Prediction of disease genes using tissue-specified gene-gene network
By Gamage Upeksha Ganegoda, Jianxin Wang, Fang-Xiang Wu, Min Li. 2014
26 citations recorded by the source corpus.
BackgroundTissue specificity is an important aspect of many genetic diseases in the context of genetic disorders as the disorder affects only few tissues. Therefore tissue specificity is important in identifying disease-gene associations. Hence this paper seeks to discuss the impact of using tissue specificity in predicting new disease-gene associations and how to use tissue specificity along with phenotype information for a particular disease.MethodsIn order to find out the impact of using tissue specificity for predicting new disease-gene associations, this study proposes a novel method called tissue-specified genes to construct tissues-specific gene-gene networks for different tissue samples. Subsequently, these networks are used with phenotype details to predict disease genes by using Katz method. The proposed method was compared with three other tissue-specific network construction methods in order to check its effectiveness. Furthermore, to check the possibility of using tissue-specific gene-gene network instead of generic protein-protein network at all time, the results are compared with three other methods.ResultsIn terms of leave-one-out cross validation, calculation of the mean enrichment and ROC curves indicate that the proposed approach outperforms existing network construction methods. Furthermore tissues-specific gene-gene networks make a more positive impact on predicting disease-gene associations than generic protein-protein interaction networks.ConclusionsIn conclusion by integrating tissue-specific data it enabled prediction of known and unknown disease-gene associations for a particular disease more effectively. Hence it is better to use tissue-specific gene-gene network whenever possible. In addition the proposed method is a better way of constructing tissue-specific gene-gene networks.
Subfields: Genetics, Molecular Biology, Computational Biology & Bioinformatics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Genetics
In Molecular Biology
- Marinka Zitnik
- Jure Leskovec
- Petar Velickovic
- William L. Hamilton
- Rex Ying
- Stephan Günnemann
- Xinchao Wang
- Aleksandar Bojchevski
In Computational Biology & Bioinformatics
- Jure Leskovec
- Marinka Zitnik
- Petar Velickovic
- Yiding Yang
- Xinchao Wang
- Bernard Ghanem
- Guohao Li
- Pietro Lio'
Citations in the corpus
- Predicting multicellular function through multi-layer tissue networks (2017, background): “(3) Third, only few computational approaches (Magger et al., 2012; Guan et al., 2012; Ganegoda et al., 2014; Antanaviciute et al., 2015) used tissue-specific information to identify novel genes and relationships between genes.”