Exploiting physico-chemical properties in string kernels

Abstract

Background: String kernels are commonly used for the classification of biological sequences, nucleotide as well as amino acid sequences. Although string kernels are already very powerful, when it comes to amino acids they have a major short coming. They ignore an important piece of information when comparing amino acids: the physico-chemical properties such as size, hydrophobicity, or charge. This information is very valuable, especially when training data is less abundant. There have been only very few approaches so far that aim at combining these two ideas.

Results: We propose new string kernels that combine the benefits of physico-chemical descriptors for amino acids with the ones of string kernels. The benefits of the proposed kernels are assessed on two problems: MHC-peptide binding classification using position specific kernels and protein classification based on the substring spectrum of the sequences. Our experiments demonstrate that the incorporation of amino acid properties in string kernels yields improved performances compared to standard string kernels and to previously proposed non-substring kernels.

Conclusions: In summary, the proposed modifications, in particular the combination with the RBF substring kernel, consistently yield improvements without affecting the computational complexity. The proposed kernels therefore appear to be the kernels of choice for any protein sequence-based inference.

Availability: Data sets, code and additional information are available from http://www.fml.tuebingen.mpg.de/raetsch/suppl/aask. Implementations of the developed kernels are available as part of the Shogun toolbox.

Figure 1

Learning Curve Analysis on MHC allele A*0201. Shown are areas under the ROC curves averaged over 100 different test splits (30%) and for increasing numbers of training examples (up to 70%). The training part was used for training and model selection using 5-fold cross-validation.

Figure 2

Performance of WD and WD-RBF (blosum50) kernels on human MHC alleles from the IEDB benchmark data set. The pie chart displays the number of alleles for which the WD (green) and the WD-RBF (red) performed best, respectively, and the number of alleles for which they performed equally (blue).