Microorganism culture medium recommendation method and system based on gene large model embedding

By using a pre-trained genome-wide language model and deep learning networks, the problems of high-dimensional data processing and nonlinear interaction in microbial culture medium recommendation were solved, achieving efficient and accurate culture medium formulation recommendation.

CN122224293APending Publication Date: 2026-06-16SHANGHAI TAOXUAN SCI INSTR CO LTD
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHANGHAI TAOXUAN SCI INSTR CO LTD
Filing Date
2026-03-17
Publication Date
2026-06-16

AI Technical Summary

⚠Technical Problem

Existing technologies struggle to effectively convert genomic information into microbial culture medium formulations. Traditional methods are time-consuming, labor-intensive, and have low success rates. Existing methods also face challenges such as the curse of dimensionality and complex nonlinear interactions when processing high-dimensional genomic data, resulting in unsatisfactory recommendations.

⚗Method used

We use a pre-trained genome-wide language model to extract deep semantic features of microbial genomes, compress features through a stacked denoising autoencoder network, and optimize culture medium recommendation sorting by combining a bilinear attention mechanism and a triplet boundary sorting loss function.

🎯Benefits of technology

It significantly improves the accuracy and efficiency of culture medium recommendations, effectively captures the evolutionary conservation and functional patterns of gene sequences, reduces computational complexity, and enhances the model's generalization ability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The application discloses a kind of microorganism culture medium recommendation method and system based on gene big model embedding, input target microorganism whole genome sequence into pre-trained genome large language model to obtain genome feature vector, feature compression and denoising processing are carried out by stacked denoising auto-encoder network to obtain low-dimensional microorganism strain feature vector, which is combined with the chemical composition concentration feature vector of candidate culture medium to construct pairing feature set, input deep metric learning network based on bilinear attention mechanism to calculate the adaptation degree score, and output the optimal culture medium recommendation formula in order from high to low according to score.The application extracts deep semantic features using genome large language model, compresses into low-dimensional discriminative representation through supervised dimension reduction network, models multi-order feature interaction using factorization machine, optimizes recommendation quality using ranking learning loss function, and realizes accurate and efficient culture medium formula recommendation.
Need to check novelty before this filing date? Find Prior Art