Class Imbalance Methods for Translation Initiation Site Recognition.

Translation initiation sites (TIS) recognition is one of the first, steps in gene structure prediction, and one of the common components in any gene recognition system Many methods have been described HI the libel;Wire to identify TIS in transcripts such as mRNA, EST and cDNA sequences However, the recognition of TIS in DNA sequences is a fat more challenging task, and the methods described so far for transcripts achieve poor results in DNA sequences Most, methods approach tins problem taking into account, its biological features In this work we try a different, view, considering this classification problem from a purely machine learning perspectiveFrom the point of view of machine learning, TIS recognition is a. class imbalance problem Thus, in this paper we approach TIS recognition from tins angle, and apply the different methods that. have been developed to deal with imbalance datasetsResults show an advantage of class imbalance methods with respect. to the same methods applied without considering the class unbalance nature of the problem The applied methods are also able to improve the results obtained with the best method in the literature, winch is based on looking for the next, in-frame stop codon from the putative TIS that, must be predicted.