Aging degree evaluation method, device, equipment and medium

Abstract

The invention discloses an aging degree evaluation method, device, equipment and medium, and relates to the field of life health, and the method comprises the following steps: respectively carrying out Olink proteomics sequencing and transcriptomics sequencing on a target sample of a target object to obtain a target standardized protein expression value and a target gene relative expression quantity; based on the target standardized protein expression value and the target gene relative expression quantity, extracting a current target marker sample corresponding to the target marker name from the target sample by using a target machine learning algorithm; wherein the target marker names are a target gene level marker name, a target protein level marker name and a target gene and protein level combined marker name which are determined by using the target machine learning algorithm in advance; and obtaining an aging degree evaluation result of the target object by using the current target marker sample and a target aging evaluation model. Through the scheme, the accuracy of aging degree evaluation is improved.

Description

Technical Field

[0001] The present invention relates to the field of life and health, and in particular to a method, device, equipment and medium for evaluating the degree of aging. Background Art

[0002] With the acceleration of aging in my country, studying the characteristics of aging and its specific markers is one of the frontiers of scientific research. Aging is a multi-factorial and complex physiological change process, which is closely related to the occurrence and development of various chronic diseases such as cardiovascular disease, metabolic-related diseases and cancer. The aging of human cells is a result of cells being triggered in a stress response, which is characterized by cell cycle arrest, secretion of various pro-inflammatory cytokines, DNA damage, genomic instability and metabolic adaptation. At the same time, there are changes in biomarkers of cellular aging.

[0003] In recent years, with the development of multi-omics sequencing technology, the search for new aging markers has broad prospects for clinical translational applications in assessing the degree of aging, predicting biological age and its related disease risks, finding suitable targets and intervening to delay aging.

[0004] In summary, how to improve the accuracy of aging degree assessment is a problem to be solved in this field. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for evaluating the degree of aging, so as to improve the accuracy of the evaluation of the degree of aging. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a method for assessing the degree of aging, comprising:

[0007] Olink proteomic sequencing and transcriptomic sequencing were performed on the target samples of the target subjects to obtain the target standardized protein expression value and the relative expression of the target gene;

[0008] Based on the target standardized protein expression value and the relative expression amount of the target gene, a current target marker sample corresponding to the target marker name is extracted from the target sample using a target machine learning algorithm; wherein the target marker name is a target gene level marker name, a target protein level marker name, or a target gene and protein level combined marker name determined in advance using the target machine learning algorithm;

[0009] The current target marker sample and the target aging assessment model are used to obtain an aging degree assessment result of the target object.

[0010] Optionally, the target samples of the target object are subjected to Olink proteomic sequencing and transcriptomic sequencing respectively to obtain the target standardized protein expression value and the relative expression amount of the target gene, including:

[0011] Performing Olink proteomic sequencing on a first target sample of the target object to obtain a target standardized protein expression value; wherein the first target sample is peripheral blood plasma of the target object;

[0012] The second target sample of the target object is subjected to transcriptomic sequencing to obtain the relative expression level of the target gene; wherein the second target sample is a mixture of peripheral blood mononuclear cells of the target object and a total RNA extraction reagent.

[0013] Optionally, performing Olink proteomics sequencing on the first target sample of the target object to obtain a target standardized protein expression value includes:

[0014] Performing Olink proteomic sequencing on the first target sample of the target subject to obtain the original protein expression value;

[0015] The original protein expression values ​​are standardized and logarithmically transformed to obtain target standardized protein expression values.

[0016] Optionally, the target gene level markers are named B2M, PRPF38B, SIRT7, LIME1, TMEM123 and RPL17-C18orf32, the target protein level markers are named COL9A1, TREM2, CXCL14, SPON1, WNT9A and CXCL17, and the target gene and protein level combined markers are named CXCL17, ITGB5, TREM2, WNT9A, CXCL14, COLEC12, FGF5, CD248, ERV3-ZNF117 and SEC62.

[0017] Optionally, get the target marker name, including:

[0018] Determine each historical marker sample based on the historical standardized protein expression value and the historical gene relative expression; wherein the historical marker samples include historical gene level marker samples and historical protein level marker samples;

[0019] The historical marker samples are analyzed using a LASSO regression algorithm to obtain each post-screening marker sample;

[0020] The target machine learning algorithm is used to evaluate the importance score of each of the screened marker samples in the target aging assessment model, so as to determine the name of the target marker according to the importance score.

