PROTAC molecular degradation rate prediction system based on neural network and construction method thereof

The invention discloses a PROTAC molecular degradation rate prediction system based on a neural network and a construction method thereof. The neural network comprises a graph convolutional neural network, an addition pooling layer, a full connection layer, a node embedding layer, an embedding layer and a bidirectional long-short-term memory layer; a PROTAC molecule comprises a target protein ligand, a ubiquitin ligase ligand and a connector; and the specific content is shown in the specfication. The prediction system provided by the invention overcomes the problem of difficulty in design caused by an indefinite structure-function relationship of PROTAC molecules. By applying the prediction system, molecules which are screened by the artificial intelligence neural network and have a good predicted degradation effect can be obtained, and then synthesis and cell experiment are performed, so that the success rate of drug research and development is increased, the cycle of drug research and development is shorten