Back to Search
Start Over
Improving biomolecular pattern discovery and visualization with hybrid self-adaptive networks.
- Source :
-
IEEE transactions on nanobioscience [IEEE Trans Nanobioscience] 2002 Dec; Vol. 1 (4), pp. 146-66. - Publication Year :
- 2002
-
Abstract
- There is an increasing need to develop powerful techniques to improve biomedical pattern discovery and visualization. This paper presents an automated approach, based on hybrid self-adaptive neural networks, to pattern identification and visualization for biomolecular data. The methods are tested on two datasets: leukemia expression data and DNA splice-junction sequences. Several supervised and unsupervised models are implemented and compared. A comprehensive evaluation study of some of their intrinsic mechanisms is presented. The results suggest that these tools may be useful to support biological knowledge discovery based on advanced classification and visualization tasks.
- Subjects :
- Algorithms
Gene Expression Profiling methods
Humans
Leukemia genetics
Reproducibility of Results
Sensitivity and Specificity
User-Computer Interface
Biomarkers, Tumor genetics
Leukemia diagnosis
Neoplasm Proteins genetics
Neural Networks, Computer
Oligonucleotide Array Sequence Analysis methods
Pattern Recognition, Automated methods
Sequence Analysis, DNA methods
Subjects
Details
- Language :
- English
- ISSN :
- 1536-1241
- Volume :
- 1
- Issue :
- 4
- Database :
- MEDLINE
- Journal :
- IEEE transactions on nanobioscience
- Publication Type :
- Academic Journal
- Accession number :
- 16689206
- Full Text :
- https://doi.org/10.1109/tnb.2003.809465