A0469
Title: Phylogeny and artificial neural networks
Authors: Alina F Leuchtenberger - Medical University of Vienna (Austria) [presenting]
Stephen M Crotty - University of Adelaide (Australia)
Tamara Drucks - TU Wien (Austria)
Heiko A Schmidt - Medical University of Vienna (Austria)
Sebastian Burgstaller-Muehlbacher - Medical University of Vienna (Austria)
Arndt von Haeseler - University of Vienna (Austria)
Abstract: In recent years Artificial Neural Networks (ANNs) have become extremely popular. As powerful learning methods, they solve pattern recognition tasks and other challenges. We demonstrate how ANNs can be employed to solve phylogenetic problems. Long-branch attraction is a classical problem in phylogenetics. When long branches are placed adjacent to each other on a reconstructed tree, it is difficult to tell if this is artefactual (Felsenstein-type), or accurate (Farris-type). We developed F-zoneNN, an ANN which is able to infer with high accuracy if a multiple sequence alignment evolved under a Farris-type or Felsenstein-type tree. Despite its success, it is difficult to identify the features within the data that F-zoneNN leverages in making its determination. F-zoneNN is a composition of 9 linear and 9 non-linear functions including more than 1.2 million parameters, and so it is impossible to tell what drives the decisions of such an ANN. To get deeper insights into the decision-making process we endeavoured to simplify our trained network as much as possible, without sacrificing accuracy. This led to the development of an alternative mathematical representation of sequence alignments. Using this representation as input, we found that a linear function can infer the tree-type with high accuracy. This technique harbours the great potential for use in other phylogenetic applications of ANNs.
