An artificial intelligence antibacterial drug dynamic monitoring device

Abstract

The present invention relates to an artificial intelligence antibacterial drug dynamic monitoring device, comprising: a gene determination unit for determining the number of drug-resistant genes; an analysis and judgment unit for obtaining the degree of resistance to the corresponding antibacterial drug based on the number of drug-resistant genes measured by the gene sequencing unit. The present invention is based on a highly organic combination of molecular biology technology and computer technology, summarizes and designs existing known drug-resistant gene determination primers, and utilizes the advantages of rapid and accurate gene sequencing to conduct comprehensive data analysis of the central axis relationship of bacterial drug-resistant genes-resistant bacteria-resistance through statistical models, so as to achieve rapid bedside detection of the number and functional abundance of drug-resistant genes, and real-time monitoring of the application effect of antibacterial drugs on patients, helping clinicians to adjust medication in a timely manner, and guiding patients to use medication scientifically and rationally at home.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically, to an artificial intelligence antibacterial drug dynamic monitoring device. Background Art

[0002] Antibiotics are one of the greatest medical discoveries in human history, and they have saved countless lives. However, with the overuse of antibiotics, it is not uncommon for bacteria to develop resistance to antibiotics. With the emergence of more and more "super bacteria", it is particularly important to effectively detect resistance and avoid overuse of drugs.

[0003] Traditional microbial identification methods rely on phenotypic identification, mainly using staining, culture and simple biochemical tests. The main indicators for monitoring the in vitro pharmacodynamics of antimicrobial drugs are: ① bacterial sensitivity (MIC / MBC); ② antimicrobial spectrum (antimicrobial mechanism); ③ antimicrobial characteristics (bactericidal / bacteriostatic); ④ post-antimicrobial effect (PAE); ⑤ antimicrobial combination.

[0004] Although traditional identification methods are still widely used, they have two major shortcomings: they are only applicable to microorganisms that can be cultured in vitro, and some strains exhibit unique biochemical characteristics that do not conform to known species patterns; another problem is that the culture cycle is too long, bacteria are a dynamic process in the human body, and the effect of antimicrobial drugs is related to concentration / time. Timely identification of the composition of pathogens and the efficacy of antimicrobial drugs is closely related to the patient's prognosis.

[0005] With the development of biotechnology in the 21st century, "gene sequencing" has been widely used in various basic and clinical research and commercial testing because it does not rely on living cultures and can often reveal subtle differences between organisms that cannot be detected by traditional methods. The interpretation of microbial genetic information has greatly improved the accuracy and cycle of clinical pathogen identification. At present, the main methods of identifying microorganisms using microbial gene sequences are: ① PCR identification (such as qPCR); ② microarray chip identification technology; ③ next-generation gene sequencing technology. However, doctors' diagnosis and antibacterial treatment of infections still remain at a single static level such as the biochemical analysis of microbial types and their metabolites, and have failed to fully apply the timeliness, sensitivity and comprehensiveness of gene sequencing to clinical practice.

[0006] Based on this, the existing technology still needs to be improved. Summary of the invention

[0007] In response to the above-mentioned problems, the present invention aims to provide an artificial intelligence antimicrobial drug dynamic monitoring device to obtain antibiotic resistance evaluation results through gene sequencing.

[0008] In order to achieve the above object, the present invention adopts the following technical scheme:

[0009] The present invention discloses an artificial intelligence antibacterial drug dynamic monitoring device, which includes:

[0010] A gene determination unit, used to determine the number of drug resistance genes;

[0011] The analysis and judgment unit derives the degree of resistance to the corresponding antimicrobial drug based on the number of drug-resistant genes measured by the gene sequencing unit.

[0012] In the gene determination unit, the determination of the number of drug-resistant genes can be achieved through the following methods: quantitative PCR (such as qPCR); microarray chip identification technology; and next-generation gene sequencing technology.

[0013] Furthermore, the analysis and judgment unit also includes: obtaining an antibiotic resistance enrichment result through hypergeometric distribution calculation and analysis according to the correspondence between different resistance genes and different antibiotics, and outputting an analysis result based on the antibiotic resistance enrichment result.

[0014] Furthermore, the analysis results include recommendations for relevant antibiotics and medication adjustment plans.

[0015] Furthermore, the determination of the number of drug-resistant genes comprises:

[0016] Determine the number of genes m that can be detected among the known drug-resistant genes in the sample,

[0017] The number of genes a contained in a certain antibiotic resistance gene group in the gene group with increased number is obtained;

[0018] The number of genes contained in a certain antibiotic resistance gene group in the gene group that has not changed is b;

[0019] The number of genes in the gene group with increased quantity, excluding a, is c;

[0020] The number of genes in the gene group that has not changed is d, excluding b.

