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
Classification accuracies of the k-mer model and PWM models. The test set classification accuracy is plotted for 3 different k-mer model approaches and the PWM model. The 95% normal approximation confidence intervals are plotted on top of each bar.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 1: Classification accuracies of the k-mer model and PWM models. The test set classification accuracy is plotted for 3 different k-mer model approaches and the PWM model. The 95% normal approximation confidence intervals are plotted on top of each bar.

Mentions: The classification accuracies together with 95% confidence intervals are shown in Figure 1. The k- mer model clearly outperforms the PWM models as can be seen from the figure. In the first bars the accuracy of the k-mer model is the accuracy using the optimal number of most frequent k-mers. The average classification accuracy is 71% for the k-mer model and 62% for the PWM models. In the second and third bars the accuracy is obtained with k-mer model using the most enriched k-mers. Surprisingly k-mer model performance is better, when choosing the most frequent k-mers instead of the most enriched k-mers. This might indicate that assigning high affinity scores to k-mers responsible for binding as well as giving negative affinity scores to frequent k-mers that are not part of the binding are important.


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

Kähärä J, Lähdesmäki H - BMC Bioinformatics (2013)

Classification accuracies of the k-mer model and PWM models. The test set classification accuracy is plotted for 3 different k-mer model approaches and the PWM model. The 95% normal approximation confidence intervals are plotted on top of each bar.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 1: Classification accuracies of the k-mer model and PWM models. The test set classification accuracy is plotted for 3 different k-mer model approaches and the PWM model. The 95% normal approximation confidence intervals are plotted on top of each bar.
Mentions: The classification accuracies together with 95% confidence intervals are shown in Figure 1. The k- mer model clearly outperforms the PWM models as can be seen from the figure. In the first bars the accuracy of the k-mer model is the accuracy using the optimal number of most frequent k-mers. The average classification accuracy is 71% for the k-mer model and 62% for the PWM models. In the second and third bars the accuracy is obtained with k-mer model using the most enriched k-mers. Surprisingly k-mer model performance is better, when choosing the most frequent k-mers instead of the most enriched k-mers. This might indicate that assigning high affinity scores to k-mers responsible for binding as well as giving negative affinity scores to frequent k-mers that are not part of the binding are important.

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