Gene expression data classifier

Abstract

The invention relates to the field of electric data processing, in particular to a gene expression data classifier. On the basis of a traditional multi-task deep learning processing method, a gene expression data classifier with an input layer, a first hidden layer, a second hidden layer and an output layer is designed. Particularly, a shared hiding unit is arranged on the first hidden layer and the second hidden layer, so that the classifier can process gene expression data which come from different data sets and have different identifiers. The problem that tissue samples are insufficient when the gene expression data are classified is effectively solved. Adverse effects caused by the introduction of high feature space dimensions are reduced.

Description

technical field [0001] The invention relates to the field of electrical data processing, in particular to a gene expression data classifier. Background technique [0002] The study of the relationship between gene expression profiles and cancer / disease states is a very important content in biological and medical tasks. For example, comparing diseased and normal tissue can improve understanding of pathology and help identify different tissues (cancerous or normal) because gene expression data can provide clues to tissue phenotype, function, and physiological processes. However, considering the quantity and complexity of gene expression data, traditional biological experiments cannot handle such data. [0003] Table 1 Examples of gene expression data [0004] [0005] Table 1 is an example of gene expression data. Gene expression data is usually expressed using a matrix of n rows and m columns, these rows represent characteristics (genes), and these columns represent sam...

AI Technical Summary

Problems solved by technology

Therefore, the high dimensionality of the feature space increases the risk of overfitting, since the number of genes is much larger than the number of samples

The second challenge is the lack of tissue samples, and it is difficult for existing methods to represent cancer information well because there is little training data for cancer

In the past five years, although the above-mentioned multi-task-based deep learning model has achieved success in computer vision and biomedical image analysis, the existing methods are all independently learning expression and obtaining learning results.

Images