基於 N-gram 分子圖以及新穎圖神經網路架構之快速藥物篩選平台
Rapid drug screening using N-gram molecular graphs via a novel architecture of graph neural network
Drug-target affinity (DTA) prediction is crucial for drug discovery.
We proposed N-gram graph DTA (NG-DTA)  based on graph neural networks (GNN) with self-attention to utilize drug and N-gram protein molecular graphs.
NG-DTA achieves the best performance among deep-learning based DTA models.