A new online detection method of tobacco impurities for tobacco robot.

In the tobacco industry, impurity detection is an important prerequisite for ensuring the quality of tobacco. However, in the actual production process, the complex background environment and the variability of impurity shapes can affect the accuracy of impurity detection by tobacco robots, which leads to a decrease in product quality and an increase in health risks. To address this problem, we propose a new online detection method of tobacco impurities for tobacco robot. Firstly, a BCFormer attention mechanism module is designed to effectively mitigate the interference of irrelevant information in the image and improve the network's ability to identify regions of interest. Secondly, a Dual Feature Aggregation (DFA) module is designed and added to Neck to improve the accuracy of tobacco impurities detection by augmenting the fused feature maps with deep semantic and surface location data. Finally, to address the problem that the traditional loss function cannot accurately reflect the distance between two bounding boxes, this paper proposes an optimized loss function to more accurately assess the quality of the bounding boxes. To evaluate the effectiveness of the algorithm, this paper creates a dataset specifically designed to detect tobacco impurities. Experimental results show that the algorithm performs well in identifying tobacco impurities. Our algorithm improved the mAP value by about 3.01% compared to the traditional YOLOX method. The real-time processing efficiency of the model is as high as 41 frames per second, which makes it ideal for automated inspection of tobacco production lines and effectively solves the problem of tobacco impurity detection.

Nature-Inspired Incorporation of Precipitants into High-Strength Bulk Aluminum Alloys Enables Life-Long Extraordinary Corrosion Resistance in Diverse Aqueous Environments.

The safe service and wide applications of lightweight high-strength aluminum alloys are seriously challenged by diverse environmental corrosion, since high strength and corrosion resistance are mutually exclusive for metals while surface protection cannot provide life-long corrosion resistance. Here, inspired by fish secreting slime from glands to resist external changes, a strategy of incorporating precipitants as the slime into bulk metals using the inner cavity of opened carbon nanotubes (CNTs) as the glands is developed to enable high-strength aluminum alloys with life-long superior corrosion resistance. The resulting material has ultrahigh tensile strength (≈700 MPa) and extraordinary corrosion resistance in acidic, neutral and alkaline media. Notably, it has the highest resistance to intergranular corrosion, exfoliation corrosion and stress-corrosion cracking, compared with all previously reported aluminum alloys, and its corrosion rate is even much lower than that of corrosion-resistant pure aluminum, which results from the pronounced surface enrichment of precipitants released (secreted) from exposed CNTs forming a protective surface film. Such high corrosion resistance is life-long and self-healing due to the on-demand minimal self-supply of the precipitants dispersed throughout the bulk material. This strategy can be readily expanded to other aluminum alloys, and could pave the way for developing corrosion-resistant high-strength metallic materials.

The GABAergic pathway from anterior cingulate cortex to lateral hypothalamus area regulates irritable bowel syndrome in mice and its underlying mechanism.

Irritable bowel syndrome (IBS), which is characterized by chronic abdominal pain, has a high global prevalence. The anterior cingulate cortex (ACC), which is a pivotal region involved in pain processing, should be further investigated regarding its role in the regulation of visceral sensitivity and mental disorders. A C57BL/6J mouse model for IBS was established using chronic acute combining stress (CACS). IBS-like symptoms were assessed using behavioral tests, intestinal motility measurements, and abdominal withdrawal reflex scores. Fluoro-Gold retrograde tracing and immunohistochemistry techniques were employed to investigate the projection of ACC gamma-aminobutyric acid-producing (GABAergic) neurons to the lateral hypothalamus area (LHA). Chemogenetic approaches enabled the selective activation or inhibition of the ACC-LHA GABAergic pathway. Enzyme-linked immunosorbent assay (ELISA) and western blot analyses were conducted to determine the expression of histamine, 5-hydroxytryptamine (5-HT), and transient receptor potential vanilloid 4 (TRPV4). Our findings suggest that CACS induced IBS-like symptoms in mice. The GABA type A receptors (GABAAR) within LHA played a regulatory role in modulating IBS-like symptoms. The chemogenetic activation of ACC-LHA GABAergic neurons elicited anxiety-like behaviors, intestinal dysfunction, and visceral hypersensitivity in normal mice; however, these effects were effectively reversed by the administration of the GABAAR antagonist Bicuculline. Conversely, the chemogenetic inhibition of ACC-LHA GABAergic neurons alleviated anxiety-like behaviors, intestinal dysfunction, and visceral hypersensitivity in the mouse model for IBS. These results highlight the crucial involvement of the ACC-LHA GABAergic pathway in modulating anxiety-like behaviors, intestinal motility alterations, and visceral hypersensitivity, suggesting a potential therapeutic strategy for alleviating IBS-like symptoms.

