Logistic regression for disease classification using microarray data: model selection in a large p and small n case.

Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Abstract Text:

J G Liao,Khew-Voon Chin,

MOTIVATION: Logistic regression is a standard method for building prediction models for a binary outcome and has been extended for disease classification with microarray data by many authors. A feature (gene) selection step, however, must be added to penalized logistic modeling due to a large number of genes and a small number of subjects. Model selection for this two-step approach requires new statistical tools because prediction error estimation ignoring the feature selection step can be severely downward biased. Generic methods such as cross-validation and non-parametric bootstrap can be very ineffective due to the big variability in the prediction error estimate. RESULTS: We propose a parametric bootstrap model for more accurate estimation of the prediction error that is tailored to the microarray data by borrowing from the extensive research in identifying differentially expressed genes, especially the local false discovery rate. The proposed method provides guidance on the two critical issues in model selection: the number of genes to include in the model and the optimal shrinkage for the penalized logistic regression. We show that selecting more than 20 genes usually helps little in further reducing the prediction error. Application to Golub's leukemia data and our own cervical cancer data leads to highly accurate prediction models. AVAILABILITY: R library GeneLogit at http://geocities.com/jg_liao

Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Publishing Authors By Initials

JG Liao,KV Chin,

For similar biological factors: biological markers: tumor markers, biological research abstracts see: biological factors: biological markers: tumor markers, biological research

PUBMED ID PMID:

MEDLINE DATE:

Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Journal Published:

PUBLICATION TYPE: Research Support, N.I.H., Extr

Journal: Bioinformatics (Oxford, England)

VOLUME: 23

Page Numbers: 1945-51

Journal Abbreviation: Bioinformatics

ISSN: 1460-2059

DAY: 31

MONTH: 05

YEAR: 2007

Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 9808944

Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Keywords Mesh Terms:

KEYWORDS: Tumor Markers, Biological

MESH TERMS: analysis

Chemical & Substance for Abstract: Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Information

Substance Name: Tumor Markers, Biological

Registry Number: 0

Grant and Affiliation Information for Logistic regression for disease classification using microarray data: model selection in a large p and small n case.

AFFILIATION: Drexel University School of Public Health, Philadelphia, PA 19102, USA. jl544@drexel.edu

Country: England

AGENCY: United States NCI

GRANT: 2P30 CA 72720-04

ACRONYM: CA

MEDLINETA: Bioinformatics

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Logistic regression for disease classification using microarray data: model selection in a large p and small n case Related Publications

• A comparison of DNA copy number profiling platforms.
• Acetylation-dependent signal transduction for type I interferon receptor.
• Altered partition of serum cholesterol and cholesteryl ester in a petroleum ether-ethanol-water system after incubation.
• CHF1/Hey2 plays a pivotal role in left ventricular maturation through suppression of ectopic atrial gene expression.
• Cell therapy in murine atherosclerosis: in vivo imaging with high-resolution helical SPECT.
• Continuing benefit of zoledronic acid in preventing skeletal complications in patients with bone metastases.
• Do religious physicians disproportionately care for the underserved?
• Evaluation of lipid oxidation and oxidative products as affected by pork meat cut, packaging method, and storage time during frozen storage (-10 degrees C).
• Evolution and termination of a femtosecond laser filament in air.
• Following the call: how providers make sense of their decisions to work in faith-based and secular urban community health centers.
• Genome-wide mapping of RELA(p65) binding identifies E2F1 as a transcriptional activator recruited by NF-kappaB upon TLR4 activation.
• Laryngeal nerve monitoring and minimally invasive thyroid surgery: complementary technologies.
• Logistic regression for disease classification using microarray data: model selection in a large p and small n case.
• Obstetric cholestasis in Hong Kong--local experience with eight consecutive cases.
• Parkin-mediated K63-linked polyubiquitination targets misfolded DJ-1 to aggresomes via binding to HDAC6.
• Performance and characteristics of an IR localizing system for radiation therapy.
• Phage immobilized magnetoelastic sensor for the detection of Salmonella typhimurium.
• Predictors of patient selection in bariatric surgery.
• Preparation and properties of electrophoretic microcapsules for electronic paper.
• Provider perceptions of limited health literacy in community health centers.
• Realization of complex onsets by pediatric users of cochlear implants.
• Reprogramming the amino-acid substrate specificity of orthogonal aminoacyl-tRNA synthetases to expand the genetic code of eukaryotic cells.
• Robotics and its applications in stereotactic radiosurgery.
• Scenario of a dirty bomb in an urban environment and acute management of radiation poisoning and injuries.
• Selective enrichment of DJ-1 protein in primate striatal neuronal processes: implications for Parkinson's disease.
• The cost-effectiveness of improving diabetes care in u.s. Federally qualified community health centers.
• Transcription factor CHF1/Hey2 regulates the global transcriptional response to platelet-derived growth factor in vascular smooth muscle cells.
• Trust and reciprocity: foundational principles for human subjects imaging research.
• Two cases of postmaturity-related perinatal mortality in non-local expectant mothers.
• Variation in consonant cluster production by pediatric cochlear implant users.