We develop a hypergraph neural network (HyGNN), a model that learns the DDIs by generating and using the representation of hyperedges as drugs. HyGNN has an encoder-decoder ar- chitecture. First, we present a novel hypergraph edge encoder to generate the embedding of drugs. Afterward, the pair-wise representations of drugs are passed through decoder functions to predict a binary score for each drug pair that represents whether two drugs interact.

we present a novel heterogeneous graph attention model, HAN-DDI to predict drug-drug interactions. We create a heterogeneous network of drugs with different biological entities. Then, we develop a heterogeneous graph attention network to learn DDIs using relations of drugs with other entities. It consists of an attention-based heterogeneous graph node encoder for obtaining drug node representations and a decoder for predicting drug-drug interactions. Further, we utilize comprehensive experiments to evaluate of our model and to compare it with state-of-the-art models.

We propose a new method for DDI prediction where we learn the representation of drugs by considering only drugs’ chemical structures and their similarities. We consider two drugs to be similar if they have similar functional sub-structure (i.e., functional groups). Instead of using whole chemical structures of drugs to measure their similarities, we use frequent substructures in them.

We design a heterogeneous information network (HIN) to model relations between these entities. Afterward, we extract the rich semantic relationships among these entities using different meta-path-based topological features. An extensive set of features are fed to different classifiers.

We propose a novel Network Embedding method, NECL, to generate embedding more efficiently or effectively. Our goal is to answer the following two questions: 1) Does the network Compression significantly boost learning? 2) Does network compression improve the quality of the representation? For these goals, first, we propose a novel graph compression method based on the neighborhood similarity that compresses the input graph to a smaller graph with incorporating local proximity of its vertices into super-nodes; second, we employ the compressed graph for network embedding instead of the original large graph to bring down the embedding cost and also to capture the global structure of the original graph; third, we refine the embeddings from the compressed graph to the original graph.