Molecular property prediction method, system and device and storage medium

The invention discloses a molecular property prediction method, system and device and a storage medium. The method comprises the following steps: acquiring a first molecule; extracting a first feature of the first molecule through a double-graph network model; in the pre-training process of the double-graph network model, on the basis of double-graph neural network comparative learning, feature representation of one molecule is aggregated through multiple neural networks, and supplementary fusion processing is carried out on molecule information obtained by different neural networks; and predicting the molecular property through the first characteristic. According to the embodiment of the invention, molecular feature representation is carried out based on the double-graph network model, so that molecular representations obtained by different networks are similar as much as possible, and molecular information extracted by different networks complements each other; the process of obtaining the molecular charact