CKG-IMC: An inductive matrix completion method enhanced by CKG and GNN for Alzheimer's disease compound-protein interactions prediction.

Alzheimer's disease (AD) is one of the most prevalent chronic neurodegenerative disorders globally, with a rapidly growing population of AD patients and currently no effective therapeutic interventions available. Consequently, the development of therapeutic anti-AD drugs and the identification of AD targets represent one of the most urgent tasks. In this study, in addition to considering known drugs and targets, we explore compound-protein interactions (CPIs) between compounds and proteins relevant to AD. We propose a deep learning model called CKG-IMC to predict Alzheimer's disease compound-protein interaction relationships. CKG-IMC comprises three modules: a collaborative knowledge graph (CKG), a principal neighborhood aggregation graph neural network (PNA), and an inductive matrix completion (IMC). The collaborative knowledge graph is used to learn semantic associations between entities, PNA is employed to extract structural features of the relationship network, and IMC is utilized for CPIs prediction. Compared with a total of 16 baseline models based on similarities, knowledge graphs, and graph neural networks, our model achieves state-of-the-art performance in experiments of 10-fold cross-validation and independent test. Furthermore, we use CKG-IMC to predict compounds interacting with two confirmed AD targets, 42-amino-acid ß-amyloid (Aß42) protein and microtubule-associated protein tau (tau protein), as well as proteins interacting with five FDA-approved anti-AD drugs. The results indicate that the majority of predictions are supported by literature, and molecular docking experiments demonstrate a strong affinity between the predicted compounds and targets.

Study on the impact of smart city construction on the health of the elderly population--A quasi-natural experiment in China.

In the context of global aging, promoting the health of the elderly has become a critical issue. However, whether the development of smart cities can impact the health of older adults remains to be further validated. In this paper, based on panel data from the China Health and Retirement Longitudinal Study (CHARLS), a difference in difference model is used to empirically investigate whether smart city construction improves the health of older people in the region. The results show that smart city construction enhances the health of the elderly. Specifically, the construction achieved a significant improvement in the physical health of the elderly who did not live with their children. The health promotion effect of the smart city was more significant for the urban elderly than for the rural elderly. The elucidated mechanisms of influence suggest that smart cities bring about their effects through the promotion of urban leisure infrastructure, enhancement of medical service provision, advancement in urban environmental protection and stimulation of urban information and communication technology infrastructure development.

The Influence of Heat Treatment on the Microstructure and Properties of a Cu-Bearing Ultra-Low Carbon Steel.

This study reveals the relationship between the Cu precipitates and mechanical properties of a Cu-baring ultra-low carbon steel after two-phase zone quenching and tempering at 923 K for 0.5-2.5 h. The tensile and microstructural properties were investigated as a function of heat treatment time. The contribution of the precipitation-strengthening mechanism to yield strength was calculated. The size, morphology, and distribution of the precipitated particles were observed using TEM. As the heat treatment time increased, the strength gradually decreased and then remained stable, and the elongation gradually increased and then remained stable. Additionally, the contributions of each strengthening mechanism to the yield strength under different heat treatments were 117, 107, 102, and 89 MPa, respectively. The size and quantity of the precipitates increased with the increase in heat treatment time. After tempering for more than 2 h, the precipitates continued to coarsen, but their quantity decreased. The precipitated Cu had a 3R structure with a length of approximately 17.1 nm and a width of approximately 9.7 nm, with no twinning inside. The stacking order was ABC/ABC. The stable Cu precipitation structure was FCC, maintaining a K-S orientation relationship 11¯1FCC Cu //(0 1 1) α, 1¯10FCC Cu//[11¯1] α.

Transcutaneous auricular vagal nerve stimulation for consciousness recovery in patients with prolonged disorders of consciousness (TAVREC): study protocol for a multicenter, triple-blind, randomized controlled trial in China.

