Marker combination for assisting diagnosis of depression and bipolar disorder and use thereof

Abstract

This application provides a biomarker combination for assisting in the diagnosis of depression and bipolar disorder, and its specific application. The biomarker comprises nine circulating small RNAs, the sequences of which are shown in SEQ ID No. 1 to SEQ ID No. 9, respectively. The technical solution provided in this application has the following significant beneficial effects: it is the first to screen and validate a biomarker combination consisting of nine circulating small RNAs. This biomarker combination combines high diagnostic efficacy, objective quantification capability, non-invasive detection advantages, and extremely high clinical feasibility, providing a revolutionary tool for the accurate differential diagnosis and stratified management of depression (MDD) and bipolar disorder (BD), and has significant clinical value and social significance.

Description

Technical Field

[0001] This application relates to the field of biotechnology, specifically to a combination of biomarkers for the auxiliary diagnosis of depression and bipolar disorder and their applications. Background Technology

[0002] In the field of mental illness diagnosis, the differential diagnosis between major depressive disorder (MDD) and bipolar disorder (BD) has long been a significant clinical challenge and a core factor leading to a high misdiagnosis rate. Statistics show that up to 75% of bipolar disorder patients, especially during their first visit in the course of a depressive episode, are misdiagnosed as having simple major depressive disorder; simultaneously, about 12% of patients initially diagnosed with MDD are subsequently reclassified as having BD. This grim reality highlights the fundamental flaws of the current symptomatology-based diagnostic framework. The DSM and ICD diagnostic criteria, as well as rating scales such as the HAMD, primarily focus on the core symptoms of the current depressive episode (such as depressed mood, loss of interest, and decreased energy), while the characteristic manifestations of bipolar disorder—manic or hypomanic episodes—are often not actively reported by patients or systematically traced by physicians. When patients present only with depressive episodes, their clinical manifestations highly overlap with those of MDD, making effective differentiation impossible solely based on cross-sectional symptom assessment. The consequences of this difficulty in differentiation are extremely serious: misdiagnosing bipolar depression as unipolar depression, especially with the use of antidepressants alone without the combination of mood stabilizers or antipsychotics, can induce manic phases, accelerate mood cycles, lead to treatment resistance, and even worsen long-term prognosis and increase suicide risk. Therefore, developing objective diagnostic tools that can effectively differentiate between MDD and BD during depressive episodes, or even in the early stages of the disease, is an urgent need in psychiatric clinical practice. Existing clinical assessment tools are inadequate because they rely on subjective reports and fail to address the potentially different neurobiological bases of the two diseases. With the development of molecular diagnostic techniques, the search for biomarkers with differential diagnostic value has become a research hotspot. Circulating small RNAs (sRNAs), as key regulatory molecules of gene expression, may reflect specific perturbations in the pathophysiological processes of different mental illnesses. Given the overlap and differences between MDD and BD in genetic susceptibility, neural circuits, and molecular mechanisms, systematic analysis of sRNA expression patterns in peripheral fluids such as blood may reveal specific molecular features that can distinguish between the two. This study aims to construct and validate a combination of circulating sRNA biomarkers that can accurately distinguish between MDD and BD through large-scale, multi-center sRNA sequencing analysis. The goal is to provide objective diagnostic criteria when patients first present with depressive symptoms, thereby fundamentally reducing misdiagnosis, guiding precise initial treatment selection, and improving long-term patient outcomes. Summary of the Invention

[0003] In view of the above-mentioned technical limitations, this application proposes a combination of biomarkers for the auxiliary diagnosis of depression and bipolar disorder and their application; which overcomes the deficiencies and defects mentioned in the background art.

[0004] To achieve the above objectives, this application adopts the following technical solution: The inventive point of this application is to provide a combination of biomarkers for the auxiliary diagnosis of depression and bipolar disorder, the combination of biomarkers including one or more of miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f and miR-378i; their sequences are shown as SEQ ID No. 1-SEQ ID No. 9 respectively.

[0005] The sequences of SEQ ID No. 1 to SEQ ID No. 9 are shown in Table 1.

[0006] Table 1

[0007] The second inventive point of this application is to provide an application of a primer combination in the preparation of reagents for the auxiliary diagnosis of depression and bipolar disorder, wherein the primer combination includes one or more of miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i; the sequences of which are shown in SEQ ID No. 1-SEQ ID No. 9, respectively.

[0008] Optionally, in the above application, the primer combination includes a primer combination for detecting at least one sRNA marker among miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i. The primer combination consists of reverse transcription primers and primer pairs, wherein: The nucleotide sequences of the reverse transcription primers used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i are shown in SEQ ID No. 10-SEQ ID No. 18. The primer pair used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i consists of an upstream primer and a downstream primer. The nucleotide sequences of the upstream primer are shown in SEQ ID No. 19-SEQ ID No. 27, and the nucleotide sequences of the downstream primer are shown in SEQ ID No. 28-SEQ ID No. 36, respectively.

