Farhan Tanvir
Farhan Tanvir
Home
Experience
Publications
Contact
1
HyGNN: Drug-Drug Interaction Prediction via Hypergraph Neural Network
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.
Khaled Mohammed Saifuddin
,
Briana Bumgardner
,
Farhan Tanvir and Esra Akbas
PDF
DOI
DDI Prediction via Heterogeneous Graph Attention Networks
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.
Farhan Tanvir
,
Khaled Mohammed Saifuddin and Esra Akbas
PDF
DOI
Drug-Drug Interaction Prediction: a Purely SMILES Based Approach
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.
Bri Bumgardner
,
Farhan Tanvir
,
Khaled Mohammed Saifuddin and Esra Akbas
PDF
Cite
DOI
Predicting Drug-Drug Interactions Using Meta-path Based Similarities
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.
Farhan Tanvir
,
Muhammad Ifte Khairul Islam and Esra Akbas
PDF
Cite
DOI
Cite
×