Learning on Weighted Hypergraphs to Integrate Protein Interactions and Gene Expressions for Cancer Outcome Prediction

By TaeHyun Hwang, Ze Tian, Rui Kuang, Jean-Pierre A Kocher. 2008

81 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

EgoNet: identification of human disease ego-network modules (2014, methodology): “To date, many computational methods have been developed to integrate gene expression profiles with protein-protein interaction maps or pathway databases, with the goal of identifying significant subnetwork markers for predicting biological or clinical outcomes [10-18].”
Visual Classification by ℓ1-Hypergraph Modeling (2015, methodology): “Among these methods, hypergraph learning [22], [24], as”
Network-based machine learning and graph theory algorithms for precision oncology (2017, methodology): “In the hypergraph formulation introduced in the papers, 39, 41 the gene expression data are represented as weighted hyperedges on the patient nodes, and a graph Laplacian on the hypergraph can be introduced for semi-supervised learning on the patient samples.”
Hypergraph Neural Networks (2018, background): “In (Hwang et al. 2008), the correlation among hyperedges is further explored by a assumption that highly correlated hyperedges should have similar weights.”
Protein Networks as Logic Functions in Development and Cancer (2011, background): “74 (Figures 4A, S5A), which was better by 3–6% than previously reported results for a variety of standard and network/pathway-based classification methods [24,25,27].”