Bioinformatics–the Machine Learning Approach

Abstract

Computational analysis of biological sequences – linear descriptions of protein, DNA and RNA molecules has completely changed its character since the late 1980s. The main driving force behind the changes has been the introduction of new, efficient experimental techniques, primarily DNA sequencing that has led to an exponential growth of data. As genome and other sequencing projects continue to advance, the interest progressively switches from the accumulation of data to its interpretation. There are some problems concerning the vast amount of data in the biological databases that has to be taken into account.