Cancer tissue classification method and device, electronic equipment and storage medium

Abstract

The invention provides a cancer tissue classification method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring gene data corresponding to a to-be-detected tissue set; the to-be-detected tissue comprises a plurality of to-be-detected tissue samples; determining a gene feature matrix and a gene adjacent matrix according to the gene data; inputting the gene feature matrix and the gene adjacent matrix into a graph convolutional neural network to obtain a plurality of graph convolutional network layers; aggregating the plurality of graph convolutional network layers through an enhanced graph convolutional neural network to obtain an aggregation result; and inputting an aggregation result into a classifier for classification to obtain a diagnosis result. The scheme is high in cancer tissue classification accuracy.

Description

technical field [0001] The invention belongs to the technical field of gene identification, and in particular relates to a cancer tissue classification method, device, electronic equipment and storage medium. Background technique [0002] The classification of cancer diseases is a complex issue. With the rapid development of high-throughput sequencing, the role of gene expression profiling and gene network technology has become increasingly prominent, and it also provides strong support for the diagnosis and decision-making of cancer patients. On the one hand, gene expression profiles can classify samples for disease classification. On the other hand, the role of gene networks is to describe the relationship between genes. If a gene is mutated, the impact will be amplified through the gene network. In previous studies, researchers often Only for some genes, and the gene network can involve the regulatory relationship between multiple genes and has an amplification effect. Th...

AI Technical Summary

Problems solved by technology

[0003] From the perspective of network methods, the common correlation between nodes in the network is the network centrality index. Since the network centrality method only evaluates the importance of nodes by their positions in the network, this method ignores the importance of nodes. Its own characteristics cannot consider the node relationship of different order neighbor distances

At present, many machine learning algorithms are also used in disease detection. Classical machine learning algorithms such as logistic regression, support vector machine (SVM) classification algorithm, random forest and feed-forward neural network are all directly based on the gene expression profile of the sample. Classification and prediction of samples, none of these methods can further process network features

[0004] The existing single gene expression profile and network centrality methods have limitations and one-sidedness when classifying cancer tissues, and the classification accuracy is low

Images