GRAPH NEURAL NETWORK-BASED CLINICAL OMICS DATA PROCESSING METHOD AND APPARATUS, DEVICE, AND MEDIUM

摘要

A graph neural network-based clinical omics data processing method and apparatus, a device, and a medium, relating to the technical fields of medical treatment, artificial intelligence, cloud data and the like. The method comprises: obtaining first omics data of a target object, and extracting at least two first omics features from the first omics data (S101); determining a first correlation between different omics features in the at least two first omics features (S102); constructing a first graph structure corresponding to the first omics data according to the at least two first omics features and the first correlation, wherein the first graph structure comprises at least two nodes, and each node represents one first omics feature in the first omics data, the first graph structure at least comprises a connection edge connecting the at least two nodes, and the two nodes connected by the connection edge correspond to the first correlation (S103); according to the first graph structure, obtaining the node feature of each node in the first graph structure by means of a first graph neural network, wherein the node feature has at least one dimension (S104); and according to the node feature of each node, performing medical analysis on the target object to obtain a medical analysis result corresponding to each dimension in the at least one dimension, wherein the medical analysis comprises performing disease diagnosis, disease typing, and survival prediction on the target object, and the medical analysis result comprises a probability that the target object corresponding to each dimension has a disease, a probability that the disease of the target object corresponding to each dimension is a certain disease category, and a survival probability of the target object corresponding to each dimension (S105).