A greedy-network-based approach for human disease module identification

DOI

10.2991/iceeecs-16.2016.98How to use a DOI?

Keywords

Gene expression, Biological networks, Greedy algorithm, Machine learning, Cancer biology

Abstract

The accurate classification of disease module from gene expression profiles is quite challenging for new biomarkers because of high noise in gene expression measurements and the small sample size [1]. Studies have shown that network-based gene selection is more reliable than individual genes. Because genes related with same or similar disease modules usually reside in the same vicinity of the molecular network [3]. Based on this theory, we propose a greedy-network-based approach for gene identification. In our study, we use this method in a pediatric acute lymphoblastic leukemia (ALL) [4] dataset and a triple-negative breast cancer (TNBC) microarray dataset. The results show our method achieves higher accuracy in the identification of gene makers.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Meng Jin
AU  - Zhiyuan Yang
AU  - Jianwei Lu
AU  - Tianwei Yu
PY  - 2016/12
DA  - 2016/12
TI  - A greedy-network-based approach for human disease module identification
BT  - Proceedings of the 2016 4th International Conference on Electrical & Electronics Engineering and Computer Science (ICEEECS 2016)
PB  - Atlantis Press
SP  - 474
EP  - 478
SN  - 2352-538X
UR  - https://doi.org/10.2991/iceeecs-16.2016.98
DO  - 10.2991/iceeecs-16.2016.98
ID  - Jin2016/12
ER  -