SNP site detection kit for predicting drugs for treating mental diseases

Abstract

The present application relates to the technical field of gene determination, and particularly relates to a SNP site detection kit for predicting medication for treating mental diseases, which comprises a data acquisition module, a gene detection module, a drug applicability analysis module, a reference patient analysis module and a medication recommendation module. The individual applicability of various mental disease treatment drugs is determined by gene detection on a target patient and each historical patient, so that the reference patient of the target patient among each historical patient is determined based on the similarity of the clinical data and the individual applicability between the target patient and each historical patient, and finally the medication recommendation information of the target patient is generated based on the medication information of the reference patient. The individual applicability of various mental disease treatment drugs is determined by gene detection, and the similarity of the clinical data and the individual applicability between the target patient and each historical patient is quantified, so that the medication recommendation of the target patient is effectively realized.

Description

Technical Field

[0001] This invention relates to the field of gene sequencing technology, specifically to a SNP site detection kit for predicting medication use in the treatment of mental illnesses. Background Technology

[0002] Mental illnesses, such as depression, schizophrenia, and anxiety disorders, have been on the rise globally in recent years. Although the specific causes of these illnesses are not fully understood, genetic factors are believed to play a significant role. Single nucleotide polymorphisms (SNPs) are variations in a single nucleotide in a DNA sequence and are one of the most common types of genetic variation. Studies have shown that specific SNP sites are closely related to susceptibility to mental illnesses, drug response, and treatment efficacy. By detecting specific SNP sites associated with medications used to treat mental illnesses, medication prediction and guidance can be achieved.

[0003] Current methods for predicting medication use in mental illnesses using SNP locus testing primarily focus on the SNP genotype and the functional expression of the corresponding gene, then constructing a predictive model based on the genotype. However, the ultimate goal of prediction is to guide medication use, and existing methods fail to fully integrate genetic information directly related to the characteristics of the drugs themselves. This results in predictive results (such as predicting a patient's "high," "moderate," or "low" response to a certain type of drug) not being directly translated into specific medication recommendations, such as choosing a particular drug or adjusting the dosage. Furthermore, the efficacy and safety of medications for mental illnesses are not only influenced by genetic factors but also highly dependent on the patient's specific clinical presentation. Direct genetic testing predictions may not be accurate enough and generally cannot be directly used for individualized medication guidance; a certain amount of accumulated clinical experience is required. Summary of the Invention

[0004] To address the technical problem that existing SNP site detection methods cannot be directly applied to medication guidance, the present invention aims to provide an SNP site detection kit for predicting medication use in the treatment of mental illnesses. The specific technical solution adopted is as follows: In a first aspect, the present invention provides a SNP site detection kit for predicting medication use in the treatment of mental illnesses, comprising: The data acquisition module is used to acquire clinical data of target patients suffering from a certain mental illness, as well as clinical data and medication information of historical patients suffering from the same type of mental illness as the target patients. The gene testing module is used to perform gene testing on the target patient and each historical patient separately to obtain gene testing results; The drug suitability analysis module is used to determine the individual suitability of various mental illness treatment drugs based on the genotype distribution of each SNP site of the gene associated with the various mental illness treatment drugs in the gene detection results, and in combination with the functional attributes of the genes associated with the various mental illness treatment drugs. The reference patient analysis module is used to determine the reference patient among the historical patients based on the similarity of clinical data between the target patient and the historical patients, as well as the similarity of individual applicability of various mental illness treatment drugs. The medication recommendation module is used to generate medication recommendation information for the target patient based on the medication information of the reference patient.

[0005] In conjunction with the first aspect above, in some possible implementations, the drug suitability analysis module includes: The functional score analysis unit is used to encode the genotype of each SNP locus of the gene associated with various mental illness treatment drugs in the gene detection results, and to determine the functional score of the gene associated with various mental illness treatment drugs based on the encoding value of the genotype of each SNP locus. A gene classification unit is used to classify all genes associated with various mental illness treatment drugs according to their functional attributes, thereby obtaining several attribute gene categories. The attribute scoring analysis unit is used to determine the attribute score of each attribute gene category based on the functional scores of all genes in each attribute gene category. The individual suitability analysis unit is used to determine the individual suitability of various mental illness treatment drugs based on the attribute scores of all attribute gene categories associated with various mental illness treatment drugs.

[0006] In conjunction with the first aspect above, in some possible implementations, the functional score analysis unit is specifically used for: For each SNP locus of the gene associated with various drugs for the treatment of mental illnesses, the genotypes in the gene detection results are respectively encoded as the first value, the second value, and the third value, with the first value, the second value, and the third value increasing sequentially. Based on the weighted weights of each SNP site of each gene, the genotype coding values ​​of each SNP site of the genes associated with various mental illness treatment drugs are weighted and accumulated to obtain the functional scores of the genes associated with various mental illness treatment drugs.

[0007] In conjunction with the first aspect above, in some possible implementations, the functional attributes of the gene include metabolic capacity, therapeutic effect, and adverse reactions, and the gene classification unit is specifically used for: All genes associated with various drugs for treating mental illnesses are classified according to their functional attributes into metabolic capacity, therapeutic effect, and adverse reaction categories, thereby obtaining the aforementioned gene categories.