INTRODUCTION: Prolonged disorders of consciousness (pDoC) are a catastrophic condition following brain injury with few therapeutic options. Transcutaneous auricular vagal nerve stimulation (taVNS), a safe, non-invasive intervention modulating thalamo-cortical connectivity and brain function, is a possible treatment option of pDoC. We developed a protocol for a randomised controlled study to evaluate the effectiveness of taVNS on consciousness recovery in patients with pDoC (TAVREC). METHODS AND ANALYSIS: The TAVREC programme is a multicentre, triple-blind, randomised controlled trial with 4 weeks intervention followed by 4 weeks follow-up period. A minimum number of 116 eligible pDoC patients will be recruited and randomly receive either: (1) conventional therapy plus taVNS (30 s monophasic square current of pulse width 300 µs, frequency of 25 Hz and intensity of 1 mA followed by 30 s rest, 60 min, two times per day, for 4 weeks); or (2) conventional therapy plus taVNS placebo. Primary outcome of TAVREC is the rate of improved consciousness level based on the Coma Recovery Scale-Revised (CRS-R) at week 4. Secondary outcomes are CRS-R total and subscale scores, Glasgow Coma Scale score, Full Outline of UnResponsiveness score, ECG parameters, brainstem auditory evoked potential, upper somatosensory evoked potential, neuroimaging parameters from positron emission tomography/functional MRI, serum biomarkers associated with consciousness level and adverse events. ETHICS AND DISSEMINATION: This study was reviewed and approved by the Research Ethics Committee of the First Affiliated Hospital of Nanjing Medical University (Reference number: 2023-SR-392). Findings will be disseminated in a peer-reviewed journal and presented at relevant conferences. TRIAL REGISTRATION NUMBER: ChiCTR2300073950.

m6A epitranscriptomic modification of inflammation in cardiovascular disease.

Cardiovascular disease is currently the number one cause of death endangering human health. There is currently a large body of research showing that the development of cardiovascular disease and its complications is often accompanied by inflammatory processes. In recent years, epitranscriptional modifications have been shown to be involved in regulating the pathophysiological development of inflammation in cardiovascular diseases, with 6-methyladenine being one of the most common RNA transcriptional modifications. In this review, we link different cardiovascular diseases, including atherosclerosis, heart failure, myocardial infarction, and myocardial ischemia-reperfusion, with inflammation and describe the regulatory processes involved in RNA methylation. Advances in RNA methylation research have revealed the close relationship between the regulation of transcriptome modifications and inflammation in cardiovascular diseases and brought potential therapeutic targets for disease diagnosis and treatment. At the same time, we also discussed different cell aspects. In addition, in the article we also describe the different application aspects and clinical pathways of RNA methylation therapy. In summary, this article reviews the mechanism, regulation and disease treatment effects of m6A modification on inflammation and inflammatory cells in cardiovascular diseases in recent years. We will discuss issues facing the field and new opportunities that may be the focus of future research.

Implications of GCLC in prognosis and immunity of lung adenocarcinoma and multi-omics regulation mechanisms.

BACKGROUND: Ferroptosis is an iron-dependent type of regulated cell death, and has been implicated in lung adenocarcinoma (LUAD). Evidence has proved the key role of glutamate-cysteine ligase catalytic subunit (GCLC) in ferroptosis, but its role in LUAD remains unclear. Herein, we explored the implications of GCLC and relevant genes in LUAD prognosis and immunity as well as underlying molecular mechanisms. METHODS: This work gathered mRNA, miRNA, DNA methylation, somatic mutation and copy-number variation data from TCGA-LUAD. WGCNA was utilized for selecting GCLC-relevant genes, and a GCLC-relevant prognostic signature was built by uni- and multivariate-cox regression analyses. Immune compositions were estimated via CIBERSORT, and two immunotherapy cohorts of solid tumors were analyzed. Multi-omics regulatory mechanisms were finally assessed. RESULTS: Our results showed that GCLC was overexpressed in LUAD, and potentially resulted in undesirable survival. A prognostic model was generated, which owned accurate and independent performance in prognostication. GCLC, and relevant genes were notably connected with immune compositions and immune checkpoints. High GCLC expression was linked with better responses to anti-PD-L1 and anti-CTLA-4 treatment. Their possible DNA methylation sites were inferred, e.g., hypomethylation in cg19740353 might contribute to GCLC up-regulation. Frequent genetic mutations also affected their expression. Upstream transcription factors (E2F1/3/4, etc.), post-transcriptional regulation of miRNAs (hsa-mir-30c-1, etc.), lncRNAs (C8orf34-AS1, etc.), and IGF2BP1-mediated m6A modification were identified. It was also found NOP58-mediated SUMOylation post-translational modification. CONCLUSIONS: Together, we show that GCLC and relevant genes exert crucial roles in LUAD prognosis and immunity, and their expression can be controlled by complex multi-omics mechanisms.