[0009] The primers are summarized in Table 2 (the primers are from GENERAL BIOL).

[0010] Table 2

[0011] The third inventive point of this application is to provide an application of a biomarker combination in the preparation of a kit for the auxiliary diagnosis of depression and bipolar disorder, wherein the kit is a real-time quantitative qRT-PCR kit and the biomarker combination is the biomarker combination described above.

[0012] Alternatively, the above applications, The kit includes primer combinations for the auxiliary diagnosis of depression and bipolar disorder. These primer combinations include primer combinations for detecting at least one sRNA marker among miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i. The primer combinations consist of reverse transcription primers and primer pairs, wherein: The nucleotide sequences of the reverse transcription primers used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i are shown in SEQ ID No. 10-SEQ ID No. 18. The primer pair used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i consists of an upstream primer and a downstream primer. The nucleotide sequences of the upstream primer are shown in SEQ ID No. 19-SEQ ID No. 27, and the nucleotide sequences of the downstream primer are shown in SEQ ID No. 28-SEQ ID No. 36, respectively.

[0013] Optionally, in the above applications, the kit further includes a total sRNA extraction reagent set and an RNA reverse transcription reagent set.

[0014] Optionally, in the above-described application, the total sRNA extraction reagent kit includes protein denaturation lysis buffer, chloroform, ethanol, and washing buffer.

[0015] Optionally, in the above-described application, the RNA reverse transcription reagent kit includes reverse transcription primers, reverse transcription reaction buffer, and a reverse transcriptase mixture.

[0016] The preferred method is to use the RNA extraction kit (product number DP419) from Tiangen Biotech (Beijing) Co., Ltd., and extract the plasma sample according to the instructions.

[0017] RT-qPCR was performed using a single-channel, one-step method. The reaction system was prepared according to Table 3 below: Table 3

[0018] Optionally, in the above applications, the kit further includes a primer for amplifying the internal reference gene U6; the sequence of the primer for amplifying the internal reference gene U6 is: Forward primer for internal reference gene U6: GCTTGGCAGCACATATACTAAA (SEQ ID No. 37); Reverse primer for internal reference gene U6: TTTGCGTGTCATCCTTGCG (SEQ ID No. 38).

[0019] Optionally, in the above application, the reaction conditions for the one-step real-time quantitative qRT-PCR method are: 16℃ for 5 min; 50℃ for 15 min; 95℃ for 10 min; 95℃ for 15 s; 60℃ for 40 s; 50 cycles, with fluorescence signal detected and acquired at 60℃.

[0020] The technical solution provided in this application has the following significant advantages compared to the prior art: It provides a highly accurate and objectively verifiable diagnostic tool that can differentiate between depression and bipolar disorder, effectively making up for the shortcomings of existing subjective assessment methods; This application is the first to screen and validate a biomarker ensemble consisting of nine circulating small RNAs. In the sequencing data discovery cohort, this ensemble model demonstrated superior diagnostic performance in independently validating the biological problem of differentiating between depression and bipolar disorder, with an AUC of 0.853 [0.796-0.891]. Figure 4Furthermore, for clinical applications, qPCR was used to develop a reagent kit, and the performance remained stable, with an AUC of 0.988 [0.954-1.000] for this biological problem. Figure 5 This method is comparable in efficacy to the current symptomatology-based structured diagnostic interview (the gold standard). It provides molecular biological evidence for differentiating between depression (MDD) and bipolar disorder (BD) without relying on subjective judgment, potentially leading to a fundamental reduction in clinical misdiagnosis rates.

[0021] Major depressive disorder (MDD) and bipolar disorder share overlapping depressive symptoms, frequently leading to misdiagnosis and inappropriate treatment. Many patients with bipolar disorder initially present with depressive episodes, only to develop manic or hypomanic symptoms years later. Consequently, the average diagnostic delay for bipolar disorder is 9 years, and up to 12.4% of patients initially diagnosed with MMD are later reclassified. In this study, circulating tsRNAs demonstrated the highest discriminative power, achieving an AUC of 0.941 with the random forest model. The 9-sRNA panel maintained good classification accuracy (AUC = 0.853). These findings support the potential of sRNA-based profiling as a molecular tool for early and accurate differentiation between MMD and bipolar disorder.

[0022] This application provides a complete solution from discovery and validation to clinical translation and application. Its core biomarker combination has the advantages of high diagnostic efficacy, objective quantification, non-invasive detection, and extremely high clinical feasibility. It provides a revolutionary tool for the accurate differential diagnosis and stratified management of depression (MDD) and bipolar disorder (BD), and has significant clinical value and social significance. Attached Figure Description

[0023] Figures 1-3 This embodiment of the present application illustrates the diagnostic performance of circulating sRNA in distinguishing between MDD and BD.

