Graph deep-learning QSAR

How it works

Comparisons

Evidence quality

Highlighted claims

• The GNN reached R2 0.98 and RMSE 0.02 after augmentation. — In silico study on the cytotoxicity against Hela cancer cells of xanthones bioactive compounds from Garcinia cowa: QSAR based on Graph Deep Learning, Network Pharmacology, and Molecular Docking
• Graph neural networks represented molecules as graph-structured data with nodes and edges encoding molecular structure. — In silico study on the cytotoxicity against Hela cancer cells of xanthones bioactive compounds from Garcinia cowa: QSAR based on Graph Deep Learning, Network Pharmacology, and Molecular Docking
• Graph Attention Convolution dynamically weighted neighboring nodes to focus on structurally important neighborhoods. — In silico study on the cytotoxicity against Hela cancer cells of xanthones bioactive compounds from Garcinia cowa: QSAR based on Graph Deep Learning, Network Pharmacology, and Molecular Docking
• Graph-based learning outperformed conventional models before and after augmentation. — In silico study on the cytotoxicity against Hela cancer cells of xanthones bioactive compounds from Garcinia cowa: QSAR based on Graph Deep Learning, Network Pharmacology, and Molecular Docking
• The GNN performance is interpreted as evidence that molecular graph representations are suitable for xanthone-based QSAR. — In silico study on the cytotoxicity against Hela cancer cells of xanthones bioactive compounds from Garcinia cowa: QSAR based on Graph Deep Learning, Network Pharmacology, and Molecular Docking