Unsupervised learning drug virtual screening method and system based on molecular semantic vectors

The invention discloses an unsupervised learning drug virtual screening method based on a molecular semantic vector. The method comprises the following steps: establishing a pre-training database; constructing a candidate set database D1; constructing a target compound library D2; performing data preprocessing on the pre-training database, the candidate set database D1 and the target compound library D2, and converting all compounds in the pre-training database, the candidate set database D1 and the target compound library D2 into a data set in a file storage format suitable for machine learning; establishing a micromolecule quantification model of unsupervised deep learning, and pre-training the quantification model by using data in a pre-training database to obtain a trained quantification model; quantifying data in the candidate set database D1 and the target compound library D2 by using a trained quantification model to obtain a candidate set quantification result matrix Va and a target compound library q