Characterizing human gene splice sites using evolved regular expressions

In this paper, an algorithm using evolved regular expressions to characterize and predict human gene splice sites without any prior knowledge is described. In contrast to previous pattern-based approaches to the splice site detection problem, the patterns to be matched are unknown in advance and discovered using a supervised learning approach. We have used a genetic programming based system, PerlGP, to evolve regular expressions and proper length windows for a long sequence in which the evolved regular expressions can effectively characterize and predict the splice junctions. Since the gene splicing process is too complex to be fully understood currently, and the widely accepted consensus sequences only reflect some partial statistical information around splice sites, not to mention defining a splice site. However, our evolved regular expressions may shed new light on the underlying rules that define splice sites. Experimental results demonstrate that using the evolved regular expressions, splice junctions could be accurately characterized, furthermore, these evolved regular expressions could also be employed as a predictor to detect whether a CT/AG containing sequence is a splice site or not. Our experimental results also exhibit that the performance of this approach for predicting human gene splice junctions is competitive compared with some other traditional methods.

1. INTRODUCTION

Modern molecular biology is being revolutionized by the development of new technology. With the complete sequencing of several model organisms, a pressing problem is how to describe and understand the huge amount of the biological data which is accumulating. Fortunately, the marriage of biology and computer science makes the analysis of genomic data much more tractable. To annotate genomes automatically, splice site identification is of vital importance, because it is an essential step for gene prediction. As the central dogma [1] says: “DNA makes RNA makes Protein”, when most genes of eukaryotic organisms are translated into proteins, intervening sequences known as introns are removed from the pre-mRNA in the nucleus before the matured mRNA is transported into the cytoplasm and translated. The regions of genes that are ultimately translated into proteins are often referred to as exons, and a splicesite is just the boundary of an intron and an exon. Fig. 1 presents a visual description of splice junctions in the gene structure. Hence, if we could identify splice sites accurately, a specific gene structure will become much clearer. In this sense, a good method for characterizing and predicting splice junctions would surely improve automatic genome annotation. Fig. 1. A visual description of splice junctions in the gene structure