Transfer learning of classification rules for biomarker discovery and verification from molecular profiling studies

9Citations
Citations of this article
74Readers
Mendeley users who have this article in their library.

Abstract

We present a novel framework for integrative biomarker discovery from related but separate data sets created in biomarker profiling studies. The framework takes prior knowledge in the form of interpretable, modular rules, and uses them during the learning of rules on a new data set. The framework consists of two methods of transfer of knowledge from source to target data: transfer of whole rules and transfer of rule structures. We evaluated the methods on three pairs of data sets: one genomic and two proteomic. We used standard measures of classification performance and three novel measures of amount of transfer. Preliminary evaluation shows that whole-rule transfer improves classification performance over using the target data alone, especially when there is more source data than target data. It also improves performance over using the union of the data sets. © 2011 Elsevier Inc.

Cite

CITATION STYLE

APA

Ganchev, P., Malehorn, D., Bigbee, W. L., & Gopalakrishnan, V. (2011). Transfer learning of classification rules for biomarker discovery and verification from molecular profiling studies. Journal of Biomedical Informatics, 44(SUPPL. 1). https://doi.org/10.1016/j.jbi.2011.04.009

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free