Abstract
An iterative computational scientific discovery approach is proposed and applied to gene expression data for resectable lung adenocarcinoma patients. We use genes learned from the C5.0 rule induction algorithm, clinical features and prior knowledge derived from a network of interacting genes as represented in a database obtained with PathwayAssist to discover markers for prognosis in the gene expression data. This is done in an iterative fashion with machine learning techniques seeding the prior knowledge. This research illustrates the utility of combining signaling networks and machine learning techniques to produce simple prognostic classifiers.
Original language | English (US) |
---|---|
Pages (from-to) | 256-260 |
Number of pages | 5 |
Journal | AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium |
State | Published - 2005 |
Externally published | Yes |
ASJC Scopus subject areas
- General Medicine