Exploring the association between multiple factors and urolithiasis: A retrospective study and Mendelian randomization analysis.

To investigate the relationship between several factors and urinary stone as well as different stone compositions. To guide the diagnosis, treatment, and prevention of urinary stone recurrence. We used bidirectional Mendelian randomization to analyze the causal relationship between hypertension and urinary stones, diabetes and urinary stones, and body mass index (BMI) and urinary stones. We retrospectively analyzed the medical records of patients with urinary stones admitted to a tertiary care hospital in Chongqing, China, from July 2015 to October 2022. Patients were included when they were first diagnosed with urinary stones. The odds ratio of calculi on hypertension estimated by inverse variance weighted was 8.46 (95%CI: 4.00-17.90, P = 2.25 × 10-8). The stone composition analysis showed that there were 3101 (67.02%) mixed, 1322 (28.57%) calcium oxalate monohydrate, 148 (3.20%) anhydrous uric acid, 16 (0.35%) magnesium ammonium phosphate hexahydrate, 11 (0.24%) dicalcium phosphate dihydrate, 10 (0.22%) carbonate apatite, 8 (0.17%) L-cystine, 4 ammonium uric acid (0.09%), and 7 other stone types (0.15%). Mendelian randomization studies have proven that urinary stones may be a potential risk factor for hypertension, while there is no causal relationship between diabetes and stones, BMI, and stones. Our retrospective study has shown that urinary stone components are closely associated with sex, age, hypertension, diabetes, and BMI. It is reasonable to suspect that treating a single stone component is ineffective in preventing recurrence. We also found that the peak incidence of urinary stones was at the most active stage of most people's working lives.

Patient-derived induced pluripotent stem cells with a MERTK mutation exhibit cell junction abnormalities and aberrant cellular differentiation potential.

BACKGROUND: Human induced pluripotent stem cell (hiPSC) technology is a valuable tool for generating patient-specific stem cells, facilitating disease modeling, and investigating disease mechanisms. However, iPSCs carrying specific mutations may limit their clinical applications due to certain inherent characteristics. AIM: To investigate the impact of MERTK mutations on hiPSCs and determine whether hiPSC-derived extracellular vesicles (EVs) influence anomalous cell junction and differentiation potential. METHODS: We employed a non-integrating reprogramming technique to generate peripheral blood-derived hiPSCs with and hiPSCs without a MERTK mutation. Chromosomal karyotype analysis, flow cytometry, and immunofluorescent staining were utilized for hiPSC identification. Transcriptomics and proteomics were employed to elucidate the expression patterns associated with cell junction abnormalities and cellular differentiation potential. Additionally, EVs were isolated from the supernatant, and their RNA and protein cargos were examined to investigate the involvement of hiPSC-derived EVs in stem cell junction and differentiation. RESULTS: The generated hiPSCs, both with and without a MERTK mutation, exhibited normal karyotype and expressed pluripotency markers; however, hiPSCs with a MERTK mutation demonstrated anomalous adhesion capability and differentiation potential, as confirmed by transcriptomic and proteomic profiling. Furthermore, hiPSC-derived EVs were involved in various biological processes, including cell junction and differentiation. CONCLUSION: HiPSCs with a MERTK mutation displayed altered junction characteristics and aberrant differentiation potential. Furthermore, hiPSC-derived EVs played a regulatory role in various biological processes, including cell junction and differentiation.

Hybrid Cas12a Variants with Relaxed PAM Requirements Expand Genome Editing Compatibility.