[0008] In conjunction with the first aspect above, in some possible implementations, the individual suitability analysis unit is specifically used for: Calculate the mean of the attribute scores of all attribute gene categories associated with various mental illness treatment drugs to obtain the individual scores of various mental illness treatment drugs; After normalizing the individual scores and performing negative correlation mapping, the individual applicability of various mental illness treatment drugs is obtained.

[0009] In conjunction with the first aspect above, in some possible implementations, the reference patient analysis module includes: The clinical manifestation feature construction unit is used to construct the clinical manifestation features of the target patient and each historical patient based on the clinical data of the target patient and each historical patient, respectively. The clinical manifestation difference analysis unit is used to determine the clinical manifestation differences between the target patient and the historical patients based on the differences in clinical manifestation characteristics between the target patient and the historical patients. The adaptability difference analysis unit is used to determine the medication adaptability difference between the target patient and the historical patients based on the differences in individual suitability of various mental illness treatment drugs between the target patient and the historical patients. The medication similarity analysis unit is used to determine the individual medication similarity between the target patient and each historical patient based on the differences in clinical manifestations and the differences in medication suitability. The reference patient determination unit is used to determine the maximum individual medication similarity among all the individual medication similarities, and to use the historical patient corresponding to the maximum individual medication similarity as the reference patient for the target patient among all the historical patients.

[0010] In conjunction with the first aspect above, in some possible implementations, the clinical manifestation difference analysis unit is specifically used for: Obtain the difference values ​​of each feature item in the clinical manifestation characteristics between the target patient and each historical patient; The difference values ​​of all feature items in the clinical manifestation characteristics are weighted and summed to obtain the difference in clinical manifestation between the target patient and each historical patient.

[0011] In conjunction with the first aspect above, in some possible implementations, the fitness difference analysis unit is specifically used for: The individual suitability differences of the same mental illness treatment drugs between the target patient and each of the historical patients are determined to obtain the individual suitability differences; The mean individual applicability difference for all medications for treating mental illnesses is determined to obtain the clinical performance differences between the target patient and each historical patient.

[0012] In conjunction with the first aspect above, in some possible implementations, the medication recommendation module includes: The same disease course time period determination unit is used to determine the time period when the current disease course of the reference patient and the target patient is consistent as the same disease course time period; The medication recommendation unit is used to generate medication recommendation information for the target patient based on the reference patient's medication information, including the guidance on medication and dosage during the same disease course.

[0013] In conjunction with the first aspect above, in some possible implementations, the gene detection module includes: The sample acquisition unit is used to acquire gene testing samples from the target patient and various historical patients. The SNP site determination unit is used to identify SNP sites of genes associated with various drugs for the treatment of mental illnesses as SNP sites to be detected. A gene detection unit is used to perform gene detection on the SNP site to be detected based on the gene detection sample, and obtain gene detection results, wherein the gene detection results include at least the genotype of the SNP site to be detected.

[0014] Secondly, the present invention also provides a method for predicting medication use in the treatment of mental illnesses using an SNP site detection kit, the method comprising: Acquire clinical data of target patients suffering from a certain mental illness, as well as clinical data and medication information of historical patients with the same type of mental illness as the target patients; Genetic testing was performed on the target patient and each historical patient to obtain the genetic testing results; Based on the genotype distribution of each SNP locus of the genes associated with various mental illness treatment drugs in the gene detection results, and combined with the functional attributes of the genes associated with various mental illness treatment drugs, the individual suitability of various mental illness treatment drugs is determined. Based on the similarity of clinical data between the target patient and each of the historical patients, as well as the similarity of individual applicability of various mental illness treatment drugs, a reference patient for the target patient among the historical patients is determined. Based on the medication information of reference patients, medication recommendation information is generated for the target patient.

[0015] Thirdly, the present invention also provides a medication prediction system for treating mental illnesses using an SNP site detection kit, comprising a memory and a processor. The memory stores executable computer program code, and the processor retrieves and runs the executable computer program code from the memory, causing the system to perform the steps implemented by the various modules of the SNP site detection kit for predicting medication for treating mental illnesses, as described in the first aspect or any possible implementation thereof.

[0016] Fourthly, the present invention also provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to execute the steps implemented by the various modules of the SNP site detection kit for predicting medication for treating mental illnesses, as described in the first aspect or any possible implementation thereof.

[0017] Fifthly, the present invention also provides a computer-readable storage medium storing computer program code that, when executed on a computer, causes the computer to perform the steps implemented by the various modules of the SNP site detection kit for predicting medication for treating mental illnesses, as described in the first aspect or any possible implementation of the first aspect.

[0018] This invention offers the following advantages: First, by setting up a data acquisition module, clinical data of a target patient suffering from a certain mental illness, as well as clinical data and medication information of historical patients suffering from the same type of mental illness as the target patient, a clinical data basis for drug recommendations can be obtained. In this invention, gene testing and drug suitability analysis modules are used to perform gene testing on the target patient and historical patients respectively. Based on the genotype distribution of each SNP locus of genes associated with various mental illness treatment drugs in the gene testing results, and combined with the functional attributes of the genes associated with various mental illness treatment drugs, the individual suitability of various mental illness treatment drugs is determined. This individual suitability reflects the comprehensive applicability of a patient to mental illness treatment drugs in terms of different gene functional attributes. Next, by setting up a reference patient analysis module, the similarity of clinical data between the target patient and historical patients, as well as the similarity of individual suitability of various mental illness treatment drugs, is analyzed to determine the reference patient among the historical patients. This reference patient has a high degree of similarity to the target patient in clinical manifestations and comprehensive applicability of mental illness treatment drugs in terms of different gene functional attributes. Finally, by setting up a medication recommendation module based on the medication information of reference patients, medication recommendation information for the target patient is generated, thereby achieving medication recommendation for the target patient. This invention determines the individual suitability of various mental illness treatment drugs by performing genetic testing on the target patient and various historical patients. Furthermore, by simultaneously examining the similarity of clinical manifestations between the target patient and various historical patients, as well as the similarity of individual suitability of various mental illness treatment drugs, reference patients with medication consistency with the target patient are identified, ultimately achieving accurate medication recommendations. Attached Figure Description

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the structure of a SNP site detection kit for predicting medication use in the treatment of mental illnesses, according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the gene detection module according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the drug suitability analysis module according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of a reference patient analysis module according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the medication recommendation module according to an embodiment of the present invention; Figure 6 This is a flowchart illustrating the steps of a method for predicting medication use in the treatment of mental illnesses using an SNP site detection kit, as described in an embodiment of the present invention. Detailed Implementation

[0021] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings.

[0022] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0023] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0024] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0025] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0026] Although operations or steps are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations or steps to be performed in the specific order or serial order shown, or requiring all of the shown operations or steps to be performed to obtain the desired result. In the embodiments of the present invention, these operations or steps may be performed serially; they may be performed in parallel; or a portion of these operations or steps may be performed.

[0027] The following will provide a detailed description, with reference to the accompanying drawings, of a SNP site detection kit for predicting medication use in the treatment of mental illnesses provided by an embodiment of the present invention.

[0028] Please see Figure 1 The diagram illustrates the architecture of a SNP site detection kit for predicting medication use in the treatment of mental illnesses, comprising a data acquisition module 1, a gene detection module 2, a drug suitability analysis module 3, a reference patient analysis module 4, and a medication recommendation module 5, specifically including: Data acquisition module 1 is used to acquire clinical data of target patients suffering from a certain mental illness, as well as clinical data and medication information of historical patients suffering from the same type of mental illness as the target patients.

[0029] Medication for treating mental illnesses can have varying outcomes depending on individual differences. It is necessary to monitor individual clinical information during medication administration to ensure the accuracy of medication prediction and to facilitate safe medication use based on clinical information.

[0030] In a specific example, data acquisition module 1 is used to read the electronic medical records of a target patient suffering from a certain mental illness (such as schizophrenia) to obtain the patient's clinical data. This clinical data includes: basic information such as age, gender, weight, height, and BMI (body mass index); disease diagnosis and treatment data such as disease diagnosis (e.g., paranoid / hebephrenic schizophrenia), disease stage, and symptom scores (PANSS scale, SANS negative symptom scale); and physiological and biochemical data such as liver and kidney function (ALT, AST, Cr, eGFR), blood glucose, blood lipids, electrocardiogram, and complete blood count (granulocyte count).

[0031] Simultaneously, the data acquisition module 1 reads the electronic medical records of all historical patients with the same type of mental illness as the target patient, and obtains the aforementioned clinical data and medication information of each historical patient. The medication information includes: records of previous antipsychotic medication use (drug name, dosage, course of treatment), efficacy feedback (effective / ineffective), and history of adverse reactions (such as extrapyramidal reactions, weight gain), etc.

[0032] Gene testing module 2 is used to perform gene testing on the target patient and each historical patient to obtain gene testing results.

[0033] In predicting patient medication use, it is necessary to determine the drug metabolism, efficacy, and adverse reactions of the drug in individual patients. Therefore, it is necessary to conduct relevant gene testing on patients to obtain gene testing data, thereby providing a basis for phenotypic inference and functional scoring.

[0034] Since the prediction of medication for treating mental illnesses is based on known drugs, the purpose of genetic testing on patients is to determine an individual's metabolism, efficacy, and adverse reactions to known drugs. Therefore, when conducting genetic testing on target patients and patients with a history of illness, genes associated with known drugs should be selected for testing.

[0035] The purpose of gene testing for genes known to be associated with drugs is primarily to infer gene functional status and thus link it to specific phenotypes by detecting variations in SNP sites. Gene SNP sites have clearly defined functions; for example, SNP sites located in coding regions may alter protein structure, while SNP sites located in promoters or regulatory regions may affect gene expression levels. When conducting gene testing for genes known to be associated with drugs, the selected SNP sites mainly need to target psychotropic drugs, screening for SNP sites directly related to drug metabolism, efficacy, and toxicity. This is used to characterize the drug's metabolism, efficacy, and adverse reactions, providing a genetic basis for drug use prediction.

[0036] In one possible implementation, such as Figure 2 As shown, the gene detection module 2 includes a sample acquisition unit 21, a SNP site determination unit 22, and a gene detection unit 23, specifically comprising: The sample acquisition unit 21 is used to acquire gene test samples from the target patient and various historical patients.

[0037] The sample acquisition unit 21 acquires gene testing samples from the target patient and various historical patients. The gene testing sample acquisition process involves swabbing the patient's buccal mucosa with an oral swab to collect exfoliated cells from the patient's oral mucosa, thereby obtaining the patient's gene testing sample.

[0038] The SNP site determination unit 22 is used to identify SNP sites of genes associated with various mental illness treatment drugs as SNP sites to be detected.

