Abstract

Network analysis has been shown to be an effective and cheap way to screen genes that are associated to diseases and chemicals. The identification of features that are used to order potentially related genes is key to do this job. Though many network models and structure based features have been proposed in the literature, they do not perform well enough for such gene prioritization task, especially when the heterogeneity of such networks is taken account. In this paper, a type of heterogenous network called Generalized Bi-relational Network (GBN) is formalized. A series of path based features on GBN are defined. Though some of the features have been used in other literature, it is the first time to evaluate them in both supervised and unsupervised learning models. The experiment on real chemical-disease-gene networks shows that the features proposed in this paper gain promising performance in both supervised and unsupervised framework.

Original languageEnglish (US)
Title of host publicationProceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages129-132
Number of pages4
ISBN (Electronic)9781509019151
DOIs
StatePublished - Sep 13 2016
Event20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016 - Nanchang, China
Duration: May 4 2016May 6 2016

Other

Other20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016
CountryChina
CityNanchang
Period5/4/165/6/16

Fingerprint

Genes
Unsupervised learning
Supervised learning
Electric network analysis
Prioritization
Gene
Experiments

Keywords

  • feature
  • gene prioritization
  • Generalized Bi-relation Network(GBN)
  • network analysis
  • path

ASJC Scopus subject areas

  • Management Information Systems
  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Liu, Y., Tong, H., Lei, X., & Tang, Y. (2016). Network based models and path based features for gene prioritization. In Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016 (pp. 129-132). [7565976] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCWD.2016.7565976

Network based models and path based features for gene prioritization. / Liu, Yuechang; Tong, Hanghang; Lei, Xie; Tang, Yong.

Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 129-132 7565976.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, Y, Tong, H, Lei, X & Tang, Y 2016, Network based models and path based features for gene prioritization. in Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016., 7565976, Institute of Electrical and Electronics Engineers Inc., pp. 129-132, 20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016, Nanchang, China, 5/4/16. https://doi.org/10.1109/CSCWD.2016.7565976
Liu Y, Tong H, Lei X, Tang Y. Network based models and path based features for gene prioritization. In Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 129-132. 7565976 https://doi.org/10.1109/CSCWD.2016.7565976
Liu, Yuechang ; Tong, Hanghang ; Lei, Xie ; Tang, Yong. / Network based models and path based features for gene prioritization. Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 129-132
@inproceedings{6abeeec76810441d8daee8ae7254e60c,
title = "Network based models and path based features for gene prioritization",
abstract = "Network analysis has been shown to be an effective and cheap way to screen genes that are associated to diseases and chemicals. The identification of features that are used to order potentially related genes is key to do this job. Though many network models and structure based features have been proposed in the literature, they do not perform well enough for such gene prioritization task, especially when the heterogeneity of such networks is taken account. In this paper, a type of heterogenous network called Generalized Bi-relational Network (GBN) is formalized. A series of path based features on GBN are defined. Though some of the features have been used in other literature, it is the first time to evaluate them in both supervised and unsupervised learning models. The experiment on real chemical-disease-gene networks shows that the features proposed in this paper gain promising performance in both supervised and unsupervised framework.",
keywords = "feature, gene prioritization, Generalized Bi-relation Network(GBN), network analysis, path",
author = "Yuechang Liu and Hanghang Tong and Xie Lei and Yong Tang",
year = "2016",
month = "9",
day = "13",
doi = "10.1109/CSCWD.2016.7565976",
language = "English (US)",
pages = "129--132",
booktitle = "Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Network based models and path based features for gene prioritization

AU - Liu, Yuechang

AU - Tong, Hanghang

AU - Lei, Xie

AU - Tang, Yong

PY - 2016/9/13

Y1 - 2016/9/13

N2 - Network analysis has been shown to be an effective and cheap way to screen genes that are associated to diseases and chemicals. The identification of features that are used to order potentially related genes is key to do this job. Though many network models and structure based features have been proposed in the literature, they do not perform well enough for such gene prioritization task, especially when the heterogeneity of such networks is taken account. In this paper, a type of heterogenous network called Generalized Bi-relational Network (GBN) is formalized. A series of path based features on GBN are defined. Though some of the features have been used in other literature, it is the first time to evaluate them in both supervised and unsupervised learning models. The experiment on real chemical-disease-gene networks shows that the features proposed in this paper gain promising performance in both supervised and unsupervised framework.

AB - Network analysis has been shown to be an effective and cheap way to screen genes that are associated to diseases and chemicals. The identification of features that are used to order potentially related genes is key to do this job. Though many network models and structure based features have been proposed in the literature, they do not perform well enough for such gene prioritization task, especially when the heterogeneity of such networks is taken account. In this paper, a type of heterogenous network called Generalized Bi-relational Network (GBN) is formalized. A series of path based features on GBN are defined. Though some of the features have been used in other literature, it is the first time to evaluate them in both supervised and unsupervised learning models. The experiment on real chemical-disease-gene networks shows that the features proposed in this paper gain promising performance in both supervised and unsupervised framework.

KW - feature

KW - gene prioritization

KW - Generalized Bi-relation Network(GBN)

KW - network analysis

KW - path

UR - http://www.scopus.com/inward/record.url?scp=84991730816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991730816&partnerID=8YFLogxK

U2 - 10.1109/CSCWD.2016.7565976

DO - 10.1109/CSCWD.2016.7565976

M3 - Conference contribution

SP - 129

EP - 132

BT - Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -