Single-cell sequencing data dimension reduction method fusing gene ontology and neural network

Abstract

The invention provides a single-cell sequencing data dimension reduction method fusing gene ontology and a neural network. The method comprises the following steps: firstly, extracting gene ontology terms as deep biological information priori knowledge; secondly, extracting Mut-Link constraints among cells as priori knowledge on a cell level; then, combining the two kinds of priori knowledge withan auto-encoder model, and proposing a simGOAE model; and finally, carrying out training dimension reduction on single-cell sequencing data by using the simGOAE model. The simGOAE model provided by the invention not only can adapt to the training of a large sample data set, but also can better mine the biological information of the cells and realize a better single-cell sequencing data dimension reduction effect.

Description

technical field [0001] The invention belongs to the technical field of biological information processing, and in particular relates to a dimensionality reduction method for single-cell sequencing data fused with a gene ontology and a neural network. Background technique [0002] With the development of high-throughput sequencing technology, scientists have proposed single-cell sequencing technology and widely used in transcriptomics research. This technique determines the sequence information of individual cells, providing higher differential resolution and enabling a better understanding of the function of individual cells in their microenvironment. The emergence of single-cell sequencing technology provides the possibility for humans to further study cell function and cell differential expression in the field of bioinformatics. One of the most important applications of single-cell sequencing data (scRNA-seq) is cell clustering, and the clustering results help identify new...

AI Technical Summary

Problems solved by technology

[0005] Although the above method has achieved certain effects on dimensionality reduction of single-cell sequencing data, its disadvantages are: on the one hand, it does not make full use of existing bioinformatics knowledge, and the interpretation is not strong. Dimensionality reduction and other downstream analyzes are required to obtain cell Biological information; on the other hand, today's single-cell sequencing data dimensionality reduction methods are generally effective, and have certain limitations on single-cell sequencing data from different sequencing platforms

Images