[0039] The SNP site identification unit 22 identifies genes associated with known drugs for treating mental illnesses, i.e., various mental illness treatment drugs. Table 1 shows the associated genes of some known drugs for treating a certain mental illness. Then, based on the CPIC (Clinical Pharmacogenetics Implementation Consortium) database, SNP sites that have been proven to be significantly associated with the aforementioned drugs are selected from the genes associated with known drugs, and these SNP sites are used as the SNP sites to be detected. Table 2 shows some SNP sites significantly associated with the drugs among the genes associated with known drugs.

[0040] Table 1 Drug-associated genes Table 2. SNP sites significantly associated with drugs Gene detection unit 23 is used to perform gene detection on the SNP site to be detected based on the gene detection sample, and obtain gene detection results. The gene detection results include at least the genotype of the SNP site to be detected.

[0041] The gene testing unit 23 performs gene testing on the identified SNP loci based on the obtained gene testing samples from the target patient and various historical patients, thereby obtaining the gene testing results. The gene testing method can employ ultra-high-throughput SNP genotyping technology, such as multiplex quantitative PCR. Specific primers and probes are designed for the identified SNP loci, and genotype is determined through PCR amplification and fluorescence signal acquisition, thus identifying the genotype corresponding to the SNP locus. The testing process must comply with a CLIA-certified quality control system to ensure the accuracy of the gene testing results.

[0042] Drug suitability analysis module 3 is used to determine the individual suitability of various mental illness treatment drugs based on the genotype distribution of each SNP site of the genes associated with the drugs in the gene detection results, and in combination with the functional attributes of the genes associated with the drugs.

[0043] In gene testing results, the genotype of each SNP locus is directly represented by the base composition of each testing site, mainly divided into two categories: homozygotes and heterozygotes. Homozygotes are those where the two alleles at a given SNP locus have identical bases, generally represented by two identical bases, such as AA or GG. They can be further divided into two subtypes: homozygous wild-type, where both alleles contain the most common "wild-type bases" in the population; and homozygous mutant, where both alleles contain mutated "mutant bases" (bases different from the wild-type). Heterozygotes are those where the two alleles at a given SNP locus have different bases, one wild-type and the other mutant, generally represented by two different bases, such as AG. Table 3 shows the genotypes of some SNP loci in the gene testing results of individual A.

[0044] Table 3 Genotypes of each SNP locus of the gene The purpose of gene testing is to determine the functional status of genes corresponding to different functional attributes of drugs. Gene function is primarily reflected in the genotype of the corresponding SNP locus. For example, homozygotes typically correspond to a more stable phenotype (e.g., completely normal or significantly reduced enzyme activity), while heterozygotes often exhibit phenotypes intermediate between the two homozygotes (e.g., partially reduced enzyme activity), depending on the functional effect of the mutation. Therefore, functional scores can be quantified based on the genotype distribution of each SNP locus of each gene associated with various psychiatric medications in the gene testing results. Simultaneously, by combining the functional attributes of multiple genes associated with various psychiatric medications—which reflect the drug's metabolic capacity, efficacy, and adverse reaction risk in an individual—an assessment of individual drug suitability can be conducted. Individual suitability reflects the comprehensive suitability of an individual patient for psychiatric medications across different gene functional attributes.

[0045] In one possible implementation, such as Figure 3 As shown, the drug suitability analysis module 3 includes a functional score analysis unit 31, a gene classification unit 32, an attribute score analysis unit 33, and an individual suitability analysis unit 34, specifically: The functional score analysis unit 31 is used to encode the genotypes of each SNP locus of the genes associated with various mental illness treatment drugs in the gene detection results, and to determine the functional score of the genes associated with various mental illness treatment drugs based on the encoding value of the genotype of each SNP locus.

[0046] For target patients and patients with a history of mental illness, the genotypes of each SNP locus in the genes associated with various medications for treating mental illnesses are encoded in their gene testing results, and the genotype of each SNP locus is converted into a numerical value. Considering that a single gene may contain multiple SNP loci, the encoded values ​​of multiple loci need to be fused to calculate the functional score of the gene, in order to quantify the overall functional status of the gene.

[0047] In one possible implementation, the aforementioned functional score analysis unit 31 is specifically used for: First, for each SNP locus of the gene associated with various mental illness treatment drugs, the genotypes in the gene detection results are encoded as the first value, the second value, and the third value, respectively, with the first value, the second value, and the third value increasing sequentially.

[0048] In a specific example, for the target patient and various historical patients, based on the genotypes of each SNP locus of the genes associated with various mental illness treatment drugs in their gene testing results, homozygous wild type is encoded as 0, heterozygous type as 1, and homozygous mutant type as 2, thus obtaining the encoding value for each genotype. Taking the rs1135822 locus corresponding to the CYP2D6 gene as an example, the encoding value for genotype GA (heterozygous) is 1; the encoding value for genotype AA (homozygous wild type) is 0; and the encoding value for genotype GG (homozygous mutant) is 2.

[0049] Secondly, based on the weighted weights of each SNP site of each gene, the genotype coding values ​​of each SNP site of the genes associated with various mental illness treatment drugs are weighted and accumulated to obtain the functional scores of the genes associated with various mental illness treatment drugs.

[0050] Considering that the genotypes of different SNP sites in the same gene have different effects on gene function, the weighted weights of each SNP site of each gene are obtained based on the degree of influence of different SNP sites on gene function. The coding values ​​of the genotypes of each SNP site of the drug-associated gene are then weighted and accumulated using these weighted weights to determine the functional score of the drug-associated gene.

