data demonstrating substantial improvements for some proteins. For protein GATA1 the model can distinquish between true ChIP-seq peaks and negative peaks. For proteins RFX3 and NFATC1 the performance of the model was no better than chance.

Show MeSH