Generalized Query-Based Active Learning to Identify Differentially Methylated Regions in DNA

Md Muksitul Haque; Lawrence B Holder; Michael K Skinner; Diane J Cook

doi:10.1109/TCBB.2013.38

Back

Generalized Query-Based Active Learning to Identify Differentially Methylated Regions in DNA

Accepted manuscript

Open access

Generalized Query-Based Active Learning to Identify Differentially Methylated Regions in DNA

Md Muksitul Haque, Lawrence B Holder, Michael K Skinner and Diane J Cook

IEEE/ACM transactions on computational biology and bioinformatics, Vol.10(3), pp.632-644

05/2013

DOI: https://doi.org/10.1109/TCBB.2013.38

Handle:

https://hdl.handle.net/2376/114241

PMCID: PMC8248446

PMID: 24091397

Files and links (1)

pdf

Generalized Query-Based Active Learning to Identify Differentially Methylated Regions in DNA1.74 MBDownload View

Open Access

Abstract

Training

Learning systems

Uncertainty

Accuracy

Active learning

DNA methylation

generalized query

DNA

Bioinformatics

Active learning is a supervised learning technique that reduces the number of examples required for building a successful classifier, because it can choose the data it learns from. This technique holds promise for many biological domains in which classified examples are expensive and time-consuming to obtain. Most traditional active learning methods ask very specific queries to the Oracle (e.g., a human expert) to label an unlabeled example. The example may consist of numerous features, many of which are irrelevant. Removing such features will create a shorter query with only relevant features, and it will be easier for the Oracle to answer. We propose a generalized query-based active learning (GQAL) approach that constructs generalized queries based on multiple instances. By constructing appropriately generalized queries, we can achieve higher accuracy compared to traditional active learning methods. We apply our active learning method to find differentially DNA methylated regions (DMRs). DMRs are DNA locations in the genome that are known to be involved in tissue differentiation, epigenetic regulation, and disease. We also apply our method on 13 other data sets and show that our method is better than another popular active learning technique.

Metrics

1 File views/ downloads

14 Record Views

Details

Title: Generalized Query-Based Active Learning to Identify Differentially Methylated Regions in DNA
Creators: Md Muksitul Haque - Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
Lawrence B Holder - Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
Michael K Skinner - Sch. of Biol. Sci., Washington State Univ., Pullman, WA, USA
Diane J Cook - Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
Publication Details: IEEE/ACM transactions on computational biology and bioinformatics, Vol.10(3), pp.632-644
Academic Unit: Biological Sciences, School of; Electrical Engineering and Computer Science, School of
Publisher: IEEE
Identifiers: 99900547688301842
Language: English
Resource Type: Accepted manuscript