Optimized multilayer perceptrons for molecular classification and diagnosis using genomic data
| Autor: | Yue Wang, Zuyi Wang, Yuanjian Feng, Eric P. Hoffman, Jianhua Xuan, Robert Clarke, Marina Bakay, Yibin Dong |
|---|---|
| Rok vydání: | 2006 |
| Předmět: |
Genetic Markers
Statistics and Probability Computer science Initialization computer.software_genre Sensitivity and Specificity Biochemistry Pattern Recognition Automated Bayes' theorem Neoplasms Biomarkers Tumor Humans Diagnosis Computer-Assisted Molecular Biology Receiver operating characteristic business.industry Chromosome Mapping Reproducibility of Results Pattern recognition Perceptron Linear discriminant analysis Computer Science Applications Computational Mathematics ComputingMethodologies_PATTERNRECOGNITION Computational Theory and Mathematics Sample size determination Neural Networks Computer Data mining Artificial intelligence business computer Curse of dimensionality |
| Zdroj: | Bioinformatics. 22:755-761 |
| ISSN: | 1367-4811 1367-4803 |
| DOI: | 10.1093/bioinformatics/btk036 |
| Popis: | Motivation: Multilayer perceptrons (MLP) represent one of the widely used and effective machine learning methods currently applied to diagnostic classification based on high-dimensional genomic data. Since the dimensionalities of the existing genomic data often exceed the available sample sizes by orders of magnitude, the MLP performance may degrade owing to the curse of dimensionality and over-fitting, and may not provide acceptable prediction accuracy. Results: Based on Fisher linear discriminant analysis, we designed and implemented an MLP optimization scheme for a two-layer MLP that effectively optimizes the initialization of MLP parameters and MLP architecture. The optimized MLP consistently demonstrated its ability in easing the curse of dimensionality in large microarray datasets. In comparison with a conventional MLP using random initialization, we obtained significant improvements in major performance measures including Bayes classification accuracy, convergence properties and area under the receiver operating characteristic curve (Az). Supplementary information: The Supplementary information is available on Contact: yuewang@vt.edu |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|