[0051] In a specific example, the weighting of each SNP locus is determined with reference to the CPIC database. Specifically, the eQTL effect values ​​of each SNP locus are read from the public database NHGRI-EBI GWAS Catalog, and then the β values ​​in the eQTL effect values ​​are standardized using Z-score standardization. These standardized β values ​​are then used as the functional weights of each SNP locus. Based on the weighting of each SNP locus, the genotype coding values ​​of each SNP locus of the drug-associated gene are weighted and summed to obtain the functional score of each gene. : In the formula: This represents the coding value of the i-th SNP site of each gene associated with drugs for the treatment of mental illnesses; This represents the weight of the i-th SNP site of each gene associated with drugs for the treatment of mental illnesses; This indicates the number of SNP sites for each gene associated with drugs used to treat mental illnesses.

[0052] Gene classification unit 32 is used to classify all genes associated with various mental illness treatment drugs according to their functional attributes, thereby obtaining several attribute gene categories.

[0053] A drug may be associated with multiple genes in the human body, and different genes correspond to different functional scores. When analyzing the applicability of a specific drug in an individual patient, it is necessary to evaluate it from multiple aspects such as metabolic capacity and efficacy. Since different genes play different functions, it is necessary to classify all genes according to their functional attributes (referring to the associated functional attributes of drugs for treating mental illnesses), and then determine the applicability of the drug based on the scores of different gene categories.

[0054] In one possible implementation, the functional attributes of the gene include metabolic capacity, therapeutic effect, and adverse reaction. The gene classification unit 32 is specifically used to classify all genes associated with various mental illness treatment drugs into metabolic capacity, therapeutic effect, and adverse reaction categories according to their functional attributes, thereby obtaining several attribute gene categories.

[0055] When characterizing drugs, genes are used based on their functional attributes, which refer to the associated functions of drugs for treating mental illnesses. These functional attributes can manifest as the corresponding drug's metabolic capacity, efficacy, and adverse reactions in an individual. Table 4 shows the functional attributes of genes associated with some drugs.

[0056] In a specific example, referring to the CPIC database, the functional attributes of various genes associated with different medications for treating mental illnesses are retrieved. Based on these functional attributes, all genes associated with each medication are categorized into three types: metabolic capacity, therapeutic effect, and adverse reactions. It should be understood that the functional attributes of a gene associated with a drug may simultaneously include two or three of these attributes. In such cases, the gene needs to be classified into multiple categories, meaning it may belong to multiple attribute gene categories (e.g., two or three).

[0057] Table 4 Functional properties of drug-associated genes The attribute scoring analysis unit 33 is used to determine the attribute score of each attribute gene category based on the functional scores of all genes in each attribute gene category.

[0058] Based on the functional scores of different genes within each gene class, an attribute score is calculated for each gene class separately. The higher the functional score of a different gene within a gene class, the higher the attribute score for that gene class.

[0059] In a specific example, the attribute score analysis unit 33 is specifically used to: calculate the mean of the functional scores of all genes in each attribute gene category, thereby obtaining the attribute score of each attribute gene category. That is, to calculate the mean of the functional scores of all genes corresponding to each gene category, and use this mean as the attribute score of each gene category.

[0060] Individual suitability analysis unit 34 is used to determine the individual suitability of various mental illness treatment drugs based on the attribute scores of all attribute gene categories associated with various mental illness treatment drugs.

[0061] Each type of drug for treating mental illness is associated with multiple genes. All genes together characterize the applicability of the corresponding drug. According to the functional attributes of the genes, each functional attribute can express the applicability of the drug, and the final applicability requires a combined analysis of the performance of multiple functional attributes.

[0062] In one possible implementation, the individual suitability analysis unit 34 is specifically used to: calculate the mean of the attribute scores of all attribute gene categories associated with various mental illness treatment drugs, and the individual scores of various mental illness treatment drugs; normalize the individual scores and perform negative correlation mapping to obtain the individual suitability of various mental illness treatment drugs.

[0063] In a specific example, the suitability of each drug in an individual is reflected in three functional attributes: metabolic capacity, therapeutic effect, and adverse reactions. The mean score of the attribute scores for each of the three gene types corresponding to each drug is calculated, and this mean is used as the individual score for the drug. This allows us to determine the individual score for each drug. Since the individual score is calculated from the coding value of the SNP locus genotype, a higher degree of genotype mutation results in a larger coding value, thus a higher drug score in the individual, and a worse suitability for that individual. Therefore, the individual scores for all drugs are normalized separately, specifically using the maximum-minimum normalization method to obtain the normalized results. At this time As the corresponding drug suitability for an individual, the individual suitability of various drugs can be determined.

[0064] Reference Patient Analysis Module 4 is used to identify reference patients among historical patients based on the similarity of clinical data between the target patient and each historical patient, as well as the similarity of individual applicability of various mental illness treatment drugs.

[0065] The aforementioned drug suitability analysis module 3, through genetic analysis, determines the individual suitability of various mental illness medications. However, the actual effectiveness of these medications may vary depending on clinical factors such as the patient's physiological state and disease characteristics. Generally, individuals with similar clinical manifestations (e.g., similar physiological indicators and similar conditions) exhibit a certain degree of similarity in medication use. In such cases, by analyzing the similarity of clinical data between the target patient and historical patients, as well as the similarity of individual suitability of various mental illness medications, reference patients—i.e., similar individuals—can be identified among historical patients, thereby enabling medication prediction and guidance.

