Biologically inspired ChaosNet architecture for Hypothetical Protein Classification
This work addresses a specific challenge in bioinformatics by providing a more data-efficient method for classifying hypothetical proteins, though it appears incremental as it applies an existing architecture to a new domain.
The paper tackles the problem of functional classification of hypothetical proteins in bioinformatics using the biologically inspired ChaosNet architecture, achieving results comparable to or better than standard machine learning techniques with significantly less training data.
ChaosNet is a type of artificial neural network framework developed for classification problems and is influenced by the chaotic property of the human brain. Each neuron of the ChaosNet architecture is the one-dimensional chaotic map called the Generalized Luroth Series (GLS). The addition of GLS as neurons in ChaosNet makes the computations straightforward while utilizing the advantageous elements of chaos. With substantially less data, ChaosNet has been demonstrated to do difficult classification problems on par with or better than traditional ANNs. In this paper, we use Chaosnet to perform a functional classification of Hypothetical proteins [HP], which is indeed a topic of great interest in bioinformatics. The results obtained with significantly lesser training data are compared with the standard machine learning techniques used in the literature.