[0021] Furthermore, the analysis unit comprises: using formula (I) to calculate the P value,

[0022]

[0023] Among them, C is the combination in the permutation and combination, That is, the number of combinations of n elements from m different elements;

[0024] Based on the comparison of the P value with the predetermined value, the drug resistance conclusion is obtained.

[0025] Furthermore, if the P value was less than 0.05, it was considered to be drug-resistant.

[0026] Furthermore, the smaller the P value, the stronger the drug resistance is considered.

[0027] The beneficial effects of the present invention are:

[0028] The present invention is based on a highly organic combination of molecular biology technology and computer technology, summarizes and designs existing known resistance gene determination primers, and uses the advantages of rapid and accurate gene sequencing to conduct comprehensive data analysis on the central axis relationship of bacterial resistance genes-resistant bacteria-resistance through statistical models, thereby achieving rapid bedside detection of the number and functional abundance of resistance genes to monitor the effect of antimicrobial drugs on patients in real time, helping clinicians to adjust medication in a timely manner, and guiding patients to use medication scientifically and rationally at home. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in conjunction with specific embodiments.

[0030] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.

[0031] An embodiment of the present invention discloses an artificial intelligence antibacterial drug dynamic monitoring device, which includes:

[0032] A gene determination unit, used to determine the number of drug resistance genes;

[0033] The analysis and judgment unit derives the degree of resistance to the corresponding antimicrobial drug based on the number of drug-resistant genes measured by the gene sequencing unit.

[0034] The analysis and judgment unit includes: obtaining antibiotic resistance enrichment results through hypergeometric distribution calculation and analysis according to the corresponding relationship between different drug resistance genes and different antibiotics, and outputting analysis results based on the antibiotic resistance enrichment results. Related antibiotics and medication adjustment plans can also be recommended according to the analysis results.

[0035] In some embodiments, based on the above embodiments, the determining the number of drug resistance genes comprises:

[0036] Determine the number of genes m that can be detected among the known drug-resistant genes in the sample,

[0037] The number of genes a contained in a certain antibiotic resistance gene group in the gene group with increased number is obtained;

[0038] The number of genes contained in a certain antibiotic resistance gene group in the gene group that has not changed is b;

[0039] The number of genes in the gene group with increased quantity, excluding a, is c;

[0040] The number of genes in the gene group that has not changed is d, excluding b.

[0041] The analysis unit comprises: using formula (I) to calculate the P value,

[0042]

[0043] Among them, C is the combination in the permutation and combination, That is, the number of combinations of n elements from m different elements;

[0044] Based on the comparison of the P value with the predetermined value, the drug resistance conclusion is obtained.

[0045] The smaller the P value, the stronger the drug resistance is considered. If the P value is less than 0.05, it is considered to be drug-resistant.

[0046] In the initial data model establishment process, metagenomics is used to perform microecological gene determination to verify the accuracy of known drug-resistant genes and predict unknown potential drug-resistant genes. The functional gene abundance information and phenotypic information obtained from the patient's metagenomic sequencing are combined, that is, their resistance or inresistance to antibiotics are integrated, and machine learning algorithms (classification, regression, clustering, etc.) are used to mine genes related to each antibiotic resistance and evaluate the corresponding effect values. In this way, a network relationship tree between genes and phenotypes is established.

[0047] After screening out fixed and drug-resistant related genomes, the primer information of the fixed genome is input into the mass spectrometer using gene sequencing technology or chip technology to quickly detect the number of sequences of the fixed type of genome and obtain its abundance information. According to the correspondence between different drug-resistant genes and different antibiotics, the hypergeometric distribution calculation and analysis are used to obtain the antibiotic resistance enrichment results, and intelligently recommend related antibiotics and medication adjustment plans.

[0048] The present invention provides a primer design scheme (429, see Table 1 and sequence table) required for a method for determining the number of drug-resistant genes based on quantitative PCR.

[0049] Table 1

[0050]

[0051]

[0052]

[0053]

[0054]

[0055]

[0056]

[0057]

[0058]

[0059]

[0060]

[0061]

[0062]

[0063]

[0064]

[0065]

[0066]

[0067]

[0068]

[0069] Example

[0070] Genetic testing unit

[0071] The gene quantity is determined by using quantitative PCR (such as qPCR); microarray chip recognition technology; next-generation gene sequencing technology and other nucleic acid quantitative detection methods. Taking the drug-resistant gene primers designed by the present invention as an example, quantitative PCR is used for determination.