Cas12a is a widely used programmable nuclease for genome editing across a variety of organisms, but its application is limited by its PAM recognition restriction. To alleviate these PAM constraints, protein engineering efforts have been applied to expand the PAM recognition range. In this study, we designed and constructed 990 synthetic hybrid Cas12a chimeras through domain shuffling and screened an efficient hybrid Cas12a (ehCas12a) that could recognize a broad range PAM of 5'-TYYN-3' (Y is T or C and N is A, T, C, or G). Furthermore, we constructed an ehCas12a variant, ehCas12a RRVR (T167R/N572R/K578V/N582R), with expanded PAM preference to 5'-TNYN, TWRV-3' (W is A or T, R is A or G, and V is A, C, or G), which can efficiently recognize -2* A/G PAMs that are barely recognized by Cas12a-type proteins and their mutants. Finally, we demonstrated that the DNase-inactivated ehCas12a RRVR base editor (dehCas12a RRVR-BE) was capable of targeting noncanonical PAMs in vivo and disease-related loci for potential therapeutic applications. Overall, our findings highlight the modular design and reconfiguration of Cas proteins for enhanced functionality.

Pointing Error Correction for Vehicle-Mounted Single-Photon Ranging Theodolite Using a Piecewise Linear Regression Model.

Pointing error is a critical performance metric for vehicle-mounted single-photon ranging theodolites (VSRTs). Achieving high-precision pointing through processing and adjustment can incur significant costs. In this study, we propose a cost-effective digital correction method based on a piecewise linear regression model to mitigate this issue. Firstly, we introduce the structure of a VSRT and conduct a comprehensive analysis of the factors influencing its pointing error. Subsequently, we develop a physically meaningful piecewise linear regression model that is both physically meaningful and capable of accurately estimating the pointing error. We then calculate and evaluate the regression equation to ensure its effectiveness. Finally, we successfully apply the proposed method to correct the pointing error. The efficacy of our approach has been substantiated through dynamic accuracy testing of a 450 mm optical aperture VSRT. The findings illustrate that our regression model diminishes the root mean square (RMS) value of VSRT's pointing error from 17″ to below 5″. Following correction utilizing this regression model, the pointing error of VSRT can be notably enhanced to the arc-second precision level.

Whole-transcriptome profiling and identification of cold tolerance-related ceRNA networks in japonica rice varieties.

Introduction: Low-temperature stress negatively impacts rice yield, posing a significant risk to food security. While previous studies have explored the physiological and linear gene expression alterations in rice under low-temperature conditions, the changes in competing endogenous RNA (ceRNA) networks remain largely unexamined. Methods: We conducted RNA sequencing on two japonica rice varieties with differing cold-tolerance capabilities to establish ceRNA networks. This enabled us to investigate the transcriptional regulatory network and molecular mechanisms that rice employs in response to low-temperature stress. Results: We identified 364 differentially expressed circular RNAs (circRNAs), 224 differentially expressed microRNAs (miRNAs), and 12,183 differentially expressed messenger RNAs (mRNAs). WRKY family was the most prominent transcription factor family involved in cold tolerance. Based on the expression patterns and targeted relationships of these differentially expressed RNAs, we discerned five potential ceRNA networks related to low-temperature stress in rice: osa-miR166j-5p from the miR166 family was associated with cold tolerance; osa-miR528-3p and osa-miR156j-3p were linked to stress response; and osa-miR156j-3p was involved in the antioxidant system. In addition, Os03g0152000 in the antioxidant system, as well as Os12g0491800 and Os05g0381400, correlated with the corresponding stress response and circRNAs in the network. A gene sequence difference analysis and phenotypic validation of Os11g0685700 (OsWRKY61) within the WRKY family suggested its potential role in regulating cold tolerance in rice. Discussion and conclusion: We identified Os11g0685700 (OsWRKY61) as a promising candidate gene for enhancing cold tolerance in japonica rice. The candidate miRNAs, mRNAs, and circRNAs uncovered in this study are valuable targets for researchers and breeders. Our findings will facilitate the development of cold-tolerant rice varieties from multiple angles and provide critical directions for future research into the functions of cold-tolerance-related miRNAs, mRNAs, and circRNAs in rice.

Low-loss tantalum pentoxide photonics with a CMOS-compatible process.

We report a Ta2O5 photonic platform with a propagation loss of 0.49 dB/cm at 1550 nm, of 0.86 dB/cm at 780 nm, and of 3.76 dB/cm at 2000 nm. The thermal bistability measurement is conducted in the entire C-band for the first time to reveal the absorption loss of Ta2O5 waveguides, offering guidelines for further reduction of the waveguide loss. We also characterize the Ta2O5 waveguide temperature response, which shows favorable thermal stability. The fabrication process temperature is below 350°C, which is friendly to integration with active optoelectronic components.

