Base calling method, base calling model training method, and related device

By analyzing the feature mapping and temporal neural network of fluorescence images during gene sequencing, the problem of poor base identification accuracy in gene sequencing was solved, and accurate identification of base categories was achieved.

WO2026129176A1 Publication Date: 2026-06-25MGI TECH CO LTD
4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/140200
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-12-18
Publication Date
2026-06-25

AI Technical Summary

Technical Problem

In existing technologies, it is difficult to accurately identify the correlation between multiple fluorescence images from the same sequencing cycle during gene sequencing, resulting in poor accuracy in base identification.

Method used

By acquiring multiple fluorescence images of multiple nucleic acid sequence clusters to be tested during gene sequencing, feature mapping is performed using the embedding module of the base recognition model to generate fluorescence feature sequences, which are then input into the temporal neural network module for analysis, and combined with the classification module to identify the base categories.

Benefits of technology

It improves the accuracy of base identification, enabling accurate identification of the base categories corresponding to the nucleic acid sequence clusters to be tested, enhancing the information content and dimensionality of the fluorescent feature sequences, and capturing the long-term dependence and dynamic characteristics of the fluorescent signals.

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

Abstract

Provided in the present application are a base calling method, a base calling model training method, and a related device. The base calling method comprises: acquiring a plurality of fluorescence images of a plurality of nucleic acid sequence clusters under test in a sequencing cycle process of gene sequencing; on the basis of an embedded module of a preset base calling model, performing feature mapping on fluorescence intensity sequences corresponding to the plurality of fluorescence images to obtain a fluorescence feature sequence; inputting the fluorescent feature sequence into a timing neural network module of the base calling model to obtain a target feature sequence output by the timing neural network module; and, by means of a classification module of the base calling model, classifying the plurality of nucleic acid sequence clusters under test on the basis of the target feature sequence to obtain base categories corresponding to the plurality of nucleic acid sequence clusters under test in the sequencing cycle. Using the method can improve the accuracy of calling base categories corresponding to nucleic acid sequence clusters under test.
Need to check novelty before this filing date? Find Prior Art