A machine learning heuristic to identify biologically relevant and minimal biomarker panels from omics data
Open Access
- 15 January 2015
- journal article
- Published by Springer Nature in BMC Genomics
- Vol. 16 (S1) , S2
Abstract
Investigations into novel biomarkers using omics techniques generate large amounts of data. Due to their size and numbers of attributes, these data are suitable for analysis with machine learning methods. A key component of typical machine learning pipelines for omics data is feature selection, which is used to reduce the raw high-dimensional data into a tractable number of features. Feature selection needs to balance the objective of using as few features as possible, while maintaining high predictive power. This balance is crucial when the goal of data analysis is the identification of highly accurate but small panels of biomarkers with potential clinical utility. In this paper we propose a heuristic for the selection of very small feature subsets, via an iterative feature elimination process that is guided by rule-based machine learning, called RGIFE (Rule-guided Iterative Feature Elimination). We use this heuristic to identify putative biomarkers of osteoarthritis (OA), articular cartilage degradation and synovial inflammation, using both proteomic and transcriptomic datasets.Keywords
This publication has 91 references indexed in Scilit:
- Osteoarthritis: A disease of the joint as an organArthritis & Rheumatism, 2012
- Functional Network Construction in Arabidopsis Using Rule-Based Machine Learning on Large-Scale Data SetsThe Plant Cell, 2011
- High throughput proteomic analysis of the secretome in an explant model of articular cartilage inflammationJournal of Proteomics, 2011
- Dhx34 and Nbas function in the NMD pathway and are required for embryonic development in zebrafishNucleic Acids Research, 2011
- Single-nucleotide polymorphism in the hyaluronan and proteoglycan link protein 1 (HAPLN1) gene is associated with spinal osteophyte formation and disc degeneration in Japanese womenEuropean Spine Journal, 2010
- ANCCA, an estrogen-regulated AAA+ ATPase coactivator for ERα, is required for coregulator occupancy and chromatin modificationProceedings of the National Academy of Sciences, 2007
- Molecular cloning and characterization of the human RNase , an ortholog of Cc RNaseNucleic Acids Research, 2007
- OsteoarthritisJournal of Cellular Physiology, 2007
- Empirical Statistical Model To Estimate the Accuracy of Peptide Identifications Made by MS/MS and Database SearchAnalytical Chemistry, 2002
- Biomarkers and surrogate endpoints: Preferred definitions and conceptual frameworkClinical Pharmacology & Therapeutics, 2001