[0021] Optionally, obtain a target aging assessment model, including:

[0022] An initial aging assessment model is established using the historical marker samples and the target machine learning algorithm; the dependent variable of the initial aging assessment model is age grouping;

[0023] The parameters of the initial aging assessment model are optimized using a random search algorithm to obtain a target aging assessment model.

[0024] Optionally, the initial aging assessment model includes an initial gene aging assessment model whose independent variable is the relative gene expression amount, an initial protein aging assessment model whose independent variable is the standardized protein expression value, and an initial gene-protein combined aging assessment model whose independent variables are the relative gene expression amount and the standardized protein expression value.

[0025] In a second aspect, the present application discloses a device for assessing the degree of aging, comprising:

[0026] The Omics sequencing module is used to perform Olink proteomics sequencing and transcriptomics sequencing on the target samples of the target object to obtain the target standardized protein expression value and the relative expression amount of the target gene;

[0027] A target marker extraction module, for extracting a current target marker sample corresponding to the target marker name from the target sample based on the target standardized protein expression value, the target gene relative expression amount, and using a target machine learning algorithm; wherein the target marker name is a target gene level marker name, a target protein level marker name, or a target gene and protein level combined marker name pre-determined using the target machine learning algorithm;

[0028] The aging degree assessment module is used to obtain the aging degree assessment result of the target object by using the current target marker sample and the target aging assessment model.

[0029] In a third aspect, the present application discloses an electronic device, including:

[0030] Memory, used to store computer programs;

[0031] A processor is used to execute the computer program to implement the steps of the aforementioned method for assessing the degree of aging.

[0032] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned disclosed method for assessing the degree of aging are implemented.

[0033] The beneficial effects of the present application are as follows: the present application performs Olink proteomic sequencing and transcriptomic sequencing on the target samples of the target object, respectively, to obtain the target standardized protein expression value and the target gene relative expression amount; based on the target standardized protein expression value and the target gene relative expression amount, and using the target machine learning algorithm, a current target marker sample corresponding to the target marker name is extracted from the target sample; wherein the target marker name is the target gene level marker name, the target protein level marker name, and the target gene and protein level combined marker name determined in advance by the target machine learning algorithm; and the current target marker sample and the target aging assessment model are used to obtain the aging degree assessment result of the target object. It can be seen that Olink proteomic sequencing can detect the concentrations of multiple proteins in plasma. These proteins play important physiological functions in organisms, and changes in their concentrations are often closely related to the aging process. Transcriptomic sequencing can comprehensively reveal the expression of genes, including those related to aging regulation. Differences in gene expression can reflect changes in cell state and function, and provide important clues for aging assessment. Therefore, this application performs Olink proteomic sequencing and transcriptomic sequencing on the target samples of the target objects, and the obtained target standardized protein expression values ​​and target gene relative expression levels provide a basis for subsequent aging degree assessment; further, the target marker name is the target gene level marker name, target protein level marker name, and target gene and protein level joint marker name determined in advance by the target machine learning algorithm. That is to say, the current target marker sample corresponding to the target marker name extracted from the target sample also includes protein dimension, gene dimension, and gene and protein joint dimension. The target aging assessment model can comprehensively analyze the aging process from multiple levels, thereby improving the accuracy of the assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0035] Figure 1 This is a flow chart of a method for assessing the degree of aging disclosed in this application;

[0036] Figure 2 A schematic diagram of ranking of a specific target marker name disclosed in this application;

[0037] Figure 3 A schematic diagram of a ROC curve of a specific protein level marker disclosed in this application;

[0038] Figure 4 A schematic diagram of a ROC curve of a specific gene level marker disclosed in this application;

[0039] Figure 5 A schematic diagram of a ROC curve of a specific gene and protein level joint marker disclosed in the present application;

[0040] Figure 6 A specific protein-age relationship diagram disclosed in this application;

[0041] Figure 7 A specific gene-age relationship diagram disclosed in this application;

[0042] Figure 8 A schematic diagram of a specific gene protein-age relationship disclosed in this application;

[0043] Fig. 9 This is a schematic diagram of the structure of an aging degree assessment device disclosed in this application;

[0044] Fig.10 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0046] With the acceleration of aging in my country, studying the characteristics of aging and its specific markers is one of the frontiers of scientific research. Aging is a multi-factor, complex physiological change process, which is closely related to the occurrence and development of various chronic diseases such as cardiovascular disease, metabolic-related diseases and cancer. The aging of human cells is a result of cells being triggered in a stress response, and its characteristics are cell cycle arrest, secretion of various pro-inflammatory cytokines, DNA damage, genomic instability and metabolic adaptation. At the same time, there are changes in biomarkers of cellular aging.

