Selected article for: "binding interaction and drug binding interaction"
Author: Liu, Siyuan; Wang, Yusong; Wang, Tong; Deng, Yifan; He, Liang; Shao, Bin; Yin, Jian; Zheng, Nanning; Liu, Tie-Yan
Title: Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer
  • Cord-id: t88tittk
  • Document date: 2021_10_14
    • ID: t88tittk
    Snippet: The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery. Although recent deep learning-based approaches achieved better performance than molecular docking, existing models often neglect certain aspects of the intermolecular information, hindering the performance of prediction. We recognize this problem and propose a novel approach named Intermolecular G
    Document: The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery. Although recent deep learning-based approaches achieved better performance than molecular docking, existing models often neglect certain aspects of the intermolecular information, hindering the performance of prediction. We recognize this problem and propose a novel approach named Intermolecular Graph Transformer (IGT) that employs a dedicated attention mechanism to model intermolecular information with a three-way Transformer-based architecture. IGT outperforms state-of-the-art approaches by 9.1% and 20.5% over the second best for binding activity and binding pose prediction respectively, and shows superior generalization ability to unseen receptor proteins. Furthermore, IGT exhibits promising drug screening ability against SARS-CoV-2 by identifying 83.1% active drugs that have been validated by wet-lab experiments with near-native predicted binding poses.

    Search related documents:
    Co phrase search for related documents
    • active drug and machine learning: 1, 2, 3, 4, 5, 6, 7
    • active ligand and machine learning: 1, 2, 3
    • active one and low resource: 1
    • active one and machine learning: 1, 2, 3
    • activity prediction and low accuracy: 1
    • activity prediction and machine learning: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
    • activity prediction and machine learning set: 1
    • activity prediction model and machine learning: 1, 2
    • low accuracy and machine learning: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
    • low accuracy and machine learning set: 1
    • low accuracy cost and machine learning: 1, 2
    • low accuracy cost compare and machine learning: 1
    • low resource and machine learning: 1, 2, 3, 4, 5, 6, 7, 8