AI-assisted microbial gene editing target prediction method and system
By using AI-assisted systems to interact with databases in real time and perform multi-dimensional characteristic matching analysis, combined with tools such as CRISPR-Cas9 for gene editing, the problem of low efficiency and insufficient accuracy in predicting microbial gene editing targets in existing technologies has been solved, achieving efficient and accurate target prediction and editing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-22
- Publication Date
- 2026-03-24
AI Technical Summary
Existing technologies are inefficient and have a high error tolerance in predicting microbial gene editing targets. They cannot achieve real-time comparison of gene functional characteristics with databases, making it difficult to accurately and quickly pinpoint target sites.
The system employs an AI-assisted system to interact with a database of known ligand-target relationships in real time. It combines this with a target analysis system to perform multi-dimensional characteristic matching analysis. Gene editing tools such as CRISPR-Cas9 nuclease are used to precisely cut and recombine DNA. The target is then amplified and detected using a PCR system.
It significantly improved target prediction efficiency by more than 30%, achieved an accuracy rate of over 90%, reduced labor costs and error tolerance, and realized efficient and accurate gene editing target prediction.
Smart Images
Figure CN121725872A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of microbial gene editing technology, specifically to an AI-assisted method and system for predicting microbial gene editing targets. Background Technology
[0002] Microbial gene editing target prediction refers to the use of bioinformatics, computational biology, and machine learning methods to pre-screen and identify specific DNA sites in the microbial genome that are most suitable for gene editing. Its core objective is to improve the efficiency and accuracy of gene editing through rational design and avoid the waste of resources caused by blind experiments.
[0003] In existing technologies, predicting gene editing targets typically requires identifying the gene to be edited, then scanning the target region using the CRISPR system to find PAM sequences, screening for nearby 20bp candidate gRNA targets, and then using tools such as BLAST and CRISPRoff to compare the whole genome and exclude sequences highly homologous to non-target regions. This process does not incorporate AI for multi-dimensional gene functional characteristic input analysis, relying on manual step-by-step verification, which is inefficient and has a high error tolerance. It cannot achieve real-time comparison and prediction of gene functional characteristics with databases, making it difficult to accurately and quickly locate target sites. Therefore, we propose an AI-assisted method and system for predicting microbial gene editing targets. Summary of the Invention
[0004] The purpose of this invention is to provide an AI-assisted method and system for predicting microbial gene editing targets.
[0005] To achieve the above objectives, the present invention provides the following technical solution: an AI-assisted microbial gene editing target prediction system comprising: The AI-assisted system establishes a real-time data interaction connection with a computer terminal and a known ligand-target relationship database through wired or wireless communication protocols (such as TCP / IP, 5G), supporting real-time input of gene functional characteristic parameters, retrieval of database data, and feedback of prediction results. Microbial culture system for culturing microorganisms with recombinant enzymes and microorganisms from which genes are to be extracted; The target analysis system is connected to an AI-assisted system. By inputting gene functions with specified characteristics, such as gene name, degree, betweenness, and centrality, into the AI-assisted system, preliminary analysis is performed to reduce the error rate. Then, the gene sequence in the microorganism from which the gene is to be extracted is subjected to characteristic prediction analysis to achieve target prediction. Gene-binding systems involve knocking out obtained gene sequences and then editing them with microorganisms that possess recombinases. The PCR system is used to culture recombinant genes and achieve rapid amplification of target DNA. The detection system identifies the target by screening cells with recombinant genes for resistance.
[0006] As a further aspect of the present invention, the known ligand-target relationship database mainly includes three publicly available standardized databases: Genecard, OMIM, and GAD. All of these databases support the retrieval and retrieval of gene function and target association data.
[0007] As a further aspect of the present invention, the microorganisms possessing recombinant enzymes include yeast and other usable microorganisms.
[0008] As a further aspect of the present invention, the target analysis system includes GC content analysis, secondary structure analysis, and PAM analysis, and the tools used include CRISPRdirect, CRISPRscan, etc.
