Single-cell transcriptome-based model construction method based on mamba-transformer hybrid architecture

By constructing a basic single-cell transcriptome model based on the Mamba-Transformer hybrid architecture, the problems of poor generalization and weak noise resistance in single-cell data analysis are solved. It achieves improved robustness under sparse and high-noise data and cross-platform and cross-modal knowledge transfer capabilities, making it suitable for a variety of downstream tasks.

CN122598744APending Publication Date: 2026-08-18DALIAN NATIONALITIES UNIVERSITY
0 Cites 0 Cited by

Patent Information

Application Number
CN202610632604.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-09
Publication Date
2026-08-18

AI Technical Summary

Technical Problem

Existing single-cell data analysis methods suffer from poor generalization and weak noise resistance, making it difficult to effectively uncover global biological patterns. Furthermore, they lack cross-platform and cross-modal knowledge transfer capabilities, resulting in insufficient robustness of the models when dealing with sparse and noisy data.

Method used

We employ a single-cell transcriptome model based on a Mamba-Transformer hybrid architecture. By combining gene expression value prediction and cell characterization learning tasks with a pre-training strategy, we construct a hybrid network architecture, including Mamba network modules, Transformer network modules, and sparse hybrid expert network modules. We use a self-supervised learning paradigm to mine high-order co-expression relationships between genes in massive datasets.

Benefits of technology

It significantly improves the signal-to-noise ratio and feature robustness of data, has strong cross-batch and cross-modal alignment capabilities, reduces the dependence on high-quality manually labeled data, and improves prediction performance and computational resource utilization efficiency in complex scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides a single-cell transcriptome basic model construction method based on a Mamba-Transformer hybrid architecture, and belongs to the technical field of artificial intelligence and bioinformatics. The technical scheme is as follows: quality control and standardization are performed on single-cell transcriptome data to obtain a standardized gene expression matrix; an input embedding containing gene identification, expression value marking and state label is constructed to form a cell-level continuous vector representation; a hybrid network architecture in which Mamba, Transformer and sparse hybrid experts are alternately stacked is constructed, combined with residual connection and layer normalization; joint pre-training is performed in combination with gene expression value prediction and cell representation learning tasks to obtain a basic model. The beneficial effects are as follows: the application overcomes zero inflation and technical noise by learning global context, improves signal-to-noise ratio and feature robustness, constructs a unified representation space to effectively strip batch effects, realizes precise alignment across platforms and modalities, and significantly reduces the dependence on artificial annotation for downstream tasks and saves computing resources by virtue of strong knowledge transfer capability.
Need to check novelty before this filing date? Find Prior Art