Limits...
A statistical learning approach to the modeling of chromatographic retention of oligonucleotides incorporating sequence and secondary structure data.

Sturm M, Quinten S, Huber CG, Kohlbacher O - Nucleic Acids Res. (2007)

Bottom Line: We propose a new model for predicting the retention time of oligonucleotides.Because of the secondary structure information, the model is applicable even at relatively low temperatures where the secondary structure is not suppressed by thermal denaturing.We describe different possibilities of feature calculation from base sequence and secondary structure, present the results and compare our model to existing models.

View Article: PubMed Central - PubMed

Affiliation: Simulation of Biological Systems, Eberhard Karls University, Tübingen, Germany. sturm@informatik.uni-tuebingen.de

ABSTRACT
We propose a new model for predicting the retention time of oligonucleotides. The model is based on nu support vector regression using features derived from base sequence and predicted secondary structure of oligonucleotides. Because of the secondary structure information, the model is applicable even at relatively low temperatures where the secondary structure is not suppressed by thermal denaturing. This makes the prediction of oligonucleotide retention time for arbitrary temperatures possible, provided that the target temperature lies within the temperature range of the training data. We describe different possibilities of feature calculation from base sequence and secondary structure, present the results and compare our model to existing models.

Show MeSH

Related in: MedlinePlus

Number of training data points plotted versus prediction performance. The error bars show the SD, derived from 200 repetitions of the experiment.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC1919494&req=5

Figure 6: Number of training data points plotted versus prediction performance. The error bars show the SD, derived from 200 repetitions of the experiment.

Mentions: Figure 6 shows the results for the ‘count_multistruct_stacking’ model. From the figure, one can see that even for a temperature of 30° C, 40 training sequences (or more) are sufficient to construct a model describing oligonucleotide retention with acceptable accuracy. No significant improvement is observed for more than 50 data points.Figure 6.


A statistical learning approach to the modeling of chromatographic retention of oligonucleotides incorporating sequence and secondary structure data.

Sturm M, Quinten S, Huber CG, Kohlbacher O - Nucleic Acids Res. (2007)

Number of training data points plotted versus prediction performance. The error bars show the SD, derived from 200 repetitions of the experiment.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC1919494&req=5

Figure 6: Number of training data points plotted versus prediction performance. The error bars show the SD, derived from 200 repetitions of the experiment.
Mentions: Figure 6 shows the results for the ‘count_multistruct_stacking’ model. From the figure, one can see that even for a temperature of 30° C, 40 training sequences (or more) are sufficient to construct a model describing oligonucleotide retention with acceptable accuracy. No significant improvement is observed for more than 50 data points.Figure 6.

Bottom Line: We propose a new model for predicting the retention time of oligonucleotides.Because of the secondary structure information, the model is applicable even at relatively low temperatures where the secondary structure is not suppressed by thermal denaturing.We describe different possibilities of feature calculation from base sequence and secondary structure, present the results and compare our model to existing models.

View Article: PubMed Central - PubMed

Affiliation: Simulation of Biological Systems, Eberhard Karls University, Tübingen, Germany. sturm@informatik.uni-tuebingen.de

ABSTRACT
We propose a new model for predicting the retention time of oligonucleotides. The model is based on nu support vector regression using features derived from base sequence and predicted secondary structure of oligonucleotides. Because of the secondary structure information, the model is applicable even at relatively low temperatures where the secondary structure is not suppressed by thermal denaturing. This makes the prediction of oligonucleotide retention time for arbitrary temperatures possible, provided that the target temperature lies within the temperature range of the training data. We describe different possibilities of feature calculation from base sequence and secondary structure, present the results and compare our model to existing models.

Show MeSH
Related in: MedlinePlus