[0009] As a further aspect of the present invention, the microorganism from which the gene is to be extracted contains several gene sequences.
[0010] As a further aspect of the present invention, the gene knockout process must ensure that the gene sequence to be extracted has a complementary fragment of 40 bp (base pairs), and the gene in the microorganism with recombinase must have homology walls at both ends to achieve the reproducible culture of the overlapping gene.
[0011] As a further aspect of the present invention, it also includes gene editing technology, which uses commonly used gene editing nucleases such as CRISPR-Cas9 nuclease and Cas12a nuclease to perform site-specific and precise cutting of target DNA regions.
[0012] As a further aspect of the present invention, this invention also includes a target prediction method for an AI-assisted microbial gene editing target prediction system, comprising the following steps: S1. Select the specified microorganisms with recombinase and the microorganisms from which the gene is to be extracted. Input the gene function with specified characteristics (such as gene name, degree, betweenness, centrality) into the AI-assisted system to perform a preliminary analysis of multi-dimensional characteristic matching. At the same time, perform real-time comparison analysis with gene function-target association data in the known ligand-target relationship database. Analyze the data in the known ligand-target relationship database, and then perform characteristic prediction analysis on the gene sequence in the microorganism from which the gene is to be extracted to achieve target prediction. S2. Using gene editing technology, specific nucleases are used to precisely cut DNA, and the obtained gene sequence is edited and recombined with microorganisms that have recombinase through a gene binding system; S3. The recombinant gene is cultured using a PCR system to achieve rapid amplification of the target DNA. Finally, the recombinant gene is screened for resistance using a detection system to confirm the target site.
[0013] Compared with the prior art, the beneficial effects of the present invention by adopting the above technical solution are as follows: 1. This invention selects specific microorganisms containing recombinases and microorganisms from which genes are to be extracted. By inputting gene functions with specified characteristics (such as gene name, degree, betweenness, and centrality) into an AI-assisted system, a preliminary multi-dimensional characteristic matching analysis is performed. Simultaneously, real-time comparison analysis is conducted with gene function-target association data in a known ligand-target relationship database. Further analysis is performed on the gene sequence in the microorganism from which the gene is to be extracted, enabling target prediction. The gene sequence can be screened using the AI-assisted system. Experimental verification shows that the target prediction efficiency of this invention is more than 30% higher than existing technologies, with a prediction accuracy exceeding 90%, significantly reducing the manual cost and error tolerance of target screening.
[0014] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description
[0015] Figure 1 This is a flowchart of the AI-assisted microbial gene editing target prediction method proposed in this invention. Step S1 includes three sub-steps: gene function parameter input, database comparison, and sequence characteristic prediction. Step S2 includes two core operations: DNA cutting and gene recombination. Figure 2 This is a schematic diagram of the structure of the AI-assisted microbial gene editing target prediction system proposed in this invention. The AI-assisted system is the core control module, which establishes control command interaction with the target analysis system and gene binding system through the data transmission module. The operating data of the microbial culture system, PCR system and detection system are fed back to the AI-assisted system in real time. Detailed Implementation
[0016] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.
[0017] Furthermore, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0018] Please see the appendix Figure 1 and attached Figure 2 The AI-assisted microbial gene editing target prediction system includes an AI-assisted system, a microbial culture system, a target analysis system, a gene binding system, a PCR system, and a detection system. The AI-assisted system establishes a real-time data interaction connection with a computer terminal and a known ligand-target relationship database via wired or wireless communication protocols (such as TCP / IP and 5G). It supports real-time input of gene functional characteristic parameters, database data retrieval, and prediction result feedback. The known ligand-target relationship database mainly includes three publicly available standardized databases: GeneCard, OMIM, and GAD. All of these databases support the retrieval and retrieval of gene function and target association data. The microbial culture system... The system is used to cultivate microorganisms with recombinase and microorganisms from which the gene is to be extracted. The target analysis system is connected to the AI-assisted system. By inputting gene functions with specified characteristics, such as gene name, degree, betweenness, and centrality, into the AI-assisted system, preliminary analysis is performed to reduce the error margin. Then, the gene sequence in the microorganism from which the gene is to be extracted is subjected to characteristic prediction analysis to predict the target. The gene binding system is used to edit the obtained gene sequence after gene knockout with microorganisms with recombinase. The PCR system is used to culture the recombinant gene and realize the rapid amplification of the target DNA. The detection system confirms the target by screening for resistance to recombinant genes.