[0024] Figure 1 To demonstrate the performance of the MOMP prioritization model for distinguishing between MDD and BD based on four types of sRNAs and their integrated combinations in the discovery cohort, the curves represent the average AUC values ​​obtained through 10-fold cross-validation; the 95% confidence intervals were estimated using a 1,000-step bootstrap method. Figure 1 a- Figure 1 The results show that in the MOMP model, the internal 10x cross-validation AUC ranges from 0.992 to 0.998.

[0025] Figure 2 To evaluate the performance of the MOMP prioritization model in an independent validation queue, 95% confidence intervals were generated using a bootstrap method based on 1,000 repeated samplings. Figure 3This is the confusion matrix for the MOMP model in the independent validation queue. The matrix shows the number of true positives, true negatives, false positives, and false negatives, providing a visual summary of classification accuracy. The color gradient reflects the ratio of correctly classified to incorrectly classified cases.

[0026] Figure 2 a and Figure 3 The results show that in the external validation cohort (139 MDDs and 61 BDs), the AUC of mirina-based models ranged from 0.780 to 0.935, with the multilayer perceptron (MLP) model performing best (AUC 0.935; 95% CI, 0.898–0.965; sensitivity, 92.09%; specificity, 75.41%).

[0027] Figure 2 b and Figure 3 b shows that the RSRNA-based model also exhibits high accuracy, with the random forest model having an AUC of 0.924 (95% CI 0.866 ~ 0.956), a sensitivity of 84.89%, and a specificity of 83.61%.

[0028] Figure 2 c and Figure 3 c shows that the AUC of the TSRNA-based model is 0.941 (95% CI 0.894 ~ 0.973), the sensitivity is 92.09%, and the specificity is 73.77%.

[0029] Figure 2 d and Figure 3 The pirna-based model performed more moderately, with the best support vector machine (SVM) model having an AUC of 0.894 (95% CI, 0.839 ~ 0.942), a sensitivity of 94.24%, and a specificity of 67.21%.

[0030] Figure 2 e and Figure 3 The integrated model, which incorporates all four sRNA classes, further improved the classification, achieving an AUC of 0.923 (95% CI, 0.872 to 0.959), with a sensitivity of 87.05% and a specificity of 85.25%.

[0031] These findings demonstrate the potential of circulating sRNA profiles (particularly miRNA and tsRNA) as diagnostic biomarkers for differentiating major depressive disorder from bipolar disorder in the discovery and validation cohort.

[0032] Random forest was selected as the optimal model, and it was subsequently used for feature selection, training, and validation of 9penal.

[0033] Figure 4 It is the process of obtaining 9 sRNA penals. Figure 4 A. A random forest model was used to perform sequential forward selection on the integrated sRNA panel of the discovery cohort. Bar plots show the feature importance of integrated sRNAs in distinguishing between MDD and BD (obtained from average information and judged by SHAP values). Line plots depict the cumulative AUC (right axis) after adding sRNAs one by one in each iteration. Figure 4 B, the specific values ​​of FIshap and FImodel (the aforementioned average information and SHAP value) for the top 10 main features. The specific sequences are then merged according to the mature organism to obtain the final 9-penal combination used to distinguish between MDD and BD. Figure 4 C represents the performance of the 9-sRNA model for the task in the independent validation cohort. AUC and 95% confidence intervals were calculated using 1000 bootstrap replicates.

[0034] Figure 5 The validation results of the 9-penal group in the qPCR cohort showed that its discrimination effect could reach 0.988.

[0035] Figure 6 To illustrate the differential expression of sRNAs between MDD and BD using volcano plots, the x-axis represents a Log² change, and the y-axis represents -Log10 (adjusted P-value). Significance was assessed using a two-tailed Mann-Whitney U test and corrected using the Benjamini-Hochberg method. Red dots indicate upregulated sRNAs in MDD, while blue dots indicate downregulated sRNAs (adjusted P < 0.05, |log² FC| > 0.58). In the individual comparisons between MDD and BD, 603 differentially abundant sRNAs were detected, with 268 upregulated and 335 downregulated in MDD. Notably, significant downregulation of miRNAs was observed in both comparisons, highlighting the unique sRNA expression pattern that distinguishes MDD from BD and the control. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this application clearer, a more detailed description is provided below. However, it should be understood that the description herein is merely for explaining this application and is not intended to limit its scope.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. All reagents and instruments used herein are commercially available, and the characterization methods involved can be found in relevant descriptions in the prior art, and will not be repeated here.

[0038] MDD, Depression; BD, Bipolar Disorder; Control Group, Non-Depressed Control Group; HC, Healthy Control Group; Other, Control Group with Other Mental Disorders; PCoA, Principal Coordinate Analysis.

