Document Detail


Bayesian neural network approaches to ovarian cancer identification from high-resolution mass spectrometry data.
MedLine Citation:
PMID:  15961495     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
MOTIVATION: The classification of high-dimensional data is always a challenge to statistical machine learning. We propose a novel method named shallow feature selection that assigns each feature a probability of being selected based on the structure of training data itself. Independent of particular classifiers, the high dimension of biodata can be fleetly reduced to an applicable case for consequential processing. Moreover, to improve both efficiency and performance of classification, these prior probabilities are further used to specify the distributions of top-level hyperparameters in hierarchical models of Bayesian neural network (BNN), as well as the parameters in Gaussian process models. RESULTS: Three BNN approaches were derived and then applied to identify ovarian cancer from NCI's high-resolution mass spectrometry data, which yielded an excellent performance in 1000 independent k-fold cross validations (k = 2,...,10). For instance, indices of average sensitivity and specificity of 98.56 and 98.42%, respectively, were achieved in the 2-fold cross validations. Furthermore, only one control and one cancer were misclassified in the leave-one-out cross validation. Some other popular classifiers were also tested for comparison. AVAILABILITY: The programs implemented in MatLab, R and Neal's fbm.2004-11-10.
Authors:
Jiangsheng Yu; Xue-Wen Chen
Related Documents :
19814905 - Novel kernels for error-tolerant graph classification.
19380125 - Eeg-based classification for elbow versus shoulder torque intentions involving stroke s...
18546495 - Performance improvement in protein n-myristoyl classification by bonsai with insignific...
19390645 - Is bagging effective in the classification of small-sample genomic and proteomic data?
25352555 - Sasbdb, a repository for biological small-angle scattering data.
23271095 - Predicting severe injury using vehicle telemetry data.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.    
Journal Detail:
Title:  Bioinformatics (Oxford, England)     Volume:  21 Suppl 1     ISSN:  1367-4803     ISO Abbreviation:  Bioinformatics     Publication Date:  2005 Jun 
Date Detail:
Created Date:  2005-06-17     Completed Date:  2006-06-22     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  9808944     Medline TA:  Bioinformatics     Country:  England    
Other Details:
Languages:  eng     Pagination:  i487-94     Citation Subset:  IM    
Affiliation:
School of Electronics Engineering and Computer Science, Peking University China.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Bayes Theorem*
Computational Biology / methods*
Female
Humans
Mass Spectrometry / methods*
Models, Statistical
Neural Networks (Computer)*
Normal Distribution
Ovarian Neoplasms / diagnosis*,  metabolism*
Programming Languages
Reproducibility of Results
Software

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Automatic detection of subsystem/pathway variants in genome analysis.
Next Document:  Classifying noisy protein sequence data: a case study of immunoglobulin light chains.