[0019] In the specific implementation, yeast (Saccharomyces cerevisiae, containing recombinase RecA) was selected as the microorganism with recombinase, and Escherichia coli (E. coli K-12) was selected as the microorganism from which the gene was to be extracted. The gene functional characteristics were input into the AI-assisted system: γ-PGA synthase gene (pgsA), degree value ≥ 0.8, betweenness value ≥ 0.6, and centrality ranking in the top 5%. After real-time comparison and analysis with the GeneCard database, the pgsA gene sequence to be extracted was analyzed for GC content (GC content 45%-55%), secondary structure (stem-loop structure ratio ≤ 20%), and PAM sequence (NGG type). The predicted target was the 120-140bp region of the pgsA gene. After PCR amplification and ampicillin resistance screening, the target confirmation accuracy rate was 92%, which is 35% more efficient than existing technologies.
[0020] As one technical optimization of the present invention, please refer to the appendix. Figure 1 and attached Figure 2 The microorganisms containing recombinases include yeast and other usable microorganisms.
[0021] In practice, by using microorganisms with recombinases as vectors for recombinant genes, the metabolic capacity of recombinant microorganisms for specific substrates can be enhanced.
[0022] As one technical optimization of the present invention, please refer to the appendix. Figure 1 and attached Figure 2 The target analysis system includes GC content analysis, secondary structure analysis, and PAM analysis, and the tools used include CRISPRdirect and CRISPRscan.
[0023] In practice, the target analysis system is used to perform a full-range analysis of the selected genes, reducing the difficulty of target prediction.
[0024] As one technical optimization of the present invention, please refer to the appendix. Figure 1 and attached Figure 2 The microorganism from which the gene is to be extracted contains several gene sequences.
[0025] In practice, by screening out several gene sequences and recombining them, the range of target prediction can be improved.
[0026] As one technical optimization of the present invention, please refer to the appendix. Figure 1 and attached Figure 2 The gene knockout process requires that the gene sequence to be extracted has a complementary fragment of 40 bp (base pairs), and that the gene in the microorganism with recombinase has homology walls at both ends to achieve the reproducible culture of the overlapping gene.
[0027] As one technical optimization of the present invention, please refer to the appendix. Figure 1 and attached Figure 2 It also includes gene editing technology, which uses commonly used gene editing nucleases such as CRISPR-Cas9 nuclease and Cas12a nuclease to perform site-specific and precise cutting of target regions of DNA.
[0028] As one technical optimization of the present invention, please refer to the appendix. Figure 1 and attached Figure 2 The present invention also includes a target prediction method for an AI-assisted microbial gene editing target prediction system, comprising the following steps: S1. Select the specified microorganisms with recombinase and the microorganisms from which the gene is to be extracted. Input the gene function with specified characteristics (such as gene name, degree, betweenness, centrality) into the AI-assisted system to perform a preliminary analysis of multi-dimensional characteristic matching. At the same time, perform real-time comparison analysis with gene function-target association data in the known ligand-target relationship database. Analyze the data in the known ligand-target relationship database, and then perform characteristic prediction analysis on the gene sequence in the microorganism from which the gene is to be extracted to achieve target prediction. S2. Using gene editing technology, specific nucleases are used to precisely cut DNA, and the obtained gene sequence is edited and recombined with microorganisms that have recombinase through a gene binding system; S3. The recombinant gene is cultured using a PCR system to achieve rapid amplification of the target DNA. Finally, the recombinant gene is screened for resistance using a detection system to confirm the target site.