[0066] In one possible implementation, such as Figure 4 As shown, the aforementioned reference patient analysis module 4 includes a clinical manifestation feature construction unit 41, a clinical manifestation difference analysis unit 42, an adaptation difference analysis unit 43, a medication similarity analysis unit 44, and a reference patient determination unit 45, specifically including: The clinical manifestation feature construction unit 41 is used to construct clinical manifestation features for the target patient and each historical patient based on clinical data of the target patient and each historical patient, respectively.

[0067] Based on the physiological data (such as age, weight, liver and kidney function), disease status data (such as disease course, complications, PANSS baseline score), and lifestyle data (such as diet, smoking, and alcohol consumption history) from the clinical data of the target patient and various historical patients, some or all of these data can be selected as feature data to construct the corresponding clinical manifestation characteristics of the patient. In constructing clinical manifestation characteristics, numerical data (such as age, weight, and PANSS baseline score) from the physiological, disease status, and lifestyle data can be directly used as feature values ​​for the corresponding numerical data items. For non-numerical data (disease course, complications, diet, smoking, and alcohol consumption habits), these non-numerical data need to be numerically converted, and the converted values ​​are used as feature values ​​for the corresponding non-numerical data items. For example, the disease course typically includes four main stages: the incubation period, the prodromal period, the symptom onset period, and the resolution period. These four main stages can be assigned numbers 0, 1, 2, 3, and 4, respectively. For example, when a certain complication exists, its corresponding feature value is set to 1, and vice versa; when an unhealthy diet exists, its corresponding feature value is set to 1, and vice versa; when there is a history of smoking, its corresponding feature value is set to 1, and vice versa. The clinical manifestation characteristics of each patient are constructed by using the feature values ​​of all the above data items in the physiological data, disease state data, and lifestyle data from each patient's clinical data.

[0068] In a specific example, age, weight, disease duration, and baseline PANSS score were selected from the clinical data of the target patient and each historical patient to constitute the corresponding clinical manifestation characteristics. It should be understood that the disease duration here refers to the stage of disease progression recorded at admission or before the start of treatment for both the target patient and each historical patient.

[0069] The clinical manifestation difference analysis unit 42 is used to determine the clinical manifestation differences between the target patient and each historical patient based on the differences in clinical manifestation characteristics between the target patient and each historical patient.

[0070] The differences in various characteristic values ​​of clinical manifestations between the target patient and each historical patient are calculated to determine the differences in clinical manifestations between the target patient and each historical patient. The greater the difference in the characteristic values ​​of clinical manifestations between the target patient and historical patients, the greater the difference in their clinical manifestations. Furthermore, to accurately quantify the differences in clinical manifestations between the target patient and each historical patient, reference weights are assigned to different characteristic values ​​based on their importance. The sum of the reference weights for all characteristic values ​​is 1. These reference weights are then used to weight the differences in the characteristic values ​​of clinical manifestations between the target patient and historical patients, thus ultimately yielding the differences in their clinical manifestations.

[0071] In one possible implementation, the aforementioned clinical manifestation difference analysis unit 42 is specifically used to: obtain the difference values ​​of each feature item in the clinical manifestation characteristics between the target patient and each historical patient; and perform a weighted summation of the difference values ​​of all feature items in the clinical manifestation characteristics to obtain the clinical manifestation differences between the target patient and each historical patient.

[0072] In a specific example, the reference weights for age, weight, disease duration, and baseline PANSS score in the clinical manifestation features are set to 0.25, 0.2, 0.35, and 0.2, respectively. The differences in each feature among the clinical manifestation features between the target patient and each historical patient are calculated to obtain the differences in age, weight, disease duration, and baseline PANSS score. These differences are then weighted and summed using the reference weights of each feature to obtain the clinical manifestation differences between the target patient and each historical patient. : In the formula: This represents the difference in clinical presentation between target patient i and the j-th historical patient; This represents the value of the k-th feature among the clinical manifestations of target patient i; This represents the value of the k-th feature among the clinical manifestations of the j-th historical patient; This represents the reference weight of the k-th feature among the clinical manifestations. ; This indicates the number of characteristic items in the clinical manifestations. ; This represents a positive minimum value, used to prevent the denominator from being 0. The fitness difference analysis unit 43 is used to determine the fitness difference of medication between the target patient and each historical patient based on the individual fitness differences of various mental illness treatment drugs between the target patient and each historical patient.

[0073] In one possible implementation, the fitness difference analysis unit 43 is specifically used to: determine the difference in individual fitness of the same mental illness treatment drug between the target patient and each historical patient to obtain the individual fitness difference; and determine the mean value of the individual fitness difference corresponding to all mental illness treatment drugs to obtain the difference in clinical performance between the target patient and each historical patient.

[0074] In a specific example, the difference in individual suitability for the same drug shown by the genetic testing results of the target patient and each historical patient is calculated as the individual suitability difference for the same drug between the target patient and each historical patient. Then, the mean of the individual suitability differences for all drugs between the target patient and each historical patient is calculated as the drug suitability difference between the target patient and each historical patient. : In the formula: This represents the difference in medication suitability between target patient i and the j-th historical patient; Indicates that the target patient i is related to the first... Individual suitability of certain medications for treating mental illnesses; This indicates that the j-th historical patient has a positive effect on the j-th historical patient. Individual suitability of certain medications for treating mental illnesses; This indicates the number of types of medications used to treat mental illnesses; This represents a positive minimum value, used to prevent the denominator from being 0. .

