Imbalanced Class Learning in Epigenetics

M. Muksitul Haque; Michael K Skinner; Lawrence B Holder

doi:10.1089/cmb.2014.0008

Back

Imbalanced Class Learning in Epigenetics

Accepted manuscript

Open access

Imbalanced Class Learning in Epigenetics

M. Muksitul Haque, Michael K Skinner and Lawrence B Holder

Journal of computational biology, Vol.21(7), pp.492-507

07/01/2014

DOI: https://doi.org/10.1089/cmb.2014.0008

Handle:

https://hdl.handle.net/2376/116162

PMCID: PMC4082351

PMID: 24798423

Files and links (2)

pdf

Imbalanced class learning in epigenetics444.30 kBDownload View

Open Access

url

https://doi.org/10.1089/cmb.2014.0008View

Published (Version of record) Open

Abstract

computational molecular biology

machine earning

Epigenetics

Genomics

DNA

In machine learning, one of the important criteria for higher classification accuracy is a balanced dataset. Datasets with a large ratio between minority and majority classes face hindrance in learning using any classifier. Datasets having a magnitude difference in number of instances between the target concept result in an imbalanced class distribution. Such datasets can range from biological data, sensor data, medical diagnostics, or any other domain where labeling any instances of the minority class can be time-consuming or costly or the data may not be easily available. The current study investigates a number of imbalanced class algorithms for solving the imbalanced class distribution present in epigenetic datasets. Epigenetic (DNA methylation) datasets inherently come with few differentially DNA methylated regions (DMR) and with a higher number of non-DMR sites. For this class imbalance problem, a number of algorithms are compared, including the TAN+AdaBoost algorithm. Experiments performed on four epigenetic datasets and several known datasets show that an imbalanced dataset can have similar accuracy as a regular learner on a balanced dataset .

Metrics

1 File views/ downloads

5 Record Views

See more details

Details

Title: Imbalanced Class Learning in Epigenetics
Creators: M. Muksitul Haque - Center for Reproductive Biology, School of Biological Sciences
Michael K Skinner - Center for Reproductive Biology, School of Biological Sciences
Lawrence B Holder - School of Electrical Engineering and Computer Science
Publication Details: Journal of computational biology, Vol.21(7), pp.492-507
Academic Unit: Biological Sciences, School of; Electrical Engineering and Computer Science, School of
Publisher: Mary Ann Liebert, Inc; 140 Huguenot Street, 3rd FloorNew Rochelle, NY 10801USA
Identifiers: 99900547743901842
Language: English
Resource Type: Accepted manuscript