Depression diagnosis marker and application thereof

Abstract

The invention provides a depression diagnosis marker which is selected from one or more of immune cell Trem1 classical mononuclear cells, B cells, CD36 mononuclear cells, HLADR mononuclear cells, Th17, Treg, cell factors CXCL14, VEGFR1IL-1, RII, RANK, XEDAR, GITR, CRTAM, IL-11, IGFBP-2 and Fetuin A. The depression diagnosis marker has high MDD curative effect prediction efficiency. The invention further discloses application of the depression diagnosis marker in preparation of products for diagnosing depression, and the depression diagnosis marker has high MDD diagnosis value.

Description

Technical Field

[0001] The present invention belongs to the field of biomedicine technology, and particularly relates to depression diagnosis, and specifically relates to a depression diagnosis marker and application thereof. Background Art

[0002] Major depressive disorder (MDD) is a type of mental illness with high morbidity, high recurrence, high disability and high suicide rate that seriously affects the quality of life of patients. The 2019 China Mental Health Survey (CMHS) showed that the lifetime prevalence of mood disorders in China is 6.8%, and the lifetime prevalence of MDD is 3.4%, which is the second largest mental illness in China after anxiety disorders, causing a serious disease burden. However, there is still a lack of objective and effective biological diagnostic indicators for MDD. Therefore, the diagnosis of MDD still relies heavily on the doctor's personal clinical experience or assessment scale, so the recognition rate is low, and the missed diagnosis and misdiagnosis rates are high. Therefore, finding biomarkers with high sensitivity and specificity to optimize the diagnosis and treatment of depression is an urgent problem that needs to be solved today.

[0003] In recent years, a large number of studies have shown that immune-inflammatory mechanisms may be involved in the pathogenesis of MDD. Certain cytokines can participate in cell signal transduction, immune response, and response to internal and external factors such as inflammation. A large number of studies have reported elevated levels of peripheral blood cytokines in patients with MDD, including IL-6, IL-10, and TNF-α. Some research results also show that these inflammatory factors, TNF-α, IL-6, IL-12, and IL-4, may serve as objective biological diagnostic markers for MDD. In addition to cytokines, significant changes in immune cells have also been found in patients with MDD, and there are significant differences in the immune cell profiles between patients with MDD and healthy controls. In patients with MDD, the proportions of CCR2+CD8T cells, Trem1+monocytes, IgD+memory B cells, and plasmablasts increased, but the levels of different Tregs, follicular T cells, gamma-deltaT cells, Th17 cells, naive CD4 T cells, and CD4 T cells decreased.

[0004] Despite the above findings, there are still many limitations in current studies, such as small sample size, only testing one or individual cytokines and immune cells, lack of longitudinal studies, low reproducibility, etc. Therefore, the development of clinically relevant biomarkers remains crucial. Traditional fluorescence flow cytometry performs poorly because it cannot analyze multiple features simultaneously. Single-cell mass cytometry (CyTOF) can overcome this shortcoming. CyTOF can measure up to 50 features in a single cell and is now widely used in cancer and other neurological disease research, such as solid tumors, Alzheimer's disease and Parkinson's disease. However, the application of CyTOF in MDD research is still rare. Although CyTOF has been used to identify differences in peripheral blood immune cell profiles between MDD patients and healthy controls, the goal of using CyTOF to find diagnostic markers for MDD remains to be explored.

[0005] However, previous studies have pointed out that when a single indicator or a single group indicator is used as a diagnostic biomarker, the diagnostic performance may be poor. Therefore, the cell type abundance and cytokine expression profile detected by CyTOF can be explored to explore the potential of MDD diagnostic biomarkers. However, finding MDD diagnostic markers based on high-throughput detection data is still a very challenging task.

[0006] As a widely used artificial intelligence technology, machine learning has been widely used in the automatic analysis of complex data across various biomedical fields, and has obvious advantages in interpreting omics data, identifying biomarkers, and building predictive models for precision medicine. However, research on using machine learning to analyze cytokine and immune cell data in MDD to establish diagnostic models is still quite insufficient. Summary of the invention

[0007] The purpose of the present invention is to overcome at least one disadvantage of the above-mentioned prior art and to provide a depression diagnostic marker and its application.

[0008] In order to solve the above technical problems, the first aspect of the present invention provides a depression diagnostic marker, the main feature of which is that it is selected from one or more of the immune cells Trem1 classical monocytes, B cells, CD36 monocytes, HLADR monocytes, Th17, Treg, cytokines CXCL14, VEGFR1IL-1, RII, RANK, XEDAR, GITR, CRTAM, IL-11, IGFBP-2, and FetuinA.

[0009] The second aspect of the present invention provides the use of the depression diagnostic marker in the preparation of a product for diagnosing depression.

[0010] Preferably, the product comprises a kit or chip containing reagents for detecting the level of the depression diagnostic marker.