[0047] In recent years, with the development of multi-omics technology, the search for new aging markers has broad prospects for clinical translational applications in assessing the degree of aging, predicting biological age and its related disease risks, and finding suitable targets and intervening to delay aging.

[0048] To this end, the present application provides a corresponding aging degree assessment scheme to improve the accuracy of aging degree assessment.

[0049] See also Figure 1 As shown, the embodiment of the present application discloses a method for assessing the degree of aging, comprising:

[0050] Step S11: performing Olink proteomic sequencing and transcriptomic sequencing on the target samples of the target object to obtain the target standardized protein expression value and the relative expression amount of the target gene.

[0051] In this embodiment, the target samples of the target object are subjected to Olink proteomic sequencing and transcriptomic sequencing respectively to obtain the target standardized protein expression value and the relative expression amount of the target gene, including: performing Olink proteomic sequencing on the first target sample of the target object to obtain the target standardized protein expression value; wherein the first target sample is the plasma of the peripheral blood of the target object; performing transcriptomic sequencing on the second target sample of the target object to obtain the relative expression amount of the target gene; wherein the second target sample is a mixture of peripheral blood mononuclear cells of the target object and a total RNA extraction reagent.

[0052] The process of obtaining the target standardized protein expression value: First, obtain the first target sample of the target object. The specific process is: collect 5mL of peripheral blood from the target object under sterile conditions, place the peripheral blood in a heparin anticoagulation tube, obtain peripheral blood plasma by centrifugation at 1500rpm for 10min, and immediately store the peripheral blood plasma in a refrigerator at minus 80°C, so as to obtain the first target sample; Next, perform Olink proteomics sequencing on the first target sample of the target object to obtain the target standardized protein expression value. Olink proteomics has the advantages of high throughput, low volume, fast speed, targeting, high sensitivity, wide dynamic range, automation, liquid biopsy, etc. Specifically, Olink Explore 384 Inflammation+Target 96 Oncology II is used to detect the concentration of 384+96 proteins in peripheral blood plasma. The Proximity Extension Assay in Olink The proximity extension assay (PEA) technology is to design a pair of specific matching antibodies when detecting each antigen (protein) to ensure the specific binding of the antigen and antibody. When the antibody specifically binds to the corresponding antigen, it forms a nucleic acid double strand that can be detected by qPCR (Quantitative Real-time polymerase chain reaction). With the help of the ultra-high-throughput microfluidic qPCR platform, the PEA technology can detect the expression levels of multiple proteins in the same sample well at the same time point.

[0053] The process of obtaining the relative expression of the target gene: First, obtain the second target sample of the target object. Specifically, use phosphate buffer solution (PBS) to resuspend the lower layer cells and transfer them to a centrifuge tube. Take another new centrifuge tube and add 15mL of lymphocyte separation solution. Slowly add the diluted blood cells to the upper layer of lymphocyte separation solution, centrifuge at 2500rpm, increase speed by 5, decrease speed by 5, centrifuge for 25min, extract the buffy coat layer and transfer it to another centrifuge tube, add PBS to wash the cells, centrifuge at 1500rpm, increase speed by 9, decrease speed by 9, centrifuge for 10min, and the precipitate obtained is the peripheral blood mononuclear cells (PBMCs). 1 mL of TRIzol (i.e., total RNA extraction reagent) was added to PBMCs to obtain a mixture of peripheral blood mononuclear cells of the target object and the total RNA extraction reagent, which was then frozen in liquid nitrogen to obtain a second target sample of the target object. Next, transcriptomic sequencing was performed on the second target sample of the target object to obtain the relative expression of the target gene. Specifically, RNA-seq was used to perform transcriptome sequencing on the collected second target sample. RNA-seq is a high-throughput sequencing technology that obtains transcript information of the sample through steps such as RNA extraction, cDNA library construction, and on-machine detection. The specific indicator used to measure the relative expression of the gene is FPKM (Fragments Per Kilobase of exon model per Million mapped fragments).

