Prediction system for lupus nephritis, electronic equipment and storage medium
By detecting Afamin protein in urine and constructing a machine learning model, the problem of insufficient sensitivity and specificity in the diagnosis of lupus nephritis in existing technologies is solved, providing a non-invasive and simple method for predicting lupus nephritis and improving the accuracy of diagnosis.
Patent Information
- Application Number
- CN202511016852.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-23
- Publication Date
- 2025-11-07
AI Technical Summary
Existing non-invasive biomarkers lack sufficient sensitivity and specificity in the diagnosis and monitoring of lupus nephritis. Kidney biopsy carries invasive risks, and existing urine test indicators have large errors and poor specificity, which limits their clinical application.
Afamin protein was used as a urinary biomarker. Its expression level was detected by multiple detection methods, and a machine learning model was constructed for prediction. Combined with specific recognition probes and primers, it was detected and evaluated using chips, test strips or kits.
This study provides a non-invasive, simple, and easily applicable method for predicting lupus nephritis. Afamin protein has good specificity and sensitivity in urine, and can directly reflect the condition of the kidneys, thus improving the accuracy of diagnosis.
Smart Images
Figure CN120913729A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of intelligent medical treatment, in particular to a prediction system for lupus nephritis, an electronic device and a storage medium. BACKGROUND
[0002] Systemic lupus erythematosus is a chronic and complex autoimmune disease, and SLE can involve multiple organs, especially the kidney. Studies have shown that 30-60% of adult systemic lupus erythematosus patients and up to 70% of juvenile systemic lupus erythematosus patients will progress to lupus nephritis. Lupus nephritis is one of the most severe manifestations of systemic lupus erythematosus, and its clinical manifestations and histopathological changes are diverse and often indicate poor prognosis for patients. So far, kidney biopsy is still the gold standard for the diagnosis of lupus nephritis. However, kidney biopsy is invasive and has the risk of bleeding. Therefore, non-invasive biomarkers are important for dynamic observation of disease progression and adjustment of treatment regimens. Currently recognized commonly used laboratory indicators for lupus nephritis include the following: urine protein, creatinine clearance rate, anti-double-stranded DNA antibody, complement, etc. However, the sensitivity and specificity of the above indicators need to be improved. Therefore, finding new non-invasive biomarkers is of great significance for the judgment of the activity of lupus nephritis, the prediction of disease recurrence, and the monitoring of treatment effect.
[0003] Previous studies have shown that some indicators in serum, such as anti-double-stranded DNA antibody, complement C3, and creatinine, also play an important role in the diagnosis and efficacy evaluation of systemic lupus erythematosus. However, these indicators lack specificity and are abnormal in other autoimmune diseases and even in healthy elderly populations. Moreover, serum biomarkers are less effective than urine biomarkers in directly reflecting kidney damage.
[0004] Compared with serum biomarkers, urine biomarkers show higher sensitivity and specificity in the diagnosis and monitoring of systemic lupus erythematosus and its kidney involvement. Moreover, since urine is stored in the kidney in the form of primary urine before excretion, some substances in urine can directly reflect the condition of the kidney. Some existing urine detection indicators, such as urine protein and creatinine clearance rate, can assist in the diagnosis and treatment of lupus nephritis to some extent. However, urine protein and creatinine clearance rate detection has the characteristics of large error and poor specificity, which limits the application of these indicators in clinical practice. SUMMARY
[0005] (1) Technical problems solved
[0006] In view of this, one of the main purposes of the present application is to provide a prediction system for lupus nephritis, an electronic device and a storage medium. It has good specificity and sensitivity, and is simple to operate and easy to popularize and apply.
[0007] (II) Technical Solution
[0008] To achieve the above object, the present application provides an application of a reagent for detecting expression level of a biomarker, which is Afamin protein, in preparation of a product for diagnosing lupus nephritis in a subject.
[0009] In one embodiment, the biomarker is derived from urine.
[0010] In another aspect, the present application provides an application of the above-mentioned reagent in preparation of a product for screening lupus nephritis in a subject.
[0011] In another aspect, the present application also provides an application of the above-mentioned reagent in preparation of a product for evaluating risk of lupus nephritis in a subject.
[0012] In one embodiment, the reagent comprises reagents required for detecting protein expression level of the biomarker, probes specifically recognizing the biomarker, and / or primers specifically amplifying the biomarker.
[0013] In one embodiment, the reagent further comprises reagents for detecting protein expression level of the biomarker by Western blotting, enzyme-linked immunosorbent assay, radioimmunoassay, sandwich assay, immunohistochemical staining, mass spectrometry detection method, immunoprecipitation analysis method, complement binding analysis method, flow cytometry fluorescence analysis technology, protein chip method, near-infrared spectroscopy, immunochemiluminescence method, capillary gel electrophoresis method, or colloidal gold immunization method.