[0039] 1. Design and Methodology From May 2021 to December 2024, this study collected 1270 plasma samples from four clinical centers, including individuals diagnosed with major depressive disorder (MDD) and bipolar disorder (BD), as well as non-depressive controls. Of these, 977 samples were used for high-throughput small RNA sequencing to establish a comprehensive circulating sRNA expression profile. The cohort included 204 MDD patients, 37 BD patients, and 427 non-depressive controls (417 healthy individuals and 10 individuals with other mental illnesses). All samples were recruited from Nanjing Brain Hospital and Nanjing University School of Medicine Affiliated Gulou Hospital (Table 4). A total of 375 individuals (MDD patients and healthy controls) had Hamilton Depression Rating Scale (HAMD-24) scores, of which 168 individuals scored >20, indicating moderate to severe depressive symptoms. The independent validation cohort included 139 MDD patients, 61 BD patients, and 109 non-depressive controls (including 83 healthy controls and 26 individuals with other mental illnesses), recruited from Guangzhou Brain Hospital Affiliated to Guangzhou Medical University and Lianyungang Fourth People's Hospital (Table 4). To further evaluate the diagnostic potential of circulating sRNA, blinded qRT-PCR was performed in a testing cohort comprising 81 MDD patients, 67 BD patients, and 145 healthy controls, all recruited at initial clinical diagnosis from Nanjing Brain Hospital and Guangzhou Brain Hospital Affiliated to Guangzhou Medical University.

[0040] The clinical and demographic characteristics of the study participants are shown in Table 4.

[0041] Table 4

[0042] 2. Subject Recruitment All patients (MDD, BD, and other mental illnesses) were diagnosed by trained psychiatrists through structured clinical interviews according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revised. Clinical assessments were conducted independently by two senior psychiatrists. Participants were eligible regardless of family history of mental illness. Participants were divided into four groups based on the following criteria: major depressive disorder, bipolar disorder, other mental illnesses (schizophrenia), and a healthy control group. (1) MDD group Inclusion criteria: (i) diagnosed with MDD according to DSM-5 criteria and with a score of ≥20 on the 24-item Hamilton Depression Rating Scale; (ii) aged 18–60 years; (iii) Han Chinese ethnicity; (iv) obtained written informed consent from the participant and their legal guardian.

[0043] Exclusion criteria: (i) mental symptoms secondary to a neurological disorder, organic brain disease or other physical illness; (ii) a disease diagnosed according to DSM-5 other than MDD; (iii) current or past use, abuse or dependence on psychoactive substances other than tobacco or alcohol; (iv) an active physical illness of clinical significance; (v) pregnancy or lactation.

[0044] (2) BD group Inclusion criteria: (i) diagnosed with BD according to DSM-5 criteria; (ii) aged 18–60 years; (iii) Han Chinese ethnicity; (iv) obtained written informed consent from the participant and their legal guardian.

[0045] Exclusion criteria: Same as for the MDD group, but applicable to BD-specific DSM-5 diagnoses.

[0046] (3) Other mental illnesses (schizophrenia) Inclusion criteria: (i) diagnosed with schizophrenia or schizophrenia spectrum disorder according to DSM-5; (ii) aged 18–60 years; (iii) Han Chinese nationality; (iv) obtaining written informed consent from the participant and their legal guardian.

[0047] Exclusion criteria: Same as group BD.

[0048] (4) Healthy control group Inclusion criteria: (i) no current or previous diagnosis of a mental disorder as defined in DSM-5; (ii) age 18–60 years; (iii) Han Chinese ethnicity; (iv) provision of written informed consent.

[0049] Exclusion criteria: (i) family history of mental disorder or suicide within three generations on the paternal or maternal side; (ii) presence of neurological disorder; (iii) use of any medication within the past two weeks; (iv) clinically significant active physical illness; (v) current or past suicidal ideation or behavior; (vi) pregnancy or lactation.

[0050] 3. Sample collection and small RNA isolation All samples in this experiment were plasma. Blood was collected between 7:00 AM and 10:00 AM, and participants were fasting (had not eaten since 8:00 PM the previous night). Venous blood was drawn from the antecubital vein using a 21-gauge needle and collected in 5 mL BD Vacutainer plasma separation tubes containing PPT gel and K2EDTA. Samples were transported vertically at room temperature and processed within 30 minutes of collection. Plasma was separated by centrifugation at 3,000 × g for 10 minutes (20°C). 1 mL of plasma was aliquoted into 1.5 mL low-protein binding tubes, flash-frozen in liquid nitrogen, and stored at –80°C until use. Circulating small RNAs were extracted from 300 μL plasma samples using the TIANGEN RNAsimple Total RNA Kit, strictly following the manufacturer's instructions.