[0054] In this embodiment, the first target sample of the target object is subjected to Olink proteomic sequencing to obtain a target standardized protein expression value, including: performing Olink proteomic sequencing on the first target sample of the target object to obtain an original protein expression value; performing normalization and logarithmic transformation on the original protein expression value to obtain a target standardized protein expression value. Specifically, when the first target sample of the target object is subjected to Olink proteomic sequencing, the original protein expression value is first obtained, and then the original protein expression value is normalized and logarithmically transformed, so that a target standardized protein expression value (Normalized Protein eXpression, i.e., NPX) can be obtained. The logarithmic transformation can be specifically log2 processing. The protein expression level usually spans several orders of magnitude. Direct data analysis may cause some highly expressed or lowly expressed proteins to be statistically neglected. By performing log2 transformation on the data, the data range can be narrowed, making the data more concentrated and convenient for statistical analysis. The data after log2 transformation is easier to interpret and understand, and the interpretation method is more in line with biological significance.

[0055] Step S12: Based on the target standardized protein expression value, the relative expression level of the target gene, and using a target machine learning algorithm, extract the current target marker sample corresponding to the target marker name from the target sample; wherein the target marker name is a target gene level marker name, a target protein level marker name, and a target gene and protein level combined marker name pre-determined using the target machine learning algorithm.

[0056] The target gene level marker name, the target protein level marker name, and the target gene and protein level joint marker name are determined in advance using the target machine learning algorithm. When the aging degree of the target object needs to be assessed, after obtaining the target standardized protein expression value and the target gene relative expression amount of the target object, the current target marker sample corresponding to the target marker name can be extracted from the first target sample and the second target sample based on the target standardized protein expression value and the target gene relative expression amount and using the target machine learning algorithm. In other words, the name of the current target marker sample is the target gene level marker name, the target protein level marker name, and the target gene and protein level joint marker name.

[0057] In this embodiment, the target gene level markers are named B2M, PRPF38B, SIRT7, LIME1, TMEM123 and RPL17-C18orf32, the target protein level markers are named COL9A1, TREM2, CXCL14, SPON1, WNT9A and CXCL17, and the target gene and protein level combined markers are named CXCL17, ITGB5, TREM2, WNT9A, CXCL14, COLEC12, FGF5, CD248, ERV3-ZNF117 and SEC62.

[0058] It should be noted that the names of target markers are divided into three categories. The first is the name of the target gene level marker, which are B2M (β2-microglobulin), PRPF38B (pre-mRNA processing factor 38B), SIRT7 (sirtuin 7), LIME1 (Lck interacting transmembrane adaptor 1), TMEM123 (transmembrane protein 123) and RPL17-C18orf32 (ribosomal protein L17 and C18orf32 gene fusion / adjacent region); the second is the name of the target protein level marker, which are COL9A1 (collagen type IX alpha 1 chain, The first type is the name of the joint markers of target gene and protein level, which are CXCL17, ITGB5 (Integrin Beta 5), ​​TREM2, WNT9A, CXCL14, COLEC12 (collectin subfamily member 12), FGF5 (Fibroblast Growth Factor 5), and mitochondrial growth factor 5 (MGF-1). 5), CD248 (CD248 molecule), ERV3-ZNF117 (fusion or adjacent region of ERV3 gene and ZNF117 gene) and SEC62 (translocation protein SEC62).

[0059] In this embodiment, obtaining the name of the target marker includes: determining each historical marker sample based on the historical standardized protein expression value and the historical gene relative expression; wherein the historical marker samples include historical gene level marker samples and historical protein level marker samples; using the LASSO regression algorithm to analyze the historical marker samples to obtain each post-screening marker sample; using the target machine learning algorithm to evaluate the importance score of each post-screening marker sample in the target aging assessment model, so as to determine the target marker name according to the importance score. When collecting historical gene level marker samples and historical protein level marker samples, it is necessary to first screen out a preset number n of healthy subjects, where n can specifically be 175, and the selection criteria for healthy subjects are:

[0060] 1) 18 years old ≤ ≤ 90 years old; 2) Normal blood pressure, pulse and body temperature, and no previous serious illness;

