The invention provides an
immunotherapy reaction marker identification method and
system based on a cooperative game theory, and relates to the technical field of intelligent
medical treatment, and the method comprises the following steps: obtaining
immunotherapy single cell sequencing data, and determining a
candidate gene set through
differential expression analysis; extracting regulation and control relation pairs of the
candidate gene set to obtain a multi-level information
gene regulation and
control network; embedding the multilevel information
gene regulation and
control network by adopting a Node2vec
algorithm to obtain a
network module containing potential biological functions, calculating the contribution degree of each
gene feature to
model prediction based on a Myerson value, and obtaining a feature importance sequence; combining the optimal features of the modules into a global candidate set; and iteratively optimizing the global candidate set, and outputting a target
immunotherapy reaction marker set. Through a Myerson value principle in a cooperative game, a biomarker set related to immunotherapy response is efficiently searched, deep analysis of a
drug resistance mechanism is realized, the accuracy and robustness of marker screening are improved, and the method serves for
cancer clinical scheme customization.