[0051] 4. Small RNA library construction and sequencing All sRNA library construction and deep sequencing were performed by BGI Genomics (Shenzhen, China). The simplified procedure involved constructing libraries using the TruSeq Small RNA Sample Prep Kit and sequencing them on an Illumina HiSeq 4000 platform after quality validation. Raw reads were filtered to remove low-quality sequences based on the following criteria: (i) reads containing more than 4 bases with a mass fraction <10 or more than 6 bases with a mass fraction <13; (ii) reads containing 5' primer contamination or lacking a 3' primer; (iii) reads without insert tags; (iv) reads containing poly(A) sequences; and (v) reads shorter than 18 nucleotides. Clean reads were retained for downstream analysis.

[0052] 5. Small RNA Data Processing and Annotation Sequence reads that did not meet the following quality control criteria were excluded: quality fraction below 25 and length less than 18 nucleotides. The resulting clean reads were then compared sequentially with the following non-coding RNA databases: (i) miRNA database, miRBase v22; (ii) genomic tRNA database, GtRNAdb (based on hg19); (iii) rRNA database assembled from the National Center for Biotechnology Information's Nucleotide and Gene Database; and (iv) piRNA database, piRBase release v3.0.

[0053] Based on the above dataset, sRNAs were annotated, and miRDeep2 was used to identify matches between precursor and mature miRNAs. piRNA annotation was performed using Bowtie, accepting only candidate sequences with no more than three mismatches. Furthermore, tsRNA and rsRNA sequences were annotated using SPORTS 1.1 software (an updated version of SPORTS 1.0, utilizing Bowtie).

[0054] 6. Standardization and Filtration To standardize, the total sequencing frequency of each type of sRNA in each sample was normalized to 1,000,000 and then transformed using the log10(x+1) formula. To ensure data integrity, sRNAs absent in more than 50% of the samples were excluded from subsequent analyses, and batch effects were corrected using the SVA software package. After filtering, the following types of sRNAs were retained for downstream analysis: 367 miRNAs, 291 rsRNAs, 99 tsRNAs, and 66 piRNAs, for a total of 823 integrated sRNAs. For each sRNA, the normality of the data distribution was assessed using the Shapiro–Wilk test using the stats.shapiro function in Python 3.11.5. To present sRNAs concisely in this paper, their names have been simplified or numbered; a list of names is provided in Table 5.

[0055] Table 5

[0056] 7. Differential Expression Analysis Pairwise comparisons of differentially expressed sRNAs were performed across different population stratifications, with thresholds set at >1.5 or <0.67 based on the fold change between the medians of the two groups. Considering the data distribution characteristics, a two-sided Mann–Whitney U test (a nonparametric equivalent of the unpaired t-test) was used to assess statistical significance. The p-values ​​were adjusted using the Benjamini-Hochberg method for multiple hypothesis testing correction; an adjusted p-value <0.05 was considered to indicate a significant difference in sRNA expression levels. Data analysis and visualization were performed using R (version 4.4.1).

[0057] 8. Machine Learning Model Construction To leverage the diagnostic potential of various sRNAs in MDD, a dataset containing 823 sRNAs covering four different sRNA types was compiled. Machine learning models were developed to assist healthcare professionals in differentiating between MDD and BD. The diagnostic performance of nine machine learning algorithms on individual sRNA subtypes and integrated sRNA datasets was evaluated, including random forest, adaptive boosting, support vector machine, LightGBM, gradient boosting decision tree, extreme gradient boosting, CatBoost, logistic regression, and multilayer perceptron.

[0058] To reduce selection bias and ensure that the model's performance is not affected by the characteristics of a single hospital or population, participants from Nanjing Brain Hospital and Nanjing University School of Medicine Affiliated Gulou Hospital were designated as the discovery cohort, while participants from Guangzhou Medical University Affiliated Brain Hospital and Lianyungang Fourth People's Hospital were designated as the independent validation cohort.

[0059] Hyperparameter tuning was performed within the discovery queue using five-fold cross-validation, and the parameter space specific to each algorithm was thoroughly explored using grid search. Considering the inherent class imbalance in some classification tasks, appropriate class imbalance correction techniques were incorporated into the model development process. Parameter ranges are listed in Table 6.

[0060] Table 6

[0061] The model was developed using Python 3.11.7 and the scikit-learn library, supplemented by the xgboost, lightgbm, and catboost libraries.