[0061] Exclusion criteria: 1) Respiratory diseases such as chronic bronchitis, pulmonary insufficiency, etc.; 2) Circulatory system diseases such as various heart diseases, hypertension, hypotension, limb arteriosclerosis, etc.; 3) Patients with blood system diseases, such as anemia, agranulocytosis, leukemia, lymphoma and other diseases; 4) Patients with immune system diseases, such as systemic lupus erythematosus, dermatomyositis, scleroderma, rheumatoid arthritis, Takayasu arteritis, etc.; 5) Patients with chronic skin diseases, allergic diseases and recurrent allergies; 6) Patients with mental illness; 7) Patients with various tumors; 8) Patients with various infectious diseases; 9) Pregnant and lactating women and patients taking long-term medication;

[0062] Next, a mixture of plasma, peripheral blood mononuclear cells and total RNA extraction reagents of each healthy subject was obtained to obtain historical standardized protein expression values ​​and historical gene relative expression amounts, respectively, and the historical standardized protein expression values ​​and historical gene relative expression amounts were divided into a training set and a test set at a ratio of 8:2. The names of target markers were divided into three categories, namely, target gene level marker names, target protein level marker names, and target gene and protein level combined marker names. The specific process is as follows:

[0063] 1) The process of obtaining the names of target gene level markers is as follows: First, taking gene expression as the independent variable and age group as the dependent variable, LASSO regression (Least absolute shrinkage and selection operator, a compression estimation algorithm) is used to analyze the preliminary number of compressed gene features. The lambda parameter with the smallest standard deviation was selected, and the first post-screening marker samples were obtained as TMEM123, RPL17-C18orf32, SIRT7, PRPF38B, LIME1, ERV3-1-ZNF117, B2M, CD248, SOX4, PANK2, CHML, SNAPC1, CEP164, BBS5, SEC62, KDM5C, TNIP2, and TTC31; secondly, the importance of the above-mentioned post-screening marker samples in the target aging assessment model was further evaluated using the target machine learning algorithm evaluation. In this embodiment, the target aging assessment model is specifically a target gene aging assessment model, among which TMEM123, RPL17-C18orf32, SIRT7, PRPF38B, B2M, and LIME1, etc., 6 genes have the highest importance. Therefore, the names of the target gene level markers are B2M, PRPF38B, SIRT7, LIME1, TMEM123, and RPL17-C18orf32;

[0064] 2) The process of obtaining the names of the target protein level markers is as follows: First, the historical standardized protein expression value was used as the independent variable and the age group was used as the dependent variable. LASSO regression analysis was used to preliminarily compress the number of protein features, and the λ parameter with the smallest standard deviation was selected. The marker samples after the second screening were CRLF1, CXCL17, ITGB5, MEPE, MK, PGF, WNT9A, TNFRSF11A, TREM2, FGF5, CD27, COLEC12, RET, OMD, SPON1, and MAD homolog5, CXCL14, COL9A1, CCL11, CTSC, CCL3, REG4, LGALS4, BTN2A1. In this embodiment, the target aging assessment model is specifically a proteomic machine learning model for assessing the level of aging. The importance of the above features in the pure proteomic model is further evaluated using the target machine learning algorithm. Among them, COL9A1, TREM2, CXCL17, CXCL14, WNT9A, SPON1 and other 6 proteins have the highest importance, so the names of the target protein level markers are COL9A1, TREM2, CXCL14, SPON1, WNT9A and CXCL17;

[0065] 3) The process of obtaining the names of the joint markers at the target gene and protein levels is as follows: For each of the first screening marker samples and each of the second screening marker samples, the importance of the above features in establishing a dual-omics machine learning model (i.e., the target aging assessment model in this embodiment) based on protein abundance and gene expression data was further evaluated using random forests, among which 7 proteins including CXCL17, TREM2, WNT9A, CXCL14, ITGB5, FGF5, and COLEC12 and 3 genes including CD248, SEC62, and ERV3-1-ZNF117 had the highest importance, so the names of the joint markers at the target gene and protein levels were CXCL17, ITGB5, TREM2, WNT9A, CXCL14, COLEC12, FGF5, CD248, ERV3-ZNF117, and SEC62;

[0066] For example Figure 2 A specific schematic diagram of the ranking of target marker names is shown, in which A represents the name of each target protein level marker, B represents the name of each target gene level marker, and C represents the name of each target gene and protein level combined marker.