[0075] The medication similarity analysis unit 44 is used to determine the individual medication similarity between the target patient and each historical patient based on differences in clinical manifestations and medication suitability.

[0076] In a specific example, the differences in clinical presentation between the target patient and each historical patient are calculated. Differences in drug suitability average and the average value negative correlation normalization results As a measure of individual medication similarity between the target patient and each historical patient, among which... This represents an exponential function with the natural constant e as the base. When clinical manifestations differ... Differences in drug suitability The smaller the value of , the larger the value of individual medication similarity, and the higher the degree of individual medication similarity between the target patient and historical patients.

[0077] The reference patient determination unit 45 is used to determine the maximum individual medication similarity among all individual medication similarities, and uses the historical patient corresponding to the maximum individual medication similarity as the reference patient for the target patient among all historical patients. That is, the historical patient with the greatest individual medication similarity is selected and used as the reference patient for medication prediction and guidance for the current target patient.

[0078] The medication recommendation module 5 is used to generate medication recommendation information for target patients based on the medication information of reference patients.

[0079] A reference patient is a historical patient whose individual medication use is most similar to that of the current target patient. Based on the medication information of the reference patient, medication recommendation information for the target patient can be generated. The medication recommendation information may include data such as the type and dosage of the medication.

[0080] In one possible implementation, such as Figure 5 As shown, the medication recommendation module 5 includes a disease course period determination unit 51 and a medication recommendation unit 52, specifically: The same disease course time period determination unit 51 is used to determine the time period when the current disease course of the reference patient and the target patient is consistent as the same disease course time period.

[0081] In the reference patient's medication history, a time period (which could be one day or one week) consistent with the current target patient's disease course is identified as the same disease course period. Specifically, based on the disease course data in the clinical data of the reference patient and the target patient, the disease course data is numerically transformed (referring to the method for numerical transformation of disease course data in clinical manifestation feature construction unit 41), and the transformed numerical data is arranged according to a time sequence to obtain the disease course time sequence of the reference patient and the target patient. The Dynamic Time Warping (DTW) algorithm is used to match and align the disease course time sequence of the reference patient and the target patient. In the disease course time sequence of the reference patient, the moment corresponding to the value of the target patient's current disease course in its disease course time sequence is identified as the target moment. One day or one week after the target moment is identified as the time period consistent with the current disease course of the reference patient and the target patient, and this time period is identified as the same disease course period consistent with the current disease course of the reference patient and the target patient.

[0082] Medication recommendation unit 52 is used to generate medication recommendation information for the target patient based on the reference patient's medication information, including guidance on medication and dosage during the same disease course.

[0083] The medication information of the reference patient will be used to guide the medication and dosage of the reference patient during the same period of disease course. This information will be used as a guide for the current target patient's medication and dosage during the current course of disease, and medication recommendation information will be generated and sent to the doctor for reference.

[0084] Based on the above technical solution, the embodiments of the invention determine the individual applicability of various mental illness treatment drugs relative to the target patient and each historical patient by performing gene testing on the target patient and each historical patient. By simultaneously examining the similarity of clinical manifestations between the target patient and each historical patient as well as the similarity of individual applicability of various mental illness treatment drugs, reference patients with medication consistency with the target patient are identified. Finally, based on the medication information of the reference patients, medication recommendation information for the target patient is generated, thereby realizing accurate medication guidance and recommendations for patients with mental illnesses.

[0085] Based on the same inventive concept, embodiments of the present invention also provide a method for predicting medication use for treating mental illnesses using an SNP site detection kit, such as... Figure 6 As shown, the method includes: Acquire clinical data of target patients suffering from a certain mental illness, as well as clinical data and medication information of historical patients with the same type of mental illness as the target patients; Genetic testing was performed on the target patient and each historical patient to obtain the genetic testing results; Based on the genotype distribution of each SNP locus of the genes associated with various mental illness treatment drugs in the gene detection results, and combined with the functional attributes of the genes associated with various mental illness treatment drugs, the individual applicability of various mental illness treatment drugs is determined. Based on the similarity of clinical data between the target patient and each historical patient, as well as the similarity of individual applicability of various mental illness treatment drugs, reference patients among each historical patient were identified for the target patient. Based on the medication information of reference patients, medication recommendation information is generated for the target patients.

[0086] Based on the same inventive concept, embodiments of the present invention also provide a system for predicting medication use for mental illnesses using an SNP site detection kit. The system includes: a memory, a processor, and computer program code stored in the memory and running on the processor. When the processor executes the computer program code, the system can perform the steps implemented by each module in any of the aforementioned SNP site detection kits for predicting medication use for mental illnesses.

[0087] This invention can divide the system into functional modules based on the steps implemented by each module in the above-described reagent kit. For example, each module can correspond to a specific function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0088] Based on the same inventive concept, embodiments of the present invention also provide a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute the steps implemented by each module in any of the SNP site detection reagents for predicting medication for treating mental illnesses described above.

[0089] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer program code that, when executed on a computer, causes the computer to perform the steps implemented by each module in any of the aforementioned SNP site detection reagents for predicting medication for treating mental illnesses.

