Schematic diagram of the process of PanGu training and PanGu application (IMAGE)
Caption
Schematic diagram of the process of PanGu training and PanGu application to a variety of AI drug screening tasks. The upper shows the conditional variational autoencoder structure of PanGu, pre-trained with chemical structures of 1.7 billion small molecules. The below shows the AI-powered drug screening flowchart consisting of AI tasks of compound-protein interaction prediction, molecular property prediction, drug-like optimization and library generation, and shows the molecule screening procedure from an initial molecular database, to a HIT candidate library, lead-like library and final screening output library. Arrows indicate PanGu Fingerprint and PanGu decoder empower the corresponding tasks.
Credit
©Science China Press
Usage Restrictions
Use with credit.
License
Original content