[0067] Furthermore, the target machine learning algorithm can be a 50-fold cross validation algorithm, a preliminary comparison random forest algorithm, a logistic regression algorithm, a support vector machine algorithm, a decision tree algorithm, a linear discriminant analysis algorithm, a naive Bayes algorithm, and a multilayer perceptron algorithm. For example, the algorithm with the highest prediction accuracy is selected as the target machine learning algorithm, that is, the target machine learning algorithm is the preliminary comparison random forest algorithm.

[0068] In this embodiment, obtaining the target aging assessment model includes: establishing an initial aging assessment model using the historical marker samples and the target machine learning algorithm; the dependent variable of the initial aging assessment model is age grouping; and optimizing the parameters of the initial aging assessment model using a random search algorithm to obtain the target aging assessment model. The initial aging assessment model is established with age grouping as the dependent variable and using the historical marker samples and the target machine learning algorithm. Further, the parameters of the initial aging assessment model are optimized using a random search algorithm, such as optimizing the number of decision trees, the maximum depth, the leaf tree and other parameters, to obtain the target aging assessment model. After the model optimization stops, the performance of the model can be evaluated, such as the training set prediction AUC (Area Under Curve, i.e., the area under the ROC curve and the coordinate axis) reaches 0.98, and the test set AUC reaches 0.89.

[0069] For example Figure 3 A schematic diagram of a specific protein level marker ROC curve is shown, A is the ROC curve of each protein indicator, B is the ROC curve of the discovery set, and C is the ROC curve of the validation set; for example Figure 4 A schematic diagram of a specific gene-level marker ROC curve is shown, A is the ROC curve of each gene indicator, B is the ROC curve of the discovery set, and C is the ROC curve of the validation set; for example Figure 5 A schematic diagram of a specific ROC curve of a joint marker of gene and protein levels is shown, A is the ROC curve of each indicator, B is the ROC curve of the discovery set, and C is the ROC curve of the validation set.

[0070] Further, for example Figure 6 A specific protein-age relationship diagram is shown, in which the protein expression levels of six groups of different age groups, namely A (20-29), B (30-39), C (40-49), D (50-59), E (60-69) and F (over 70 years old), are screened, for example Figure 7 A specific gene-age relationship diagram is shown, showing the gene expression levels of six groups screened in different age groups, namely A (20-29), B (30-39), C (40-49), D (50-59), E (60-69) and F (over 70 years old), for example Figure 8 A specific schematic diagram of the gene protein-age relationship is shown, with the protein and gene expression levels of six groups of different age groups, namely A (20-29), B (30-39), C (40-49), D (50-59), E (60-69) and F (over 70 years old), being jointly screened.

[0071] In this embodiment, the initial aging assessment model includes an initial gene aging assessment model with the independent variable being the relative expression of the gene, an initial protein aging assessment model with the independent variable being the standardized protein expression value, and an initial gene protein joint aging assessment model with the independent variable being the relative expression of the gene and the standardized protein expression value. It can be understood that the initial aging assessment model includes an initial gene aging assessment model, an initial protein aging assessment model, and an initial gene protein joint aging assessment model, wherein the initial gene aging assessment model uses age grouping as the dependent variable and the relative expression of the gene as the independent variable, the initial protein aging assessment model uses age grouping as the dependent variable and the standardized protein expression value, and the initial gene protein joint aging assessment model uses age grouping as the dependent variable and the relative expression of the gene and the standardized protein expression value as the independent variable.

[0072] Step S13: using the current target marker sample and the target aging assessment model to obtain an aging degree assessment result of the target object.

[0073] Because the target aging assessment model uses age groups as dependent variables and historical marker samples as independent variables during the training process, after obtaining the current target marker samples, the current target marker samples and the target aging assessment model can be used to obtain the aging degree assessment results of the target object, that is, the aging degree assessment results represent the age group to which the predicted target object belongs.