[0062] 9. Model Performance Evaluation and MOMP Construction To comprehensively evaluate and improve the diagnostic potential of circulating sRNA-based MDD versus BD, a multi-objective model prioritization framework was developed for constructing robust MDD diagnostic models and discovering biomarkers. An initial model pool was generated by training nine machine learning algorithms on a discovery cohort, and tenfold cross-validation was applied to mitigate overfitting. The dataset was divided into ten equal-sized, non-overlapping subsets, preserving the original class distribution to maintain statistical representativeness. In each fold iteration, one subset was designated as the internal validation set, and the remaining nine were used for model training. This process was repeated across all folds to ensure that each sample served as a validation instance exactly once. Performance metrics were averaged across folds to produce a stable estimate of the model's generalization ability. Independent external validation cohorts from Guangzhou Brain Hospital Affiliated to Guangzhou Medical University and the Fourth People's Hospital of Lianyungang City were used to further evaluate the model's generalization ability and stability.

[0063] To evaluate model performance, the true positive rate, true negative rate, false positive rate, and false negative rate were calculated, and six key evaluation metrics were subsequently derived: sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient. The calculation formulas are shown below:

[0064] Receiver operating characteristic (ROC) curves were constructed using sensitivity and 1-specificity scores, and the area under the curve was calculated. A bootstrap resampling strategy was employed (1,000 iterations), and results were reported as mean and 95% confidence intervals.

[0065] The algorithm involved employs a random forest ML model.

[0066] 10. Feature Explanation For feature interpretation, SHAP analysis was applied using the validation dataset. SHAP plots were used to visualize feature effects, where color gradients represent effect magnitudes and directionality indicates the likelihood of a particular outcome. This method was able to identify sRNAs with high predictive importance.

[0067] 11. Importance ranking of sRNAs Random forest was selected as the optimal model due to its superior AUC performance in managing tradeoffs across multiple task settings. To refine the feature set, hierarchical clustering was performed on the integrated dataset of 823 sRNAs based on Spearman rank correlation, thereby eliminating redundant sRNAs exhibiting multicollinearity. From each cluster, sRNAs with the highest AUC values ​​were retained (determined based on the training set of the random forest model on the full feature set). Subsequently, the remaining features were ranked according to their contribution to classification performance, and those features that accounted for more than 90% of the cumulative model gain were selected, with their contribution quantified as the mean information gain and the SHAP value (these metrics reflect the efficacy of each sRNA in distinguishing between depressed subjects and control subjects).

[0068] 12. Establishment of integrated sRNA assemblages To enhance the clinical applicability of the research results, the feature selection process was further refined to determine the minimum combination of sRNAs that maximizes discriminative performance for each diagnostic category. Specifically, a sequential forward selection strategy was implemented, progressively integrating sRNAs into the model classifier based on the top-ranked features, and reordering them based on the updated importance ranking. The selection process terminated when two consecutive DeLong tests showed no significant improvement in classification performance. Final validation was performed using an independent external test set to ensure robustness and provide diverse options for potential clinical applications.

[0069] 13. Small RNA one-step stem-loop RT-qPCR detection The reaction mixture for SYBR Green one-step stem-loop RT-qPCR consists of the following: 2 μL RNA template, 0.3 μL Super M-MLV reverse transcriptase, 0.6 μL hot-start HiTaq DNA polymerase, 6 μL 5× one-step RT-PCR buffer, 3 μL 10× Solution I, 0.25 μL dNTPs, and 0.3 μL RNase inhibitor. Additionally, it includes 1 μL SYBR Green dye, 0.5 μL stem-loop reverse transcription primers, 1 μL reverse amplification primers, and 1 μL forward amplification primers. The final volume is adjusted to 30 μL with nuclease-free water. Primers were synthesized by Universal Biotech, and all other reagents were purchased from Phytobio.

[0070] To further understand this application, the following detailed description is provided in conjunction with the preferred embodiments.

[0071] Example 1 In this study, circulating small RNAs (sRNAs) were deeply sequenced from 977 individuals to identify features for the diagnosis of MDD and its correlation with BD. A classification model was developed and validated using a machine learning-based prioritization framework, identifying a biomarker ensemble consisting of nine sRNAs. This ensemble was further validated in independent cohorts using quantitative reverse transcription polymerase chain reaction (RT-PCR). The results of this study provide a scalable, non-invasive diagnostic framework, representing a potential breakthrough in precision psychiatry by enabling objective MDD detection using circulating sRNAs.

[0072] (1) A multicenter cohort containing 1270 plasma samples with clinical diagnostic records was analyzed, of which 977 samples underwent small RNA sequencing for diagnostic model development and external validation; another independent cohort was used for qRT-PCR-based validation.

[0073] (2) The MOMP framework includes: sRNA-seq data preprocessing; systematic evaluation of nine machine learning classifiers through parameter grid search, discovery of 10x cross-validation in the queue and external validation; and the use of a random forest model in the validation phase to balance diagnostic accuracy and clinical deployability, thereby selecting the best diagnostic model for MDD.

