Genome-wide inferring gene-phenotype relationship by walking on the heterogeneous network

By Yongjin Li, Jagdish Chandra Patra. Bioinform., 2010

392 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/59a5da1f1138c7199daa22a52d8ab6db3c9ec937

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

Citations in the corpus

Prediction of disease genes using tissue-specified gene-gene network (2014, positive): “RWRH performs a random walk on a heterogeneous network of gene interactions and human diseases [19].”
Mining breast cancer genes with a network based noise-tolerant approach (2013, methodology): “Random walk based methods had been shown to produce good performance [18,23,29-31] in gene ranking.”
Inductive matrix completion for predicting gene–disease associations (2014, methodology): “OMIM phenotypes have become the standard data set for the evaluation of prediction of gene–disease associations (Karni et al., 2009; K €ohler et al. 2008; Li and Patra, 2010; Mordelet and Vert, 2011; Singh-Blom et al., 2013; Vanunu et al., 2010; Wu et al., 2008).”
Methods for the integration of multi-omics data: mathematical aspects (2016, methodology): “An example of application of heterogeneous network for modeling genephenotype networks was presented by Li and Patra [50].”
Network propagation: a universal amplifier of genetic associations (2017, background): “Multiple researchers 71–77 aimed to predict causal genes for a disease by starting from known causal genes of similar diseases (known as ‘seeds’) and applying network propagation to prioritize genes based on their proximity to the prior seed set.”
A review on machine learning principles for multi-view biological data integration (2016, methodology): “Random walk methods have been applied on either two-relational heterogeneous networks (such as gene–phenotype associations [88], drug–target interactions [89] and miRNA–disease associations [90, 91]) or multi-relational heterogeneous networks (for example, drug–disease associations [92]) to infer no”