[0090] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A SNP site detection kit for predicting medication use in the treatment of mental illnesses, characterized in that, include: The data acquisition module is used to acquire clinical data of target patients suffering from a certain mental illness, as well as clinical data and medication information of historical patients suffering from the same type of mental illness as the target patients. The gene testing module is used to perform gene testing on the target patient and each historical patient separately to obtain gene testing results; The drug suitability analysis module is used to determine the individual suitability of various mental illness treatment drugs based on the genotype distribution of each SNP site of the gene associated with the various mental illness treatment drugs in the gene detection results, and in combination with the functional attributes of the genes associated with the various mental illness treatment drugs. The reference patient analysis module includes: a clinical manifestation feature construction unit, used to construct clinical manifestation features for the target patient and each historical patient based on clinical data of the target patient and each historical patient; a clinical manifestation difference analysis unit, used to obtain the difference value of each feature item in the clinical manifestation features between the target patient and each historical patient, and to perform a weighted summation of the difference values ​​of all feature items in the clinical manifestation features to obtain the clinical manifestation difference between the target patient and each historical patient; a fitness difference analysis unit, used to determine the difference value of individual applicability of the same mental illness treatment drug between the target patient and each historical patient, to obtain the individual applicability difference, and to determine the mean of the individual applicability difference corresponding to all mental illness treatment drugs, thereby obtaining the clinical manifestation difference between the target patient and each historical patient; a medication similarity analysis unit, used to determine the individual medication similarity between the target patient and each historical patient based on the clinical manifestation difference and the individual applicability difference; and a reference patient determination unit, used to determine the maximum individual medication similarity among all the individual medication similarities, and to use the historical patient corresponding to the maximum individual medication similarity as the reference patient for the target patient among the historical patients; The medication recommendation module includes: a disease course period determination unit, used to determine the period when the current disease course of the reference patient and the target patient is consistent as the disease course period; and a medication recommendation unit, used to generate medication recommendation information for the target patient based on the guidance medication and dosage in the reference patient's medication information during the disease course period. Specifically, based on the disease progression data in the clinical data of reference patients and target patients, the disease progression data is numerically transformed, and the transformed numerical data is arranged according to the time sequence to obtain the disease progression time sequence of reference patients and target patients. The dynamic time warping (DTW) algorithm is used to match and align the disease progression time sequence of reference patients and target patients. In the disease progression time sequence of reference patients, the moment when the value corresponding to the value of the current disease progression of the target patient in its disease progression time sequence is determined as the target moment. One day or one week after the target moment is taken as the period when the current disease progression of reference patients and target patients is consistent, and this period is taken as the same disease progression period when the current disease progression of reference patients and target patients is consistent.

2. The SNP site detection kit for predicting medication use in the treatment of mental illnesses according to claim 1, characterized in that, The drug suitability analysis module includes: The functional score analysis unit is used to encode the genotype of each SNP locus of the gene associated with various mental illness treatment drugs in the gene detection results, and to determine the functional score of the gene associated with various mental illness treatment drugs based on the encoding value of the genotype of each SNP locus. A gene classification unit is used to classify all genes associated with various mental illness treatment drugs according to their functional attributes, thereby obtaining several attribute gene categories. The attribute scoring analysis unit is used to determine the attribute score of each attribute gene category based on the functional scores of all genes in each attribute gene category. The individual suitability analysis unit is used to determine the individual suitability of various mental illness treatment drugs based on the attribute scores of all attribute gene categories associated with various mental illness treatment drugs.

3. The SNP site detection kit for predicting medication use in the treatment of mental illnesses according to claim 2, characterized in that, The functional score analysis unit is specifically used for: For each SNP locus of the gene associated with various drugs for the treatment of mental illnesses, the genotypes in the gene detection results are respectively encoded as the first value, the second value, and the third value, with the first value, the second value, and the third value increasing sequentially. Based on the weighted weights of each SNP site of each gene, the genotype coding values ​​of each SNP site of the genes associated with various mental illness treatment drugs are weighted and accumulated to obtain the functional scores of the genes associated with various mental illness treatment drugs.

4. The SNP site detection kit for predicting medication use in the treatment of mental illnesses according to claim 2, characterized in that, The functional attributes of the gene include metabolic capacity, therapeutic effect, and adverse reactions, and the gene classification unit is specifically used for: All genes associated with various drugs for treating mental illnesses are classified according to their functional attributes into metabolic capacity, therapeutic effect, and adverse reaction categories, thereby obtaining the aforementioned gene categories.

5. A SNP site detection kit for predicting medication use in the treatment of mental illnesses according to claim 2, characterized in that, The individual suitability analysis unit is specifically used for: Calculate the mean of the attribute scores of all attribute gene categories associated with various mental illness treatment drugs to obtain the individual scores of various mental illness treatment drugs; After normalizing the individual scores and performing negative correlation mapping, the individual applicability of various mental illness treatment drugs is obtained.

6. The SNP site detection kit for predicting medication use in the treatment of mental illnesses according to claim 1, characterized in that, The gene detection module includes: The sample acquisition unit is used to acquire gene testing samples from the target patient and various historical patients. The SNP site determination unit is used to identify SNP sites of genes associated with various drugs for the treatment of mental illnesses as SNP sites to be detected. A gene detection unit is used to perform gene detection on the SNP site to be detected based on the gene detection sample, and obtain gene detection results, wherein the gene detection results include at least the genotype of the SNP site to be detected.

Images