• Corpus ID: 220055668

Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction

  title={Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction},
  author={Yunsheng Bai and Ken Gu and Yizhou Sun and Wei Wang},
We introduce Bi-GNN for modeling biological link prediction tasks such as drug-drug interaction (DDI) and protein-protein interaction (PPI). Taking drug-drug interaction as an example, existing methods using machine learning either only utilize the link structure between drugs without using the graph representation of each drug molecule, or only leverage the individual drug compound structures without using graph structure for the higher-level DDI graph. The key idea of our method is to… 

Figures and Tables from this paper

Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction

A new method, multi-view graph contrastive representation learning for drug-drug interaction prediction, MIRACLE, to capture inter-view molecule structure and intra-view interactions between molecules simultaneously, which outperforms the state-of-the-art DDI prediction models consistently.

Multi-type feature fusion based on graph neural network for drug-drug interaction prediction

A multi-type feature fusion model based on graph neural network model (MFFGNN) for DDI prediction is proposed, which can effectively fuse the topological information in molecular graphs, the interaction information between drugs and the local chemical context in SMILES sequences.

Hierarchical Graph Representation Learning for the Prediction of Drug-Target Binding Affinity

A novel hierarchical graph representation learning model for the drug-target binding affinity prediction, namely HGRL-DTA is proposed, which outperforms the state-of-the-art models and shows better model generalization among all the scenarios.

HyGNN: Drug-Drug Interaction Prediction via Hypergraph Neural Network

This paper proposes a novel Hypergraph Neural Network model based on only the SMILES string of drugs, available for any drug, for the DDI prediction problem, and develops HyGNN consisting of a novel attention-based hypergraph edge encoder to get the representation of drugs as hyperedges and a decoder to predict the interactions between drug pairs.

DeSIDE-DDI: interpretable prediction of drug-drug interactions using drug-induced gene expressions

Using drug-induced gene expression signatures followed by gating and translating embedding can increase DDI prediction accuracy while providing model interpretability, which is competitively very accurate and outperforms other state-of-the-art methods.

Graph Neural Networks for Molecules

This review introduces GNNs and their various applications for small organic molecules and summarizes the recent development of self-supervised learning for molecules withGNNs.

A Unified View of Relational Deep Learning for Polypharmacy Side Effect, Combination Synergy, and Drug-Drug Interaction Prediction

A unified theoretical view of relational machine learning models which can address polypharmacy side effect identification, drug-drug interaction prediction and combination therapy design tasks is presented.

A Unified View of Relational Deep Learning for Drug Pair Scoring

A unified theoretical view of relational machine learning models which can address polypharmacy side effect identification, drug-drug interaction prediction, and combination therapy design tasks is presented.

Detecting Drug-Drug Interactions in COVID-19 Patients

The FAERS database, along with informatics approaches, provides a novel way to select candidate drug-drug pairs to be examined in COVID-19 patients and can be candidate DDIs for clinical trial hypotheses.

Deep learning in drug discovery: an integrative review and future challenges

A systematic Literature review (SLR) that integrates the recent DL technologies and applications in drug discovery Including, drug–target interactions (DTIs), drug–drug similarity interactions (DDIs, drug sensitivity and responsiveness, and drug-side effect predictions.



Graph convolutional networks for computational drug development and discovery

This survey provides a systematic review on the emerging field of graph convolutional networks and their applications in drug discovery and molecular informatics and describes the existing applications through four perspectives: molecular property and activity prediction, interaction prediction, synthesis prediction and de novo drug design.

Modeling polypharmacy side effects with graph convolutional networks

Decagon is presented, an approach for modeling polypharmacy side effects that can predict the exact side effect, if any, through which a given drug combination manifests clinically, and is developed specifically to handle such multimodal graphs with a large number of edge types.

Protein Interface Prediction using Graph Convolutional Networks

We consider the prediction of interfaces between proteins, a challenging problem with important applications in drug discovery and design, and examine the performance of existing and newly proposed

Drug-drug interaction through molecular structure similarity analysis

A new methodology applicable on a large scale that identifies novel DDIs based on molecular structural similarity to drugs involved in established DDIs that allows the investigation of large numbers of drugs, and helps highlight the etiology of DDI.

Drug Repurposing Based on Drug–Drug Interaction

This study demonstrates the feasibility of drug repurposing based on drug–drug interaction data by employing similarity of drug interaction to infer similarity of the physiological effects or targets for the drugs.

Graph Matching Networks for Learning the Similarity of Graph Structured Objects

This paper proposes a novel Graph Matching Network model that, given a pair of graphs as input, computes a similarity score between them by jointly reasoning on the pair through a new cross-graph attention-based matching mechanism.

Molecular graph convolutions: moving beyond fingerprints

Molecular graph convolutions are described, a machine learning architecture for learning from undirected graphs, specifically small molecules, that represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

DrugCombDB: a comprehensive database of drug combinations toward the discovery of combinatorial therapy

This paper presents DrugCombDB, a comprehensive database devoted to the curation of drug combinations from various data sources, which includes 448 555 drug combinations derived from HTS assays, covering 2887 unique drugs and 124 human cancer cell lines.

PRISM: protein-protein interaction prediction by structural matching.

Prism (protein interactions by structural matching) is a system that employs a novel prediction algorithm for protein-protein interactions. It adopts a bottom-up approach that combines structure and

Comparing Graph Representations of Protein Structure for Mining Family-Specific Residue-Based Packing Motifs

It is found that graphs based on almost-Delaunay edges significantly reduce the number of edges in the graph representation and hence present computational advantage, yet the patterns extracted from such graphs have a biological interpretation approximately equivalent to that of those extracted from distance based graphs.