[0074] The beneficial effects of the present application are as follows: the present application performs Olink proteomic sequencing and transcriptomic sequencing on the target samples of the target object, respectively, to obtain the target standardized protein expression value and the target gene relative expression amount; based on the target standardized protein expression value and the target gene relative expression amount, and using the target machine learning algorithm, a current target marker sample corresponding to the target marker name is extracted from the target sample; wherein the target marker name is the target gene level marker name, the target protein level marker name, and the target gene and protein level combined marker name determined in advance by the target machine learning algorithm; and the current target marker sample and the target aging assessment model are used to obtain the aging degree assessment result of the target object. It can be seen that Olink proteomic sequencing can detect the concentrations of multiple proteins in plasma. These proteins play important physiological functions in organisms, and changes in their concentrations are often closely related to the aging process. Transcriptomic sequencing can comprehensively reveal the expression of genes, including those related to aging regulation. Differences in gene expression can reflect changes in cell state and function, and provide important clues for aging assessment. Therefore, this application performs Olink proteomic sequencing and transcriptomic sequencing on the target samples of the target objects, and the obtained target standardized protein expression values ​​and target gene relative expression levels provide a basis for subsequent aging degree assessment; further, the target marker name is the target gene level marker name, target protein level marker name, and target gene and protein level joint marker name determined in advance by the target machine learning algorithm. That is to say, the current target marker sample corresponding to the target marker name extracted from the target sample also includes protein dimension, gene dimension, and gene and protein joint dimension. The target aging assessment model can comprehensively analyze the aging process from multiple levels, thereby improving the accuracy of the assessment.

[0075] See also Fig. 9 As shown, the embodiment of the present application discloses a device for assessing the degree of aging, comprising:

[0076] The omics sequencing module 11 is used to perform Olink proteomics sequencing and transcriptomics sequencing on the target samples of the target object to obtain the target standardized protein expression value and the relative expression amount of the target gene;

[0077] A target marker extraction module 12 is used to extract a current target marker sample corresponding to the target marker name from the target sample based on the target standardized protein expression value and the target gene relative expression amount, and using a target machine learning algorithm; wherein the target marker name is a target gene level marker name, a target protein level marker name, or a target gene and protein level combined marker name determined in advance using the target machine learning algorithm;

[0078] The aging degree assessment module 13 is used to obtain the aging degree assessment result of the target object by using the current target marker sample and the target aging assessment model.

[0079] The beneficial effects of the present application are as follows: the present application performs Olink proteomic sequencing and transcriptomic sequencing on the target samples of the target object, respectively, to obtain the target standardized protein expression value and the target gene relative expression amount; based on the target standardized protein expression value and the target gene relative expression amount, and using the target machine learning algorithm, a current target marker sample corresponding to the target marker name is extracted from the target sample; wherein the target marker name is the target gene level marker name, the target protein level marker name, and the target gene and protein level combined marker name determined in advance by the target machine learning algorithm; and the current target marker sample and the target aging assessment model are used to obtain the aging degree assessment result of the target object. It can be seen that Olink proteomic sequencing can detect the concentrations of multiple proteins in plasma. These proteins play important physiological functions in organisms, and changes in their concentrations are often closely related to the aging process. Transcriptomic sequencing can comprehensively reveal the expression of genes, including those related to aging regulation. Differences in gene expression can reflect changes in cell state and function, and provide important clues for aging assessment. Therefore, this application performs Olink proteomic sequencing and transcriptomic sequencing on the target samples of the target objects, and the obtained target standardized protein expression values ​​and target gene relative expression levels provide a basis for subsequent aging degree assessment; further, the target marker name is the target gene level marker name, target protein level marker name, and target gene and protein level joint marker name determined in advance by the target machine learning algorithm. That is to say, the current target marker sample corresponding to the target marker name extracted from the target sample also includes protein dimension, gene dimension, and gene and protein joint dimension. The target aging assessment model can comprehensively analyze the aging process from multiple levels, thereby improving the accuracy of the assessment.

[0080] Furthermore, an embodiment of the present application also provides an electronic device. Fig.10 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0081] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the aging degree assessment method performed by the electronic device disclosed in any of the aforementioned embodiments.

[0082] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0083] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0084] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0085] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the aging degree assessment method performed by the electronic device disclosed in any of the aforementioned embodiments, the computer program 222 can also further include a computer program that can be used to complete other specific tasks. In addition to data transmitted from an external device received by the electronic device, the data 223 can also include data collected by its own input and output interface 25.

[0086] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned disclosed method for assessing the degree of aging is implemented. The specific steps of the method can be referred to the corresponding contents disclosed in the aforementioned embodiments, and will not be described in detail here.

