Navigation Links
An entropy-based gene selection method for cancer classification using microarray data

Accurate diagnosis of cancer subtypes remains a challenging problem. Building classifiers based on gene expression data is a promising approach; yet the selection of non-redundant but relevant genes is difficult. The selected gene set should be small enough to allow diagnosis even in regular clinical laboratories and ideally identify genes involved in cancer-specific regulatory pathways. Here an entropy-based method is proposed that selects genes related to the different cancer classes while at the same time reducing the redundancy among the genes.

Results

The present study identifies a subset of features by maximizing the relevance and minimizing the redundancy of the selected genes. A merit called "uncertainty" is employed to measure the relevance and the redundancy of the genes. In order to find a more representative subset of features, an iterative procedure is adopted that incorporates an initial clustering followed by data partitioning and the application of the algorithm to each of the partitions. A leave-one-out approach then selects the most commonly selected genes across all the different runs and the gene selection algorithm is applied again to pare down the list of selected genes until a "minimal" subset is obtained that gives a satisfactory accuracy of classification. The algorithm was applied to three different data sets and the results obtained were compared to work done by others using the same data sets.

This study presents an entropy-based iterative algorithm for selecting genes from microarray data that are able to classify various cancer sub-types with high accuracy. In addition, the feature set obtained is very compact, that is, the redundancy between genes is reduced to a large extent. This implies that classifiers can be built with a smaller subset of genes.


'"/>

Source:BioMed Central


Page: 1

Related biology news :

1. Cornell finds natural selection in humans
2. Natural selection at single gene demonstrated
3. Embryonic selection of sex avoids conceiving blind children
4. Does natural selection drive the evolution of cancer?
5. Pressured by predators, lizards see rapid shift in natural selection
6. Color-blind method opens new doors in DNA sequencing
7. New imaging method gives early indication if brain cancer therapy is effective, U-M study shows
8. Studies reveal methods viruses use to sidestep immune system
9. New methods of gene delivery using lasers
10. Breakthrough method in nanoparticle synthesis paves the way for new pharmaceutical and biomedical applications
11. Shift of weather patterns necessitates rethinking of reforestation methods
Post Your Comments:
*Name:
*Comment:
*Email:


(Date:4/11/2017)... April 11, 2017 No two people ... at the New York University Tandon School of ... have found that partial similarities between prints are ... in mobile phones and other electronic devices can ... The vulnerability lies in the fact that fingerprint-based ...
(Date:4/5/2017)... 2017  The Allen Institute for Cell Science today ... one-of-a-kind portal and dynamic digital window into the human ... first application of deep learning to create predictive models ... and a growing suite of powerful tools. The Allen ... future publicly available resources created and shared by the ...
(Date:4/4/2017)... --  EyeLock LLC , a leader of iris-based identity ... and Trademark Office (USPTO) has issued U.S. Patent No. ... iris image with a face image acquired in sequence ... th issued patent. "The issuance ... multi-modal biometric capabilities that have recently come to market ...
Breaking Biology News(10 mins):
(Date:10/10/2017)... ... October 10, 2017 , ... For the second time in ... STEM Mentoring Award. Representatives of the FirstHand program travelled to Washington, D.C. Tuesday, ... , US2020’s mission is to change the trajectory of STEM education in America ...
(Date:10/10/2017)... ... October 10, 2017 , ... USDM Life Sciences , ... life sciences and healthcare industries, announces a presentation by Subbu Viswanathan and Jennifer ... “Automating GxP Validation for Agile Cloud Platforms,” will present a revolutionary approach to ...
(Date:10/9/2017)... ... 09, 2017 , ... At its national board meeting in North Carolina, ... University’s Departments of Physics and Astronomy, has been selected for membership in ARCS ... for the 2015 Breakthrough Prize in Fundamental physics for the discovery of the accelerating ...
(Date:10/7/2017)... Seattle, WA (PRWEB) , ... ... ... the industry leader in Hi-C-based genomic technologies, launched its ProxiMeta™ Hi-C metagenome ... the ProxiMeta Hi-C kit and accompanying cloud-based bioinformatics software to perform Hi-C ...
Breaking Biology Technology: