Background: String kernels are commonly used for the classication 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 benefits of physico-chemical descriptors for amino acids with the ones of string kernels. The benefits of the proposed kernels are assessed on two problems: MHC-peptide binding classication using position specic kernels and protein classication 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 modications, 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 will be available from http://www.fml.mpg.de/raetsch/suppl/aask. The developed kernels will be part of the next Shogun toolbox release.