• Corpus ID: 13267858

Pattern Analysis for the Prediction of Eukoryatic Pro-peptide Cleavage Sites ?

@inproceedings{zr2007PatternAF,
  title={Pattern Analysis for the Prediction of Eukoryatic Pro-peptide Cleavage Sites ?},
  author={S. {\"O}z{\"o}ğ{\"u}r and John Shawe-Taylor and Gerhard-Wilhelm Weber and Z{\"u}mr{\"u}t Beg{\"u}m {\"O}gel},
  year={2007}
}
Support vector machines have many applications in analyzing biological data from analysing gene expression arrays to understanding EEG signals of sleep stages. We have developed an application that will allow the prediction of the pro-peptide cleavage site of fungal extracellular proteins which display mostly a monobasic or dibasic processing site. So, one of the critical questions to be answered within the scope of this study, reads: What are the determinants of the cleavage site which can be… 

Figures and Tables from this paper

A review on data mining and continuous optimization applications in computational biology and medicine.

Data mining and machine learning methods for an analysis of complex systems in computational biology mathematically deepens recent advances in modeling and prediction by rigorously introducing the environment and aspects of errors and uncertainty into the genetic context within the framework of matrix and interval arithmetics.

MODELLING OF KERNEL MACHINES BY INFINITE AND SEMI‐INFINITE PROGRAMMING

This work proposes a novel method of “infinite” kernel combinations for learning problems with the help of infinite and semi‐infinite programming regarding all elements in kernel space.

Infinite kernel learning via infinite and semi-infinite programming

A novel method of ‘infinite’ kernel combinations for learning problems with the help of infinite and semi-infinite optimizations is proposed and implemented with the conceptual reduction method and tested on homogeneous and heterogeneous data; this yields a better accuracy than a single-kernel learning for the heterogeneousData.

On numerical optimization theory of infinite kernel learning

The results show that the new algorithm called “infinite” kernel learning (IKL) on heterogenous data sets improves the classifaction accuracy efficiently on heterogeneous data compared to classical one-kernel approaches.

LEARNING WITH INFINITELY MANY KERNELS VIA SEMI-INFINITE PROGRAMMING

A novel method to find infinitely many kernel combinations for learning problems with the help of infinite and semi-infinite optimization regarding all elements in kernel space is proposed.

References

SHOWING 1-10 OF 32 REFERENCES

Prediction of proprotein convertase cleavage sites.

A method for prediction of cleavage sites for PCs based on artificial neural networks using furin-specific and general PC-specific networks trained on data from the Swiss-Prot protein database is developed.

Support vector machines for prediction of protein subcellular location.

Support Vector Machine (SVM), which is one kind of learning machines, was applied to predict the subcellular location of proteins from their amino acid composition and the correct prediction rates reached 82, 75, and 73% for 2240 proteins, 2513 proteins, and 2591 proteins, respectively.

Prediction of N-terminal protein sorting signals.

22 A Model of Evolutionary Change in Proteins

The body of data used in this study includes 1,572 changes of closely related proteins appearing in the Atlas volumes through Supplement 2 and the mutation data were accumulated from the phylo-genetic trees and from a few pairs of related sequences.

Amino acid substitution matrices from an information theoretic perspective