[0074] (3) Based on the comprehensive feature importance and differential expression analysis, sRNAs that can distinguish between MDD and BD were screened out, and a specific diagnostic combination for MDD was constructed.

[0075] (4) The candidate sRNAs in the combination were experimentally validated by qRT-PCR in an independent cohort, demonstrating their consistency with the sequencing results and their potential for clinical translation.

[0076] Identification of circulating small RNA characteristics in MDD: A total of 1270 plasma samples were collected from four hospitals. After quality control, 977 samples were used for small RNA sequencing, including 343 patients with MDD, 500 healthy controls, 36 patients with other mental illnesses, and 98 patients with BD. An additional 293 samples were used for independent validation of selected biomarkers via qRT-PCR. To reduce selection bias and improve generalization, the sequencing cohort was divided into a discovery cohort and an external validation cohort based on hospital location. Clinical and demographic information is summarized in Table 4.

[0077] High-throughput sRNA sequencing identified four major classes of sRNAs: microRNAs, ribosomal RNA-derived sRNAs, transfer RNA-derived sRNAs, and PIWI-interacting RNAs. The sequence length distribution of these sRNA subtypes showed subtle but consistent differences among MDD patients, non-depressed controls (including healthy individuals and other mental illness patients), and BD patients. miRNAs had the highest abundance, with a narrow peak at 21–23 nucleotides. rsRNAs were more widely distributed (18–28 nt), while tsRNAs and piRNAs spanned longer segments (28–35 nt). Compared to controls and BD, MDD samples showed lower miRNA abundance, a narrower length range, and shorter tsRNA fragments. After data preprocessing, 823 high-confidence circulating sRNAs were identified, including 367 miRNAs, 291 rsRNAs, 99 tsRNAs, and 66 piRNAs (Table 5). Principal coordinate analysis based on normalized expression values ​​revealed partially different sRNA expression patterns among MDD patients, non-depressed controls, and BD individuals. Despite some intergroup segregation, there is still a significant amount of overlap, highlighting the need for specific molecular markers to differentiate MDD.

[0078] Differential abundance analysis between MDD patients and non-depressed controls identified 447 significantly altered circulating sRNAs (54.3%), including 192 miRNAs, 168 rsRNAs, 52 tsRNAs, and 35 piRNAs (fold change >1.5 or <0.67; corrected P <0.05) (as shown in Table 7). Of these, 151 sRNAs were downregulated in MDD, and 96 were upregulated. In separate comparisons between MDD and BD, 603 differentially abundant sRNAs were detected, with 268 upregulated and 335 downregulated in MDD. Notably, significant downregulation of miRNAs was observed in both comparisons, highlighting a unique sRNA expression pattern that distinguishes MDD from BD and controls.

[0079] Table 7

[0080]

[0081]

[0082]

[0083]

[0084]

[0085] To identify MDD-specific molecular signatures, circulating sRNA profiles were compared between MDD, BD, and healthy controls. This cross-comparison analysis revealed 172 MDD-specific miRNAs, 133 rsRNAs, 42 tsRNAs, and 32 piRNAs. Recent evidence suggests that tsRNAs, rsRNAs, and piRNAs may have functions similar to miRNAs, including direct mRNA binding and translation regulation. To explore the biological relevance of these MDD-related sRNAs, gene ontology enrichment analysis was performed on their predicted target genes. The top enriched biological processes included calcium channel regulation, amyloid precursor protein metabolism, protein kinase C signaling, mitochondrial membrane potential regulation, and monocyte differentiation. KEGG pathway analysis further revealed significant enrichment in lysosomal and apoptosis pathways, dopaminergic synaptic signaling, and calcium signaling pathways—pathways previously identified as being involved in the pathophysiology of MDD. These results suggest that the unique sRNA expression signatures in MDD may regulate neurobiological pathways associated with disease occurrence and progression, supporting their potential use as biomarkers for diagnosis and disease stratification.

[0086] Development of a diagnostic model for MDD based on circulating sRNA: To evaluate the diagnostic potential of circulating sRNA in MDD, a multi-objective model prioritization framework integrating nine machine learning algorithms was developed.

[0087] Using this framework, each of the four major sRNA classes demonstrated high diagnostic accuracy in internal 10-fold cross-validation. Integrating a single classifier for all 823 sRNAs further improved performance, with the best model achieving an AUC of 0.923 when distinguishing between the external validation set of MDD and BD.

[0088] Optimized biomarker combinations for non-invasive diagnosis of MDD and BD: To improve clinical applicability, a minimal subset of circulating sRNAs with high discriminative power for MDD and BD was selected. The Random Forest algorithm—selected for its superior AUC performance within the MOMP framework—was used to prioritize features capable of stratifying MDD and BD patients. To address multicollinearity, hierarchical clustering was applied to all 823 sRNAs, and redundant features were removed. Subsequently, features were ranked according to their importance in the training set, and a sequential forward selection strategy was employed to identify sRNAs contributing more than 90% of the cumulative model gain.

