The invention provides an
antiviral drug screening method and
system based on high-dimensional features and a storage medium, and belongs to the technical field of
bioinformatics,
computational biology and
artificial intelligence crossing. Calculating a
drug integration similar matrix and a
virus integration similar matrix; based on an automatic
encoder and a graph convolutional network, combining an adjacent matrix, a
virus integration similar matrix and a
drug integration similar matrix to construct a high-dimensional
feature set; constructing a
hypergraph by taking the high-dimensional
feature set as a vertex set, defining a target function based on the
hypergraph, and solving to obtain a projection matrix; calculating a
prediction score matrix based on the projection matrix and the high-dimensional
feature set; and based on the
prediction score matrix, screening out the
score of the row where the target
virus is located, and sorting to obtain a final prediction result. According to the invention, through fusion of multiple similarities, the internal relationship of virus drugs is described more comprehensively, and the prediction performance is improved; the automatic
encoder can learn a potential nonlinear relationship between samples, and the generalization ability of the model is enhanced.