A soybean oil component gene-based positioning method based on residual shrinkage network

By constructing mixed pools of high-oil and low-oil soybeans and combining multi-source data analysis, deep residual shrinkage networks were used to screen soybean oil genes, solving the problems of low efficiency and insufficient accuracy in existing technologies, and enabling the rapid and accurate acquisition of core genes that control soybean oil content.

CN121438940BActive Publication Date: 2026-04-07SHIJIAZHUANG ACADEMY OF AGRI & FORESTRY SCI
2 Cites 0 Cited by

Patent Information

Application Number
CN202511601815.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-11-04
Publication Date
2026-04-07
Estimated Expiration
2045-11-04

AI Technical Summary

Technical Problem

Existing methods for screening and identifying key genes for soybean oil content are inefficient and imprecise, making it difficult to improve soybean oil yield and processing efficiency.

Method used

A soybean oil content gene localization method based on residual shrinkage network was adopted. By constructing high-oil and low-oil mixed pools, and combining soil physicochemical data, microclimate data and transcriptome sequence data, gene feature extraction and screening were performed using deep residual shrinkage network to obtain the core genes controlling soybean oil content.

Benefits of technology

This technology enables the rapid and accurate acquisition of core genes that control soybean oil content, improving the reliability and screening efficiency of candidate genes.

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

Abstract

The application discloses a soybean oil gene-based positioning method based on a residual shrinkage network, wherein after seeds are sowed in the same hole in a test field, an F2 generation plant is randomly harvested to obtain environment data; the oil content of the seeds harvested from the F2 generation plant is removed to obtain residual F2 generation plants, and then a high-oil pool and a low-oil pool are constructed; the two pools and parents are resequenced, and a soybean reference genome is compared to obtain single nucleotide polymorphism sites which are consistent between the pool offspring and the corresponding trait of the parent and inconsistent between the two parents; candidate genes are obtained from the environment data and the single nucleotide polymorphism sites; the expression characteristics of the parent transcriptome, the genotype characteristics of the candidate genes and the genetic effect characteristics are integrated, target characteristics are screened out through a deep residual shrinkage network, and then in combination with a function database, genes which are significantly enriched in the oil synthesis pathway are screened out, and core genes are screened out according to the enrichment probability, the genetic position, the contribution degree and the function annotation.
Need to check novelty before this filing date? Find Prior Art