Applying artificial neural networks to the classification of wheat varieties processed via MALDI-TOF mass spectrometry
Schibeci, D., Potter, R., Wathen-Dunn, K., Jones, M. and Bellgard, M. (2001) Applying artificial neural networks to the classification of wheat varieties processed via MALDI-TOF mass spectrometry. In: Mastorakis, N.E., (ed.) Advances in Neural Networks and Applications. World Scientific and Engineering Society Press, pp. 262-267.
*No subscription required
With the advent of new bio-technologies there is a significant increase in both the variety and amount of data that needs to be analysed in order to extract biological meaning. This is evident from the masses of molecular data being produced as a result of the numerous genome sequencing projects as well as from data now produced from DNA microarray/chip technologies. In this paper, we describe analysis of data obtain from recent advances in time-of-flight mass spectrometry which is a new method for rapid, high-resolution separation of protein mixtures. We employ a feedforward artificial neural network to train the resultant protein profiles processed from a number of varieties of wheat in order to classify them. The results of this study are extremely positive with results ranging from 87.5% to 100% accuracy, and we discuss them in context with a number of challenging problems for further studies.
|Publication Type:||Book Chapter|
|Murdoch Affiliation:||Western Australian State Agricultural Biotechnology Centre
School of Information Technology
|Publisher:||World Scientific and Engineering Society Press|
|Item Control Page|
Downloads per month over past year