[0072] Take the dfrA26 gene as an example using LAMP detection reaction:

[0073] Primers Primer series (5'→3') Forward primer AGGGCGTTTATTCTTCCTATAC Reverse primer GTCATTGAATCCTGATGTGA

[0074] The following steps are involved:

[0075] 1) Extract DNA;

[0076] 2) Prepare LAMP detection reaction system, the reaction system includes primers: forward primer, reverse primer (concentration 0.2 μM);

[0077] 3) The extracted nucleic acid template is subjected to amplification reaction at 63°C for 1 hour, and the reaction tube is placed in an 80°C water bath for 5 minutes to terminate the reaction. The green fluorescence intensity is observed or the DNA concentration is quantified by a real-time turbidity meter.

[0078] The LAMP detection reaction system is:

[0079] dNTPs 1.4mM, Tris-HCl pH=8.8, 20mM, (NH4)2SO4 10mM, KCl 10mM, MgSO4 8mM, betaine 0.8M, 0.1% Tween 20, Bst DNA polymerase 8U, AMV reverse transcriptase 0.5U, fluorescent dye SYBR greenI 1μl, dfrA26 gene 2μl.

[0080] Analysis and judgment unit:

[0081] At present, the total number of known drug resistance genes is 742, including 11 trimethoprim resistance-related genes, including dfrA26, dfrA12, dfrA14, dfrA17, dfrA5, dfrA8, dfrC, dfrD, dfrF, dfrG, and dfrK. Among the 742 genes (known drug resistance genes m) in a patient's sputum sample, a total of 50 genes were significantly upregulated (the number of genes in the gene group with increased numbers a+c). Among the 50 upregulated genes, four trimethoprim resistance genes, dfrA26, dfrA12, dfrA14, and dfrA17, were included (the number of genes a contained in a certain antibiotic resistance gene group in the gene group with increased numbers). Then, the number of genes b contained in a certain antibiotic resistance gene group in the gene group with unchanged numbers was 11-4=7, and the number of genes d excluding b in the gene group with unchanged numbers was 742-50-7=685.

[0082] Substitute into the formula:

[0083]

[0084] The P value was less than 0.01, suggesting that the patient was resistant to trimethoprim.

[0085] In summary, the artificial intelligence antimicrobial drug dynamic monitoring device provided by the present invention has a small size, high experimental efficiency, and saves manpower, material resources, and time. It is an artificial intelligence instrument that can quickly detect bacterial resistance genes at the bedside, realize clinical rapid diagnosis of pathogens and their sensitivity to antimicrobial drugs, and provide timely guidance on medication.

[0086] It should be particularly pointed out that the various components or steps in the above-mentioned embodiments can be cross-linked, replaced, added, or deleted with each other. Therefore, the combinations formed by these reasonable arrangements and combinations should also fall within the scope of protection of the present invention, and the scope of protection of the present invention should not be limited to the embodiments.

[0087] The above are exemplary embodiments disclosed in the present invention. The order disclosed in the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. However, it should be noted that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope disclosed in the embodiments of the present invention (including claims) is limited to these examples. Various changes and modifications may be made without departing from the scope defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.

[0088] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. An artificial intelligence antibacterial drug dynamic monitoring device, characterized in that: include: A gene determination unit, used to determine the number of drug resistance genes; An analysis and judgment unit, which obtains the degree of resistance to the corresponding antimicrobial drug based on the number of resistance genes measured by the gene sequencing unit, obtains an antibiotic resistance enrichment result through hypergeometric distribution calculation and analysis according to the correspondence between different resistance genes and different antibiotics, and outputs an analysis result based on the antibiotic resistance enrichment result; Determining the number of drug resistance genes comprises: Determine the number of genes m that can be detected among the known drug-resistant genes in the sample, The number of genes a contained in a certain antibiotic resistance gene group in the gene group with increased number is obtained. The number of genes contained in a certain antibiotic resistance gene group in the gene group has not changed. The number of genes in the gene group with increasing quantity is c, excluding a. The number of genes in the gene group that has not changed is d except for genes in b; The analysis unit comprises: using formula (I) to calculate the P value, If the P value is less than 0.05, it is considered to be drug-resistant.

2. The artificial intelligence antibacterial drug dynamic monitoring device according to claim 1 is characterized in that: The smaller the P value, the stronger the drug resistance is considered.

Images