[0029] The terms "front," "back," "left," "right," "top," and "bottom" all refer to the figures in the accompanying drawings. Figure 1 Based on.
[0030] In the description of this invention, it should be understood that the terms "center", "longitudinal", "lateral", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting the scope of protection of this invention.
[0031] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments.
[0032] For those skilled in the art, various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and these variations still fall within the protection scope of the present invention.
Claims
1. An AI-assisted microbial gene editing target prediction system, characterized in that, include: The AI-assisted system establishes a real-time data interaction connection with a computer terminal and a known ligand-target relationship database through wired or wireless communication protocols (such as TCP / IP, 5G), supporting real-time input of gene functional characteristic parameters, retrieval of database data, and feedback of prediction results. Microbial culture system for culturing microorganisms with recombinant enzymes and microorganisms from which genes are to be extracted; The target analysis system is connected to an AI-assisted system. By inputting gene functions with specified characteristics, such as gene name, degree, betweenness, and centrality, into the AI-assisted system, preliminary analysis is performed to reduce the error rate. Then, the gene sequence in the microorganism from which the gene is to be extracted is subjected to characteristic prediction analysis to achieve target prediction. Gene-binding systems involve knocking out obtained gene sequences and then editing them with microorganisms that possess recombinases. The PCR system is used to culture recombinant genes and achieve rapid amplification of target DNA. The detection system identifies the target by screening cells with recombinant genes for resistance.
2. The AI-assisted microbial gene editing target prediction system according to claim 1, characterized in that: The known ligand-target relationship databases mainly include three publicly standardized databases: GeneCard, OMIM, and GAD. All of these databases support the retrieval and retrieval of gene function and target association data.
3. The AI-assisted microbial gene editing target prediction system according to claim 1, characterized in that: The microorganisms containing recombinases include yeast and other usable microorganisms.
4. The AI-assisted microbial gene editing target prediction system according to claim 1, characterized in that: The target analysis system includes GC content analysis, secondary structure analysis, and PAM analysis, and the tools used include CRISPRdirect and CRISPRscan.
5. The AI-assisted microbial gene editing target prediction system according to claim 1, characterized in that: The microorganism from which the gene is to be extracted contains several gene sequences.
6. The AI-assisted microbial gene editing target prediction system according to claim 1, characterized in that: The gene knockout process requires that the gene sequence to be extracted has a complementary fragment of 40 bp (base pairs), and that the gene in the microorganism with recombinase contains homology walls at both ends to achieve the reproducible culture of the overlapping gene.
7. The AI-assisted microbial gene editing target prediction system according to claim 1, characterized in that: It also includes gene editing technology, which uses commonly used gene editing nucleases such as CRISPR-Cas9 nuclease and Cas12a nuclease to perform site-specific and precise cutting of target regions of DNA.
8. A target prediction method using the AI-assisted microbial gene editing target prediction system according to any one of claims 1-7, characterized in that: Includes the following steps: S1. Select the specified microorganisms with recombinase and the microorganisms from which the gene is to be extracted. Input the gene function with specified characteristics (such as gene name, degree, betweenness, centrality) into the AI-assisted system to perform a preliminary analysis of multi-dimensional characteristic matching. At the same time, perform real-time comparison analysis with gene function-target association data in the known ligand-target relationship database. Analyze the data in the known ligand-target relationship database, and then perform characteristic prediction analysis on the gene sequence in the microorganism from which the gene is to be extracted to achieve target prediction. S2. Using gene editing technology, specific nucleases are used to precisely cut DNA, and the obtained gene sequence is edited and recombined with microorganisms containing recombinases through a gene binding system; S3. The recombinant gene is cultured using a PCR system to achieve rapid amplification of the target DNA. Finally, the recombinant gene is screened for resistance using a detection system to confirm the target site.