Bioinformatics Advance Access originally published online on July 29, 2004
Bioinformatics 2004 20(18):3544-3552; doi:10.1093/bioinformatics/bth441
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Bioinformatics vol. 20 issue 18 © Oxford University Press 2004; all rights reserved.
The ‘subsequent artificial neural network’ (SANN) approach might bring more classificatory power to ANN-based DNA microarray analyses
1 Institute for Medical Informatics, Medical University of Luebeck, 23538 Luebeck, Germany, 2 Institute of Pathology, Ruhr-University of Bochum Medical School, 44787 Bochum, Germany, 3 Department of Otolaryngology, Head and Neck Surgery, St. Elisabeth Hospital, Ruhr-University of Bochum Medical School, 44787 Bochum, Germany, 4 Institute of Pathology, University Hospital of the Saarland, 66421 Homburg-Saar, Germany
Received on May 19, 2004; revised on July 20, 2004; accepted on July 23, 2004
Advance Access Publication July 29, 2004
Motivation: Human decisions often proceed in two steps. Initially those most preferred are chosen followed by a subsequent choice of these preferences. Applying one artificial neural network (ANN), a classification is limited to the preselection process. The final categorization is only possible by a subsequent ANN that distinguishes the pre-chosen classes. Existing strategies using coupled ANNs are discussed and a new approach particularly suited for multiclass classification problems is introduced (‘Subsequent ANN’, SANN).
Results: Evaluating a simulated data base comprising 3 classes, classification results of SANN were obviously superior to those achieved by ANN. To evaluate a real-world data base the microarray benchmark GCM (14 classes) was chosen. The ANN results reached 72%, comparable to previous results. Using SANN, up to 81% of the tumors were correctly classified.
Availability: Programs used in this work and numerical results are available upon request.
Contact: linder{at}imi.uni-luebeck.de
* To whom correspondence should be addressed.
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  Z. Wang, Y. Wang, J. Xuan, Y. Dong, M. Bakay, Y. Feng, R. Clarke, and E. P. Hoffman Optimized multilayer perceptrons for molecular classification and diagnosis using genomic data Bioinformatics, March 15, 2006; 22(6): 755 - 761. [Abstract] [Full Text] [PDF]
|
|