How ImageDDI Boosts Drug‑Drug Interaction Prediction with Motif Sequences and Molecular Images

The ImageDDI framework, introduced by a team from Hunan University, combines molecular motif sequences with 2D/3D molecular images using a Transformer encoder and adaptive feature fusion, achieving significantly higher accuracy and macro‑F1 scores than existing methods on multiple DDI datasets, while also providing interpretable visual explanations.

Deep LearningDrug InteractionImage Fusion

0 likes · 10 min read

How ImageDDI Boosts Drug‑Drug Interaction Prediction with Motif Sequences and Molecular Images

DataFunTalk

Jan 27, 2023 · Artificial Intelligence

GNN for Science: Foundations, Applications, and Recent Advances in Equivariant Graph Neural Networks

This article reviews the role of graph neural networks in AI for science, covering background, the evolution of GNN models, applications in physics and biomedicine, recent advances in Euclidean equivariant GNNs, and the authors' own contributions such as GMN and GROVER, concluding with key distinctions between traditional GNNs and science‑focused approaches.

AI for ScienceMolecular Representationequivariant GNN

0 likes · 16 min read

GNN for Science: Foundations, Applications, and Recent Advances in Equivariant Graph Neural Networks

DataFunSummit

Feb 22, 2022 · Artificial Intelligence

Graph Pretraining Techniques for Molecular Representation and Their Applications in Drug Discovery

This article reviews the motivation, methods, and results of graph-based self‑supervised pretraining for molecular data, introduces the ChemRL‑GEM model that incorporates 3‑D structural information, and demonstrates its superior performance on ADMET, affinity prediction, and benchmark competitions using the PaddleHelix platform.

AIChemistryMolecular Representation

0 likes · 18 min read

Graph Pretraining Techniques for Molecular Representation and Their Applications in Drug Discovery