Cathie LeBlanc, Charles R. Katholi, Thomas R. Unnasch, and Susan I. Hruska
Adaptive resonance theory (ART) describes a class of artificial neural network architectures that act as classification tools which self-organize, work in realtime, and require no retraining to classify novel sequences. We have adapted ART networks to provide support to scientists attempting to categorize tandem repeat DNA fragments from Onchocerca volvulus. In this approach, sequences of DNA fragments are presented to multiple ART-based networks which are linked together into two (or more) tiers; the first provides coarse sequence classification while the subsequent tiers refine the classifications as needed. The overall rating of the resulting classification of fragments is measured using statistical techniques based on those introduced by Zimmerman, et al. (1994) validate results from traAitional phylogenetic analysis. Tests of the Hierarchical ART-based Classification Network, or HABclass network, indicate its value as a fast, easy-to-use classification tool which adapts to new data without retraining on previously classified data.