[0014] In one embodiment, the above-mentioned product comprises a chip, test paper, or reagent kit.
[0015] In another aspect, the present application also provides a prediction method for lupus nephritis, which comprises:
[0016] Obtaining data, obtaining expression level data of a target protein of a to-be-tested sample, the target protein being Afamin protein;
[0017] Analyzing data, inputting the expression level data into a constructed prediction model, the prediction model being used for predicting whether the to-be-tested sample is a lupus nephritis sample based on the expression level data;
[0018] Outputting a prediction result, predicting and outputting whether the to-be-tested sample is a lupus nephritis sample based on the output result of the prediction model.
[0019] In one embodiment, the method for constructing the prediction model comprises: obtaining expression level data of a target protein of a test sample in a training set and clinical characteristics corresponding to the test sample, the clinical characteristics including healthy people, patients with systemic lupus erythematosus without lupus nephritis, and patients with systemic lupus erythematosus with lupus nephritis, extracting the target gene expression data in the training set as input of a machine learning model to construct a prediction model, and obtaining the constructed prediction model.
[0020] In one embodiment, the machine learning model comprises a linear regression model, a logistic regression model, a random forest model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perception model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, and / or a CatBoost model.
[0021] In one embodiment, whether the test sample is a lupus nephritis sample is determined based on the following criteria:
[0022] If the expression level of the target protein Afamin protein is higher than a threshold value, the test sample is a lupus nephritis sample.
[0023] If the expression level of the target protein Afamin protein is lower than a threshold value, the test sample is a non-lupus nephritis sample.
[0024] In another aspect, the present application also provides a prediction system for lupus nephritis, which comprises:
[0025] An acquisition unit is configured to acquire expression level data of a target protein of a test sample, the target protein being Afamin protein.
[0026] An analysis unit is configured to input the expression level data into a constructed prediction model, the prediction model being configured to predict whether the test sample is a lupus nephritis sample based on the expression level data.
[0027] An output prediction result unit is configured to predict and output whether the test sample is a lupus nephritis sample based on an output result of the prediction model.
[0028] In another aspect, the present application also provides a prediction electronic device for lupus nephritis, which comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors to implement the prediction method described above.
[0029] The application also provides, in another aspect, a non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of the above-mentioned prediction electronic device, the device is enabled to perform the above-mentioned prediction method.
[0030] (III) Beneficial Effects
[0031] The application provides a prediction system for lupus nephritis, an electronic device and a storage medium.
[0032] Compared with the prior art, the following beneficial effects are achieved:
[0033] 1. The test is non-invasive, convenient and easy to operate, simple to operate and easy to promote.
[0034] 2. The urine Afamin protein can directly reflect the condition of the kidney, and has good accuracy and specificity. BRIEF DESCRIPTION OF DRAWINGS
[0035] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, below the drawings needed to be used in the embodiment or the prior art description will be briefly introduced, obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.
[0036] Figure 1 is the urine protein profile of patients with systemic lupus erythematosus with and without nephritis.
[0037] Figure 2 is the urine afamin protein difference chart of patients with systemic lupus erythematosus with and without nephritis.
[0038] Figure 3 is the relationship chart between the urine afamin level of patients with lupus nephritis and the disease activity score (SLE DAI).
[0039] Figure 4 is the relationship chart between the urine afamin level of patients with lupus nephritis and creatinine (Scr).
[0040] Figure 5 is the relationship chart between the urine afamin level of patients with lupus nephritis and urine protein (proteinuria).
[0041] Figure 6 is the relationship chart between the urine afamin level of patients with lupus nephritis and complement (C3).
[0042] Figure 7 is the color development chart of enzyme-linked immunosorbent assay for detecting urine afamin protein.
[0043] Figure 8 is a diagnostic performance chart for evaluating lupus nephritis using urine afamin protein. DETAILED DESCRIPTION
[0044] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, 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 some of the embodiments of the present application but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.
[0045] Terms and definitions
[0046] As used herein, the term "chip" also referred to as an array, refers to a solid support comprising attached peptide probes. An array typically comprises a plurality of different peptide probes attached to the surface of a substrate at different known locations. These arrays, also referred to as "microarrays," can typically be produced using either mechanical synthesis methods or light-directed synthesis methods, which incorporate a combination of photolithographic methods and solid-phase synthesis methods. Arrays can comprise a flat surface, or can be nucleic acids or peptides on beads, gels, polymeric surfaces, fibers such as optical fibers, glass, or any other suitable substrate. Arrays can be packaged in a manner that allows for diagnostic or other manipulations of the full functional device.
[0047] The chip includes a gene chip, a protein chip.