[0011] Preferably, the depression diagnostic markers are composed of immune cells Trem1 classical monocytes, B cells, CD36 monocytes, HLADR monocytes, Th17, Treg, cytokines CXCL14, VEGFR1IL-1, RII, RANK, XEDAR, GITR, CRTAM, IL-11, IGFBP-2, and Fetuin A.

[0012] Preferably, the product includes a diagnostic model, and the diagnostic model adopts the formula: MDD risk score = CXCL14 expression × 0.93 + VEGFR1 expression × 0.47 + IL-1RII expression × 0.15 + RANK expression × 0.09 + XEDAR expression × -0.20 + GITR expression × -0.36 + CRTAM expression × -0.47 + IL-11 expression × -1.15 + IGFBP-2 expression × -1.15 + Fetuin A expression × -1.16 + Trem1 classical monocyte ratio × 1.16 + B cell ratio × 0.18 + CD36 monocyte ratio × 0.07 + HLADR monocyte ratio × -0.06 + Th17 ratio × -0.61 + Treg ratio × -1.60.

[0013] The depression diagnostic markers and applications of the present invention integrate two types of omics data, cytokine and immune cell, and use machine learning methods to systematically explore their diagnostic predictive value in MDD disease, thereby providing more objective biological diagnostic indicators for MDD. There have been no related research reports and invention patents in the past, and they have high diagnostic value for MDD. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A and Figure 1 B is the LASSO regression result graph using lambda.min as the cutoff threshold.

[0015] Figure 1 C shows the feature selection result plot of the recursive feature elimination (RFE) method.

[0016] Figure 1 D shows the results of using Venn diagram to visualize the overlap of significant features identified by univariate logistic regression, LASSO regression, and RFE algorithm.

[0017] Figure 1 E and Figure 1F is the result graph of the high accuracy and area under the curve (AUC) values ​​of the eight algorithms in the test set, among which the ridge regression analysis shows the highest accuracy and AUC value at the same time.

[0018] Figure 1 Figures G to I are the AUC performance results of the ridge regression algorithm in the training data, test data, and all data.

[0019] Figure 1 Figures J to L show the significant differences in risk scores between MDD patients and healthy controls observed in the training dataset, test dataset, and all participants. DETAILED DESCRIPTION

[0020] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further described below in conjunction with specific embodiments.

[0021] The present invention is the first to use the method of combined analysis of CyTOF and cytokines to systematically explore the potential of immune cells and cytokines as diagnostic predictive markers. The present invention combines CyTOF and cytokine data and establishes a diagnostic model MDD risk score including 16 indicators through several machine learning algorithms, namely, MDD risk score = CXCL14 expression × 0.93 + VEGFR1 expression × 0.47 + IL-1RII expression × 0.15 + RANK expression × 0.09 + XEDAR expression × -0.20 + GITR expression × -0.36 + CRTAM expression × -0.47 + IL-11 expression × -1.15 + IGFBP-2 expression × -1.15 + Fetuin A expression × -1.16 + Trem1 classical monocyte ratio × 1.16 + B cell ratio × 0.18 + CD36 monocyte ratio × 0.07 + HLADR monocyte ratio × -0.06 + Th17 ratio × -0.61 + Treg ratio × -1.60, including 6 immune cells and 10 cytokines. The AUC of the model on both the training set and the test data was greater than 0.9, indicating that it had a high diagnostic value.

[0022] Study subjects

[0023] The iMore study is a prospective observational cohort study that included patients with depression and followed up the patients for 8 weeks. Symptom changes were assessed using scales such as the Montgomery-Asberg Depression Rating Scale (MADRS). Peripheral blood was drawn from patients at baseline, and multidimensional indicators including cytokines and immune cells were detected. It aims to build a diagnostic model for depression and a model for efficacy prediction. This study has been approved by the Research Ethics Committee of Shanghai Mental Health Center, China, with the ethics approval number 2020-87. Written informed consent was obtained from all participants before the study. In addition, it has been registered in the Clinical Trial Registry with the identifier NCT04518592. The specific study design and details can be found in Integrated Module of Multidimensional Omics for Peripheral Biomarkers (iMORE) in patients with major depressive disorder: rationale and design of a prospective multicentre cohort study.

[0024] The patients with depression included in this study were patients who were enrolled in iMore from December 2020 to June 2022 and completed CYTOF or cytokine testing. A total of 134 patients with depression were included, all of whom completed CYTOF testing, and 84 patients with depression also completed 440 cytokine testing. CYTOF analyzed the immune cell types of the participants' peripheral blood PBMCs, and the protein antibody chip detected 440 types of cytokines in the participants' peripheral plasma. Because one patient had extremely low CyTOF test and cytokine test results and was excluded, the individuals finally included in the construction of the diagnostic model were 83 patients with depression and 50 healthy controls.

[0025] Inclusion criteria for patients with depression: Adult patients aged between 18 and 65 years who met the diagnostic criteria for major depressive disorder (MDD) in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5).

[0026] The inclusion criteria are as follows:

[0027] 1. Adults diagnosed with major depressive disorder (MDD) experiencing a first episode or relapse.

