Showing items 1 - 3 of 3

Disease gene prediction based on heterogeneous probabilistic hypergraph ranking

- Ding, Feng, Kong, Xiangjie, Zhao, Zhehuan, Xia, Feng, Liu, Anfu, Bai, Chenxu, Xu, Bo, Liu, Xiaoxia, Sang, Shengtian, Lin, Hongfei, Yang, Zhihao, Wang, Jian

  • Authors: Ding, Feng , Kong, Xiangjie , Zhao, Zhehuan , Xia, Feng , Liu, Anfu , Bai, Chenxu , Xu, Bo , Liu, Xiaoxia , Sang, Shengtian , Lin, Hongfei , Yang, Zhihao , Wang, Jian
  • Date: 2019
  • Type: Text , Conference proceedings
  • Relation: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); San Diego, CA, USA; 18-21 November 2019 p. 2021-2028
  • Full Text: false
  • Reviewed:
  • Description: In order to save time and cost, many disease gene prediction methods have been proposed in recent years. However, the traditional network model uses a binary relationship to represent the relationship between different proteins or gene molecules and phenotypes, which leads to the loss of information. Recently, hypergraph shows that it can overcome this loss of information to some extent and preserve the multivariate relationship, so we transformed the disease gene prediction problem into the problem of ranking the multivariate-relationship object. In this paper, we propose a method of Heterogeneous Probabilistic Hypergraph Ranking (HPHR) to predict disease genes. Firstly, fix a graph centroid for each hyperedge and according to different associations, and add other nodes related to the graph centroid to hyperedges with a certain probability. Then transform the problem of predicting disease genes into the problem of ranking heterogeneous objects, and the candidate genes are sorted by hypergraph ranking. The method is then applied to the integrated disease gene network. Compared with other prediction methods achieved better results, which was verified by this experiment.

Effective leadership behaviours to manage people issues of cross border mergers and aquisitions in China

- Wang, Jian

  • Authors: Wang, Jian
  • Date: 2015
  • Type: Text , Thesis , PhD
  • Full Text:
  • Description: The aim of this research is to identify the effective leadership behaviours in managing people issues of a British-Chinese cross border acquisition case study in China. There are three areas involved in this study: people issues in mergers and acquisitions (M&As), cross culture differences and cross culture leadership. The knowledge gap identified from past research is that there appears to be no in-depth empirical study to date on an integrated model of the three areas noted above to have a holistic understanding of their influence on the success or failure of M&As, especially in the context of cross border M&As in China. This is the focus of this research. The objectives of this research are to identify how leaders have managed cross culture issues, communications, employees’ resistance, stress and trust in a Western-Chinese cross border acquisition as well as the perceived effectiveness of these leadership behaviours both from the perspectives of Chinese employees and the western managers. The conceptual framework of this research adopted and built on the theoretical model of Project GLOBE. Findings from this study suggest a ‘multiplier’ effect with impact across all the people issues in this cross border acquisition, which means that when one people issue is not managed well by the leadership team, other people issues are triggered. The outcome of this acquisition was influenced by the integrated and holistic effect of all the people issues. In this study, management of people issues in a cross-culture environment was fundamental. There are seven culture dimensions proposed by this study to measure the organisational culture differences pre- and post-acquisition as influenced by both Chinese and British cultures. Specific cultural behaviours related to the proposed seven culture dimensions were also identified. Organisation culture clash was found with the post-acquisition organisation culture which influenced the leadership behaviours in managing the people issues and the perceived effectiveness of the leadership behaviours. This study contributes to existing knowledge by adding the integrated dimension of effective leadership behaviours in managing people issues in a cross culture context of M&As in China as well as extending the theoretical model of Project GLOBE. The practical learning from this study could help leaders in future M&As to take effective actions in managing people issues to improve the success rate of cross border M&As in China which can potentially contribute to the economic development of China and other developing countries.
  • Description: Doctor of Philosophy

Protein complexes detection based on global network representation learning

- Xu, Bo, Li, Kun, Liu, Xiaoxia, Liu, Delong, Zhang, Yijia, Lin, Hongfei, Yang, Zhihao, Wang, Jian, Xia, Feng

  • Authors: Xu, Bo , Li, Kun , Liu, Xiaoxia , Liu, Delong , Zhang, Yijia , Lin, Hongfei , Yang, Zhihao , Wang, Jian , Xia, Feng
  • Date: 2018
  • Type: Text , Conference proceedings
  • Relation: 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Madrid, Spain; 3-6 Dec. 2018 p. 210-213
  • Full Text: false
  • Reviewed:
  • Description: Detecting protein complexes from protein-protein interaction (PPI) networks allows biologists reveal the principle of cellular organization and functions. Existing computational methods try to incorporate biological evidence to enhance the quality of predicted complexes. However, it is still a challenge to integrate biological information into complexes discovery process under a unified framework. Recently, network embedding methods showed their effectiveness in graph data analysis tasks. It provides a framework for incorporating both network structure and additional node attribute information. This salient feature is particularly desirable in the context of protein complexes identification. However, none of the existing network embedding methods take node attribute proximity and high-order structure proximity into account at the same time. In this paper, we propose a novel global network embedding method, which preserves global network structure and biological information. We utilize this global representation learning method to learn vector representation for proteins. Then, we use a seed-extension clustering method to discover overlapping protein complexes with the embedding results. This novel protein complexes detection method we called GLONE. Evaluated on five real yeast PPI networks, our method outperforms the competing algorithms in terms of different evaluation metrics.
  • 1