[0048] The protein chip includes a solid phase carrier and the specific antibody of the marker protein fixed on the solid phase carrier.
[0049] In some embodiments, the components of the kit can be packaged in an aqueous medium or in lyophilized form.
[0050] Suitable containers in a kit will generally include at least one vial, test tube, flask, bottle, syringe or other container, into which a component can be placed, and preferably, suitably aliquoted. Where there is more than one component in the kit, the kit will also generally contain a second, third or other additional container into which the additional components are separately placed. It will be appreciated that the components of the kit can be supplied ready to use. It will also be appreciated that the kit of the application will typically include a container for containing the reagents, sealed to prevent contamination or evaporation, for commercial sale. Such containers can include injection or blow molded plastic containers into which the desired vials are retained.
[0051] The solid support of the kit can be, for example, plastic, silicon wafer, metal, resin, glass, membrane, particle, precipitate, gel, polymer, sheet, sphere, polysaccharide, capillary, film, plate or slide.
[0052] In some embodiments, the sample includes, but is not limited to, bone marrow, peripheral blood, tissue, blood, serum, plasma, urine, saliva, semen, milk, cerebrospinal fluid, tears, sputum, mucus, lymph, cytosol, ascites, pleural effusion, amniotic fluid, bladder irrigant, and bronchoalveolar lavage.
[0053] As used herein, the terms "antibody," "immunoglobulin" or "Ig" are used interchangeably herein and are used in the broadest sense and specifically encompass, for example, monoclonal antibodies, antibody compositions with polyepitopic or monovalent specificity, polyclonal or monovalent antibodies, multivalent antibodies, multispecific antibodies (e.g., bispecific antibodies, so long as they exhibit the desired biological activity), single-chain antibodies, and fragments thereof (e.g., domain antibodies). Antibodies can be human, humanized, chimeric, and / or affinity matured, as well as antibodies from other species, such as mouse, rabbit, llama.
[0054] As used herein, the term "sample" or "biological sample" refers to a sample including, but not limited to, bone marrow, peripheral blood, tissue, blood, serum, plasma, urine, saliva, semen, milk, cerebrospinal fluid, tears, sputum, mucus, lymph, cytosol, ascites, pleural effusion, amniotic fluid, bladder irrigant, and bronchoalveolar lavage.
[0055] As used herein, the term "detecting" refers broadly to any means of determining the presence or absence of a protein of interest. Thus "detecting" can include determining, assessing or measuring whether a microbe is present in any manner or form - which can include qualitative, quantitative or semi-quantitative determination.
[0056] As used herein, the term "subject" includes mammals and non-mammals.
[0057] Examples of mammals include, but are not limited to, any member of the mammalian class: humans, non-human primates such as chimpanzees and other apes and monkey species; farm animals such as cows, horses, sheep, goats, swine; domestic animals such as rabbits, dogs, and cats; laboratory animals including rodents, such as rats, mice and guinea pigs, and the like. Examples of non-mammals include, but are not limited to, birds, fish, or other non-mammalian animals, and the like.
[0058] In one embodiment, the subject is a human.
[0059] As used herein, “containing”, “having” or “including” encompasses “comprising”, “consisting essentially of”, “consisting essentially of”, and “consisting of”; “consisting essentially of”, “consisting essentially of”, and “consisting of” are subsumed into “containing”, “having” or “including”.
[0060] The experimental methods used in the following examples are conventional methods, and the reagents, methods and equipment used are conventional reagents, methods and equipment in the technical field unless otherwise specified.
[0061] Example 1: Acquisition of biomarkers:
[0062] Thirty patients with systemic lupus erythematosus admitted to the Department of Rheumatology and Immunology of Gulou Hospital Affiliated to Nanjing University Medical College from January 2022 to January 2023 were selected. All patients with systemic lupus erythematosus met the American College of Rheumatology 1997 revised diagnostic criteria for systemic lupus erythematosus, and had not received strong immunosuppressive agents such as mycophenolate mofetil or cyclophosphamide within 3 months. Fifteen patients with lupus nephritis were diagnosed by renal biopsy. Fifteen patients with systemic lupus erythematosus without lupus nephritis were used as a control group.
[0063] 5 milliliters of morning urine was collected from each patient. Differential proteomic analysis was performed using tandem mass spectrometry label quantitative proteomic technology to obtain differential proteins. Figure 1 The results showed that Afamin in the urine of lupus patients (LN) was significantly increased compared with normal controls (HC), and Afamin in the urine of patients with lupus nephritis was also significantly increased compared with patients with systemic lupus erythematosus without nephritis (non-LN).