[0028] 2. Baseline MADRS total score ≥24.

[0029] 3. Baseline Hamilton Depression Rating Scale-17 (HAMD-17) total score ≥ 20.

[0030] 4. Provide informed consent voluntarily.

[0031] Exclusion criteria mainly include:

[0032] 1. Current presence of any Axis I disorder other than major depressive disorder (MDD).

[0033] 2. There is a serious risk of suicide or the score on suicidal ideation (MADRS item 10) is greater than 3.

[0034] 3. The presence of serious physical illnesses, such as cerebrovascular disease, respiratory disease, blood disease, liver and kidney disease, endocrine disease, nervous system disease and other systemic diseases.

[0035] 4. Pregnancy or lactation.

[0036] Inclusion criteria for healthy controls: age and gender matched those of patients; healthy, no serious physical illness; no history of mental illness; no family history of mental illness.

[0037] Identification of key cytokines and key immune cells

[0038] First, key immune cells and key cytokines were selected using three machine learning algorithms: logistic regression, least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation, and recursive feature elimination (RFE) using a random forest classifier, also with 10-fold cross-validation. Figure 1 A to Figure 1 As shown in Figure D, the three algorithms jointly identified 10 overlapping cytokines and 6 immune cells. These overlapping cytokines and immune cells served as key cytokines and key immune cells, forming the basis for constructing the MDD diagnostic model in the training set.

[0039] Construction of MDD diagnostic model

[0040] The 133 participants were then randomly divided into a training set and a test set at a ratio of 70% and 30%, respectively. The training set included 58 patients with depression and 35 healthy controls, while the test set included 25 patients with depression and 15 healthy controls.

[0041] Based on the above 16 key diagnostic features, eight classic machine learning algorithms were used to build models, and the MDD diagnostic model was constructed using the training set. The eight classic machine learning algorithms include elastic network (Enet), ridge regression, LASSO, gradient boosting machine (GBM), random forest (RF), supervised principal component analysis (SuperPC), extreme gradient boosting (XGboost) and support vector machine (SVM).

[0042] The diagnostic model built based on the training set was then validated in the test set. The model was evaluated using indicators such as AUC, precision, recall, and F1 score. Figure 1 E and Figure 1 F shows the accuracy and AUC values ​​of various machine learning algorithms in the test set. Among them, the diagnostic model constructed by the ridge regression method had the highest accuracy and AUC values. Therefore, the optimal diagnostic model based on ridge regression analysis was: MDD risk score = CXCL14 expression × 0.93 + VEGFR1 expression × 0.47 + IL-1RII expression × 0.15 + RANK expression × 0.09 + XEDAR expression × -0.20 + GITR expression × -0.36 + CRTAM expression × -0.47 + IL-11 expression × -1.15 + IGFBP-2 expression × -1.15 + Fetuin A expression × -1.16 + Trem1 classical monocyte ratio × 1.16 + B cell ratio × 0.18 + CD36 monocyte ratio × 0.07 + HLADR monocyte ratio × -0.06 + Th17 ratio × -0.61 + Treg ratio × -1.60).

[0043] In this specification, the present invention has been described with reference to specific embodiments thereof. However, it is apparent that various modifications and variations may be made without departing from the spirit and scope of the present invention. Therefore, the description should be regarded as illustrative rather than restrictive.

Claims

1. A depression diagnostic marker, characterized in that: One or more selected from the group consisting of immune cells Trem1 classical monocytes, B cells, CD36 monocytes, HLADR monocytes, Th17, Treg, cytokines CXCL14, VEGFR1IL-1, RII, RANK, XEDAR, GITR, CRTAM, IL-11, IGFBP-2, and Fetuin A.

2. Use of the depression diagnostic marker according to claim 1 in the preparation of a product for diagnosing depression.

3. The use according to claim 2, characterized in that: The product includes a kit or chip containing reagents for detecting the level of the depression diagnostic marker.

4. The use according to claim 2, characterized in that: The depression diagnostic markers are composed of immune cells Trem1 classical monocytes, B cells, CD36 monocytes, HLADR monocytes, Th17, Treg, cytokines CXCL14, VEGFR1IL-1, RII, RANK, XEDAR, GITR, CRTAM, IL-11, IGFBP-2, and Fetuin A.

5. The use according to claim 2, characterized in that: The product includes a diagnostic model, which uses the formula: MDD risk score = CXCL14 expression × 0.93 + VEGFR1 expression × 0.47 + IL-1RII expression × 0.15 + RANK expression × 0.09 + XEDAR expression × -0.20 + GITR expression × -0.36 + CRTAM expression × -0.47 + IL-11 expression × -1.15 + IGFBP-2 expression × -1.15 + Fetuin A expression × -1.16 + Trem1 classical monocyte ratio × 1.16 + B cell ratio × 0.18 + CD36 monocyte ratio × 0.07 + HLADR monocyte ratio × -0.06 + Th17 ratio × -0.61 + Treg ratio × -1.60.

Images