Predicting Associations between circRNAs and Drug Sensitivity using Heterogeneous Graphs and Graph Attention Networks.
Xiaojun XiaoYurong QianZhijian HuangRongtao ZhengLei DengPublished in: BIBM (2023)
Keyphrases
- graph structures
- average degree
- real world graphs
- edge weights
- highly connected
- graph theory
- graph representation
- graph layout
- graph structure
- community discovery
- dynamic networks
- graph mining
- weighted graph
- graph databases
- random graphs
- directed graph
- graph matching
- small world
- graph theoretic
- complex networks
- graph model
- social graphs
- fully connected
- graph clustering
- labeled graphs
- heterogeneous networks
- spanning tree
- social networks
- graph classification
- graph data
- protein interaction networks
- graph construction
- real world social networks
- adjacency matrix
- graph properties
- degree distribution
- betweenness centrality
- undirected graph
- densely connected
- connected components
- graph partitioning
- network analysis
- bipartite graph
- graph representations
- graph search
- small world networks
- minimum spanning tree
- dynamic graph
- graph theoretical
- graph isomorphism
- social network analysis
- chemical compounds
- real world networks
- graph kernels
- community detection
- directed edges
- structural pattern recognition
- random walk
- subgraph isomorphism
- graph mining algorithms
- massive graphs
- network structure
- dense subgraphs
- structured data
- reachability queries
- finding the shortest path
- association rules
- query graph
- series parallel
- scale free
- clustering coefficient
- power law
- functional modules
- neighborhood graph
- drug discovery
- web graph
- directed acyclic graph
- link prediction
- maximum common subgraph