[0064] Further, the Afamin protein in the urine of patients with lupus nephritis and patients with systemic lupus erythematosus without nephritis was detected using the human Afamin protein enzyme-linked immunosorbent assay kit from Shanghai Jianglai Biotechnology Co., Ltd. Figure 2 The results were consistent with the results of tandem mass spectrometry label quantitative proteomic technology detection, and the Afamin protein level in the urine of patients with lupus nephritis was significantly higher than that of patients with systemic lupus erythematosus without nephritis.
[0065] In addition, the Afamin protein concentration in the urine of patients with lupus was positively correlated with disease activity ( Figure 3 ), creatinine ( Figure 4 ), urinary protein ( Figure 5 ), etc., and was negatively correlated with complement C3 ( Figure 6 ), etc.
[0066] Example 2: Verification of biomarkers:
[0067] Afamin protein in urine was detected using an enzyme-linked immunosorbent assay (ELISA) with a human Afamin kit (Shanghai Jianglai Biotechnology Co., Ltd.).
[0068] According to the instructions, add the following to the microwells pre-coated with human Afamin protein (AFM) capture antibody: sample (100 μL serum per well), standards (serially diluted to form 200, 100, 50, 25, 12.5, 6.25, 3.12, and 0 ng / mL standards, 100 μL per well), biotin-labeled detection antibody (1:100 dilution before use, 100 μL per well), and HRP enzyme conjugate (1:100 dilution before use, 100 μL per well). After incubation and washing, develop the color with the substrate TMB. TMB is converted to blue under the catalysis of HRP, and then to yellow under acidic conditions. The intensity of the color is positively correlated with the amount of human Afamin protein (AFM) in the sample.
[0069] The absorbance (OD value) was measured at a wavelength of 450 nm using an ELISA reader, and the sample concentration was calculated. Figure 7 (From left to right: Columns 1 and 2 are standards, columns 3-7 are patients with systemic lupus erythematosus without nephritis, and columns 8-12 are patients with lupus nephritis.)
[0070] like Figure 8 As shown, urinary Afamin protein has shown good value in differentiating lupus nephritis from lupus without nephritis, with a sensitivity of 93.8%, a specificity of 93.7%, and an area under the ROC curve of 0.88 (p<0.001).
[0071] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0072] The above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A prediction system for lupus nephritis, characterized by, The prediction system comprises: an acquisition data unit configured to acquire expression level data of a target protein of a sample to be tested, the target protein being Afamin protein; an analysis data unit configured to input the expression level data into a constructed prediction model, the prediction model being configured to predict whether the sample to be tested is a lupus nephritis sample based on the expression level data; an output prediction result unit configured to predict and output whether the sample to be tested is a lupus nephritis sample based on an output result of the prediction model.
2. The prediction system of claim 1, wherein, The method for constructing the prediction model comprises: acquiring expression level data of a target protein of a training set sample to be tested and clinical features corresponding to the sample to be tested, the clinical features comprising systemic lupus erythematosus patients without lupus nephritis and systemic lupus erythematosus patients with lupus nephritis, extracting the expression level data of the target protein in the training set to input a machine learning model to construct a prediction model, and obtaining the constructed prediction model.
3. The prediction system of claim 2, wherein, The machine learning model comprises a linear regression model, a logistic regression model, a random forest model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perception model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, and / or a CatBoost model.
4. The prediction system of claim 1, wherein, The sample to be tested is determined to be a lupus nephritis sample based on the following criteria: If the expression level data of the target protein is higher than a threshold value, the sample to be tested is a lupus nephritis sample. If the expression level data of the target protein is lower than a threshold value, the sample to be tested is a non-lupus nephritis sample.
5. The prediction system of claim 4, wherein, The sample to be tested is derived from a subject, and the subject has or does not have systemic lupus erythematosus.
6. The prediction system of claim 5, wherein, The subject has systemic lupus erythematosus, but has or does not have lupus nephritis.
7. The prediction system of any one of claims 1-6, wherein, The method for acquiring the expression level data of the target protein of the sample to be tested comprises one or a combination of Western blotting, enzyme-linked immunosorbent assay, radioimmunoassay, sandwich assay, immunohistochemical staining, mass spectrometry detection method, immunoprecipitation analysis method, complement binding analysis method, flow cytometry fluorescence analysis technology, protein chip method, near-infrared spectroscopy, immunochemiluminescence method, capillary gel electrophoresis method, or colloidal gold immunization method.
8. The prediction system of claim 7, wherein, The sample to be tested is derived from urine.
9. An electronic device for predicting lupus nephritis, characterized by, The prediction electronic device comprises a memory and one or more programs stored in the memory and configured to be executed by one or more processors to implement the prediction system instructions of any one of claims 1-8.
10. A non-transitory computer-readable storage medium, comprising: When the instructions in the storage medium are executed by the processor of the prediction electronic device of claim 9, the device can execute the prediction system instructions of any one of claims 1-8.