Oligo kernels for datamining on biological sequences: a case study on prokaryotic translation initiation sites

BackgroundKernel-based learning algorithms are among the most advanced machine learning methods and have been successfully applied to a variety of sequence classification tasks within the field of bioinformatics. Conventional kernels utilized so far do not provide an easy interpretation of the learnt representations in terms of positional and compositional variability of the underlying biological signals.ResultsWe propose a kernel-based approach to datamining on biological sequences. With our method it is possible to model and analyze positional variability of oligomers of any length in a natural way. On one hand this is achieved by mapping the sequences to an intuitive but high-dimensional feature space, well-suited for interpretation of the learnt models. On the other hand, by means of the kernel trick we can provide a general learning algorithm for that high-dimensional representation because all required statistics can be computed without performing an explicit feature space mapping of the sequences. By introducing a kernel parameter that controls the degree of position-dependency, our feature space representation can be tailored to the characteristics of the biological problem at hand. A regularized learning scheme enables application even to biological problems for which only small sets of example sequences are available. Our approach includes a visualization method for transparent representation of characteristic sequence features. Thereby importance of features can be measured in terms of discriminative strength with respect to classification of the underlying sequences. To demonstrate and validate our concept on a biochemically well-defined case, we analyze E. coli translation initiation sites in order to show that we can find biologically relevant signals. For that case, our results clearly show that the Shine-Dalgarno sequence is the most important signal upstream a start codon. The variability in position and composition we found for that signal is in accordance with previous biological knowledge. We also find evidence for signals downstream of the start codon, previously introduced as transcriptional enhancers. These signals are mainly characterized by occurrences of adenine in a region of about 4 nucleotides next to the start codon.ConclusionsWe showed that the oligo kernel can provide a valuable tool for the analysis of relevant signals in biological sequences. In the case of translation initiation sites we could clearly deduce the most discriminative motifs and their positional variation from example sequences. Attractive features of our approach are its flexibility with respect to oligomer length and position conservation. By means of these two parameters oligo kernels can easily be adapted to different biological problems.

[1]  Jing Peng,et al.  SVM vs regularized least squares classification , 2004, ICPR 2004.

[2]  Sean R. Eddy,et al.  Biological sequence analysis: Contents , 1998 .

[3]  L. Isaksson,et al.  Influences on translation initiation and early elongation by the messenger RNA region flanking the initiation codon at the 3' side. , 2002, Gene.

[4]  Jin Wang,et al.  Accuracy improvement for identifying translation initiation sites in microbial genomes , 2004, Bioinform..

[5]  T. D. Schneider,et al.  Anatomy of Escherichia coli ribosome binding sites. , 2001, Journal of molecular biology.

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[8]  T. Speed,et al.  Biological Sequence Analysis , 1998 .

[9]  Feng-Biao Guo,et al.  ZCURVE: a new system for recognizing protein-coding genes in bacterial and archaeal genomes. , 2003, Nucleic acids research.

[10]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[11]  T Gojobori,et al.  Codon and base biases after the initiation codon of the open reading frames in the Escherichia coli genome and their influence on the translation efficiency. , 2001, Journal of biochemistry.

[12]  S. Karlin,et al.  Correlations between Shine-Dalgarno Sequences and Gene Features Such as Predicted Expression Levels and Operon Structures , 2002, Journal of bacteriology.

[13]  Kenneth E. Rudd,et al.  EcoGene: a genome sequence database for Escherichia coli K-12 , 2000, Nucleic Acids Res..

[14]  Eleazar Eskin,et al.  The Spectrum Kernel: A String Kernel for SVM Protein Classification , 2001, Pacific Symposium on Biocomputing.

[15]  Thorsten Joachims,et al.  Making large-scale support vector machine learning practical , 1999 .

[16]  Pierre Baldi,et al.  Bioinformatics - the machine learning approach (2. ed.) , 2000 .

[17]  Bernard De Baets,et al.  Feature subset selection for splice site prediction , 2002, ECCB.

[18]  W. Tate,et al.  Codon bias at the 3'-side of the initiation codon is correlated with translation initiation efficiency in Escherichia coli. , 2001, Gene.

[19]  Rainer Merkl,et al.  YACOP: Enhanced gene prediction obtained by a combination of existing methods , 2003, Silico Biol..

[20]  Bernhard Schölkopf,et al.  Sparse Greedy Matrix Approximation for Machine Learning , 2000, International Conference on Machine Learning.

[21]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[22]  Gunnar Rätsch,et al.  Engineering Support Vector Machine Kerneis That Recognize Translation Initialion Sites , 2000, German Conference on Bioinformatics.

[23]  Martin Vingron,et al.  Support Vector Machines for Protein Fold Class Prediction , 2003 .

[24]  K. Heller,et al.  Sequence information for the splicing of human pre-mRNA identified by support vector machine classification. , 2003, Genome research.