Narrative literature review of antidiabetic drugs' effect on hyperuricemia: elaborating actual data and mechanisms.

To optimize the treatment plan for patients with type 2 diabetes mellitus (T2DM) and hyperuricemia, this narrative literature review summarizes the effect of antidiabetic drugs on serum uric acid (SUA) levels using data from observational studies, prospective clinical trials, post hoc analyses, and meta-analyses. SUA is an independent risk factor for T2DM, and evidence has shown that patients with both gout and T2DM exhibit a mutually interdependent effect on higher incidences. We find that insulin and dipeptidyl peptidase 4 inhibitor (DPP-4i) except linagliptin could increase the SUA and other drugs including metformin, thiazolidinediones (TZDs), glucagon-like peptide-1 receptor agonists (GLP-1 RAs), linagliptin, sodium-glucose cotransporter 2 inhibitors (SGLT2i), and α-glucosidase inhibitors have a reduction effect on SUA. We explain the mechanisms of different antidiabetic drugs above on SUA and analyze them compared with actual data. For sulfonylureas, meglitinides, and amylin analogs, the underlying mechanism remains unclear. We think the usage of linagliptin and SGLT2i is the most potentially effective treatment of patients with T2DM and hyperuricemia currently. Our review is a comprehensive summary of the effects of antidiabetic drugs on SUA, which includes actual data, the mechanisms of SUA regulation, and the usage rate of drugs.

Enhanced Photocatalytic Degradation of Rhodamine B Dye by Iron-Doped Europium Oxide Nanoparticles.

As a wide-bandgap rare-earth oxide, Eu2O3 was often utilized as an auxiliary material of other photocatalysts because its photocatalytic performance was limited by the luminescence characteristics of Eu3+ and low light utilization. In this study, we improved the photocatalytic degradation performance of the Eu2O3 nanoparticles by doping with Fe cations. The Eu2O3 nanoparticles with different Fe-doping concentrations (1, 3, and 5%, noted as EF1.0, EF3.0, and EF5.0, respectively) were synthesized via chemical precipitation and calcination methods. It was found that doping could reduce Eu2O3's bandgap, which probably originated from the introduction of oxygen vacancies with lower energy levels than the conduction band of Eu2O3. Compared with the undoped Eu2O3 nanoparticles with a removal efficiency of 22% for degrading rhodamine B dye within 60 min, the photocatalytic degradation efficiencies of EF1.0, EF3.0, and EF5.0 were demonstrated to be improved to 42, 48, and 33%, respectively, and EF3.0's performance was the best. The enhanced photocatalytic performance of the doped samples was related to the oxygen vacancies acting as capture centers for electrons, such that the photogenerated electron-hole pairs were efficiently separated and the redox reactions on the surface of the nanoparticles were enhanced accordingly. Additionally, the enhanced light absorption and broadened spectral band further improved EF3.0's degradation efficiency.

Stimulus-Response Patterns: The Key to Giving Generalizability to Text-based Depression Detection Models.

Text content analysis for depression detection using machine learning techniques has become a prominent area of research. However, previous studies focused mainly on analyzing the textual content, neglecting the fundamental factors driving text generation. Consequently, existing models face the challenge of poor generalization to out-of-domain data as they struggle to capture the crucial features of depression. To address this, we propose a novel computational perspective of "stimulus-response patterns" that brings us closer to the essence of clinical diagnosis of depression. Adopting this computational perspective allows us to conceptually unify diverse datasets and generalize this perspective to common datasets in the field. We introduce the Stimulus-Response Patterns-aware Network (SRP-Net) as an exemplary approach within this computational perspective. To assess the performance of the SRP-Net, we constructed a multi-stimulus dataset and conducted experimental evaluations, demonstrating its exceptional cross-stimulus generalizability. Furthermore, we demonstrated the promising performance of SPR-Net in real medical scenarios and conducted an interpretability analysis of the stimulus-response patterns. Our research investigates the critical role of stimulus-response patterns in enhancing the generalizability of text-based depression detection models, which can potentially facilitate data-driven depression detection to approach the diagnostic accuracy of psychiatrists.