[0087] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0088] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be implemented directly with hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable EPROM (Erasable Programmable Read Only Memory), electrically erasable programmable EEPROM (Electrically Erasable Programmable read only memory), register, hard disk, removable disk, CD-ROM (Compact Disc Read-Only Memory), or any other form of storage medium known in the technical field.

[0089] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0090] The above is a detailed introduction to an aging degree assessment method, device, equipment and medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for assessing the degree of aging, characterized in that: include: Olink proteomic sequencing and transcriptomic sequencing were performed on the target samples of the target subjects to obtain the target standardized protein expression value and the relative expression of the target gene; Based on the target standardized protein expression value and the relative expression amount of the target gene, a current target marker sample corresponding to the target marker name is extracted from the target sample using a target machine learning algorithm; wherein the target marker name is a target gene level marker name, a target protein level marker name, or a target gene and protein level combined marker name determined in advance using the target machine learning algorithm; The current target marker sample and the target aging assessment model are used to obtain an aging degree assessment result of the target object.

2. The aging degree assessment method according to claim 1, characterized in that: The target samples of the target object are subjected to Olink proteomic sequencing and transcriptomic sequencing respectively to obtain the target standardized protein expression value and the relative expression amount of the target gene, including: Performing Olink proteomic sequencing on a first target sample of the target object to obtain a target standardized protein expression value; wherein the first target sample is peripheral blood plasma of the target object; The second target sample of the target object is subjected to transcriptomic sequencing to obtain the relative expression level of the target gene; wherein the second target sample is a mixture of peripheral blood mononuclear cells of the target object and a total RNA extraction reagent.

3. The aging degree assessment method according to claim 2, characterized in that: The performing Olink proteomic sequencing on the first target sample of the target object to obtain a target standardized protein expression value comprises: Performing Olink proteomic sequencing on the first target sample of the target subject to obtain the original protein expression value; The original protein expression values ​​are standardized and logarithmically transformed to obtain target standardized protein expression values.

4. The method for evaluating the degree of aging according to any one of claims 1 to 3, characterized in that: The target gene level markers are named B2M, PRPF38B, SIRT7, LIME1, TMEM123 and RPL17-C18orf32, the target protein level markers are named COL9A1, TREM2, CXCL14, SPON1, WNT9A and CXCL17, and the target gene and protein level combined markers are named CXCL17, ITGB5, TREM2, WNT9A, CXCL14, COLEC12, FGF5, CD248, ERV3-ZNF117 and SEC62.

5. The aging degree assessment method according to claim 4, characterized in that: Get the target marker name, including: Determine each historical marker sample based on the historical standardized protein expression value and the historical gene relative expression; wherein the historical marker samples include historical gene level marker samples and historical protein level marker samples; The historical marker samples are analyzed using a LASSO regression algorithm to obtain each post-screening marker sample; The target machine learning algorithm is used to evaluate the importance score of each of the screened marker samples in the target aging assessment model, so as to determine the name of the target marker according to the importance score.

6. The method for assessing the degree of aging according to claim 5, characterized in that: Get targeted aging assessment models, including: An initial aging assessment model is established using the historical marker samples and the target machine learning algorithm; the dependent variable of the initial aging assessment model is age grouping; The parameters of the initial aging assessment model are optimized using a random search algorithm to obtain a target aging assessment model.

7. The method for assessing the degree of aging according to claim 6, characterized in that: The initial aging assessment model includes an initial gene aging assessment model whose independent variable is the relative gene expression amount, an initial protein aging assessment model whose independent variable is the standardized protein expression value, and an initial gene-protein combined aging assessment model whose independent variables are the relative gene expression amount and the standardized protein expression value.

8. An aging degree assessment device, characterized in that: include: The Omics sequencing module is used to perform Olink proteomics sequencing and transcriptomics sequencing on the target samples of the target object to obtain the target standardized protein expression value and the relative expression amount of the target gene; A target marker extraction module, for extracting a current target marker sample corresponding to the target marker name from the target sample based on the target standardized protein expression value, the target gene relative expression amount, and using a target machine learning algorithm; wherein the target marker name is a target gene level marker name, a target protein level marker name, or a target gene and protein level combined marker name pre-determined using the target machine learning algorithm; The aging degree assessment module is used to obtain the aging degree assessment result of the target object by using the current target marker sample and the target aging assessment model.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the method for assessing the degree of aging as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the aging degree assessment method as described in any one of claims 1 to 7 are implemented.

Images