[0089] In the task of distinguishing between MDD and BD, miR-20a-5p and miR-93-5p were identified as the top-ranking features (0.0336 and 0.0332, respectively). Adding additional sRNAs improved classification performance. In the external validation cohort, a combination containing nine sRNAs achieved an AUC of 0.853 (95% CI, 0.796–0.891), with a sensitivity of 82.73% and a specificity of 75.41%. Simultaneously, a simplified method expansion using qPCR also achieved diagnostic performance of AUC = 0.988 in the PCR cohort. These results support the feasibility of using minimized circulating sRNA signatures for accurate and scalable differential diagnosis of MDD and BD, demonstrating robust performance across validation cohorts and relevant clinical subgroups.

[0090] MDD and BD share overlapping depressive symptoms, often leading to misdiagnosis and inappropriate treatment. Many BD patients initially present during a depressive episode, with manic or hypomanic symptoms potentially appearing years later. Consequently, the average diagnosis of BD is delayed by nine years, and up to 12.4% of patients initially diagnosed with MDD are later reclassified. In our study, circulating tsRNAs exhibited the highest discriminative power. A combination of nine sRNAs further improved classification accuracy. These findings support the potential of sRNA-based analyses as a molecular tool to aid in the early and accurate differentiation between MDD and BD.

[0091] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A combination of biomarkers for the auxiliary diagnosis of depression and bipolar disorder, characterized in that, The combination of markers includes one or more of miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, piR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i; their sequences are shown as SEQ ID No. 1-SEQ ID No. 9, respectively.

2. The application of a primer combination in the preparation of reagents for the auxiliary diagnosis of depression and bipolar disorder, characterized in that, The combination of markers includes one or more of miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, piR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i; their sequences are shown as SEQ ID No. 1 to SEQ ID No. 9, respectively.

3. The application according to claim 2, characterized in that, The primer set includes primers for detecting at least one sRNA marker among miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i. The primer set consists of reverse transcription primers and primer pairs, wherein: The nucleotide sequences of the reverse transcription primers used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i are shown in SEQ ID No. 10-SEQ ID No.

18. The primer pair used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i consists of an upstream primer and a downstream primer. The nucleotide sequences of the upstream primer are shown in SEQ ID No. 19-SEQ ID No. 27, and the nucleotide sequences of the downstream primer are shown in SEQ ID No. 28-SEQ ID No. 36, respectively.

4. The application of a biomarker combination in the preparation of a reagent kit for the auxiliary diagnosis of depression and bipolar disorder, characterized in that, The kit is a real-time quantitative qRT-PCR kit, and the biomarker combination is the biomarker combination described in claim 1.

5. The application according to claim 4, characterized in that, The kit includes primer combinations for the auxiliary diagnosis of depression and bipolar disorder. These primer combinations include primer combinations for detecting at least one sRNA marker among miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i. The primer combinations consist of reverse transcription primers and primer pairs, wherein: The nucleotide sequences of the reverse transcription primers used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i are shown in SEQ ID No. 10-SEQ ID No.

18. The primer pair used to detect miR-20a-5p, miR-93-5p, miR-92a-1-5p, miR-532-5p, miR-35389, miR-1827, miR-7-5p, miR-378f, and miR-378i consists of an upstream primer and a downstream primer. The nucleotide sequences of the upstream primer are shown in SEQ ID No. 19-SEQ ID No. 27, and the nucleotide sequences of the downstream primer are shown in SEQ ID No. 28-SEQ ID No. 36, respectively.

6. The application according to claim 5, characterized in that, The kit also includes a total sRNA extraction reagent set and an RNA reverse transcription reagent set.

7. The application according to claim 6, characterized in that, The total sRNA extraction reagent kit includes protein denaturation lysis buffer, chloroform, ethanol, and washing buffer.

8. The application according to claim 6, characterized in that, The RNA reverse transcription reagent kit includes reverse transcription primers, reverse transcription reaction buffer, and reverse transcriptase mixture.

9. The application according to claim 8, characterized in that, The kit also includes primers for amplifying the internal reference gene U6; the sequence of the primers for amplifying the internal reference gene U6 is as follows: Forward primer for internal reference gene U6: GCTTCGGCAGCACATATACTAAA; Reverse primer for internal reference gene U6: TTTGCGTGTCATCCTTGCG.

10. The application according to claim 9, characterized in that, The reaction conditions for the one-step real-time quantitative qRT-PCR method are as follows: 16℃ for 5 min; 50℃ for 15 min; 95℃ for 10 min; 95℃ for 15 s; 60℃ for 40 s; 50 cycles, with fluorescence signal detected and acquired at 60℃.

Images