| Learning a predictive model for growth inhibition from the NCI DTP human tumor cell line screening data: does gene expression make a difference? | |
| | |
MedLine Citation:
|
PMID: 17094272 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
We address the problem of learning a predictive model for growth inhibition from the NCI DTP human tumor cell line screening data. Extending the classical Quantitative Structure Activity Relationship paradigm, we investigate whether including gene expression data leads to a statistically significant improvement of prediction quality. Our analysis shows that the straightforward approach of including individual gene expression as features does not necessarily improve, but on the contrary, may degrade performance significantly. When gene expression information is aggregated, for instance by features representing the correlation with reference cell lines, performance can be improved significantly. Further improvements may be expected if the learning task is structured by grouping features and instances. |
| | |
Authors:
|
Lothar Richter; Ulrich Rückert; Stefan Kramer |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Volume: - ISSN: 1793-5091 ISO Abbreviation: Pac Symp Biocomput Publication Date: 2006 |
Date Detail:
|
Created Date: 2006-11-10 Completed Date: 2007-01-03 Revised Date: 2007-09-12 |
Medline Journal Info:
|
Nlm Unique ID: 9711271 Medline TA: Pac Symp Biocomput Country: Singapore |
Other Details:
|
Languages: eng Pagination: 596-607 Citation Subset: IM |
Affiliation:
|
Institut für Informatik 112, Technische Universität München, Bolzmannstr. 3, Garching b. München, Germany. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Cell Line, Tumor Computational Biology Databases, Genetic Drug Screening Assays, Antitumor / statistics & numerical data* Gene Expression Humans Models, Biological* Pharmacogenetics / statistics & numerical data* |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Risk factor interactions and genetic effects associated with post-operative atrial fibrillation.
Next Document: Physician employment: this time around, give finance a leading role.