Glaucoma Characterization by Machine Learning of Tear Metabolic Fingerprinting

Tear metabolomics for the diagnosis of primary open-angle glaucoma

Primary Open-Angle Glaucoma (POAG) is the most prevalent glaucoma type, and the leading cause of irreversible visual impairment and blindness worldwide. Identification of early POAG biomarkers is of enormous value, as there is not an effective treatment for the glaucomatous optic nerve degeneration (OND). In this pilot study, a metabolomic analysis, by using proton (1H) nuclear magnetic resonance (NMR) spectroscopy was conducted in tears, in order to determine the changes of specific metabolites in the initial glaucoma eyes and to discover potential diagnostic biomarkers. A classification model, based on the metabolomic fingerprint in tears was generated as a non-invasive tool to support the preclinical and clinical POAG diagnosis. 1H NMR spectra were acquired from 30 tear samples corresponding to the POAG group (n = 11) and the control group (n = 19). Data were analysed by multivariate statistics (partial least squares-discriminant analysis: PLS-DA) to determine a model capable of differentiating between groups. The whole data set was split into calibration (65%)/validation (35%), to test the performance and the ability for glaucoma discrimination. The calculated PLS-DA model showed an area under the curve (AUC) of 1, as well as a sensitivity of 100% and a specificity of 83.3% to distinguish POAG group versus control group tear data. This model included 11 metabolites, potential biomarkers of the disease. When comparing the study groups, a decrease in the tear concentration of phenylalanine, phenylacetate, leucine, n-acetylated compounds, formic acid, and uridine, was found in the POAG group. Moreover, an increase in the tear concentration of taurine, glycine, urea, glucose, and unsaturated fatty acids was observed in the POAG group. These results highlight the potential of tear metabolomics by 1H NMR spectroscopy as a non-invasive approach to support early POAG diagnosis and in order to prevent visual loss.

Vacancy-Driven High-Performance Metabolic Assay for Diagnosis and Therapeutic Evaluation of Depression

Depression is one of the most common mental illnesses and is a well-known risk factor for suicide, characterized by low overall efficacy (<50%) and high relapse rate (40%). A rapid and objective approach for screening and prognosis of depression is highly desirable but still awaits further development. Herein, a high-performance metabolite-based assay to aid the diagnosis and therapeutic evaluation of depression by developing a vacancy-engineered cobalt oxide (Vo-Co3O4) assisted laser desorption/ionization mass spectrometer platform is presented. The easy-prepared nanoparticles with optimal vacancy achieve a considerable signal enhancement, characterized by favorable charge transfer and increased photothermal conversion. The optimized Vo-Co3O4 allows for a direct and robust record of plasma metabolic fingerprints (PMFs). Through machine learning of PMFs, high-performance depression diagnosis is achieved, with the areas under the curve (AUC) of 0.941-0.980 and an accuracy of over 92%. Furthermore, a simplified diagnostic panel for depression is established, with a desirable AUC value of 0.933. Finally, proline levels are quantified in a follow-up cohort of depressive patients, highlighting the potential of metabolite quantification in the therapeutic evaluation of depression. This work promotes the progression of advanced matrixes and brings insights into the management of depression.

Integrating Machine Learning in Metabolomics: A Path to Enhanced Diagnostics and Data Interpretation

Metabolomics, leveraging techniques like NMR and MS, is crucial for understanding biochemical processes in pathophysiological states. This field, however, faces challenges in metabolite sensitivity, data complexity, and omics data integration. Recent machine learning advancements have enhanced data analysis and disease classification in metabolomics. This study explores machine learning integration with metabolomics to improve metabolite identification, data efficiency, and diagnostic methods. Using deep learning and traditional machine learning, it presents advancements in metabolic data analysis, including novel algorithms for accurate peak identification, robust disease classification from metabolic profiles, and improved metabolite annotation. It also highlights multiomics integration, demonstrating machine learning's potential in elucidating biological phenomena and advancing disease diagnostics. This work contributes significantly to metabolomics by merging it with machine learning, offering innovative solutions to analytical challenges and setting new standards for omics data analysis.

Identification of a circulating three-miRNA panel for the diagnosis of primary open angle glaucoma

PURPOSE

Conventional diagnosis of primary open angle glaucoma (POAG) needs a combination of ophthalmic examinations. An efficient assay is urgently needed for a timely POAG diagnosis. We aim to explore differential expressions of circulating microRNAs (miRNA) and provide novel miRNA biomarkers for POAG diagnosis.

METHODS

A total of 180 POAG patients and 210 age-related cataract (ARC) patients were enrolled. We collected aqueous humor (AH) and plasma samples from the recruited patients. The expressions of candidate miRNAs were measured using quantitative real time polymerase chain reaction. The diagnostic ability of candidate miRNAs was analyzed by receiver operating characteristic curve.

RESULTS

The expressions of miR-21-5p and miR-29b-3p were downregulated significantly in AH and plasma of POAG and miR-24-3p expression was significantly increased in AH and plasma of POAG, comparing with those of ARC. A three-miRNA panel was constructed by a binary logistic regression. And the panel could differentiate between POAG and ARC with an area under the curve of 0.8867 (sensitivity = 78.0%, specificity = 83.3%) in aqueous humor and 0.7547 (sensitivity = 73.8%, specificity = 81.2%) in plasma. Next, we verified the three-miRNA panel working as a potential diagnostic biomarker stable and reliable. At last, we identified related function and regulation pathways in vitro.

CONCLUSIONS

In conclusion, we built and identified a circulating three-miRNA panel as a potential diagnostic biomarker for POAG. It may be developed into an efficient assay and help improve the POAG diagnosis in the future.

Identifying High Gleason Score Prostate Cancer by Prostate Fluid Metabolic Fingerprint-Based Multi-Modal Recognition

Prostate cancer (PCa) is the second most common cancer in males worldwide. The Gleason scoring system, which classifies the pathological growth pattern of cancer, is considered one of the most important prognostic factors for PCa. Compared to indolent PCa, PCa with high Gleason score (h-GS PCa, GS ≥ 8) has greater clinical significance due to its high aggressiveness and poor prognosis. It is crucial to establish a rapid, non-invasive diagnostic modality to decipher patients with h-GS PCa as early as possible. In this study, ferric nanoparticle-assisted laser desorption/ionization mass spectrometry (FeNPALDI-MS) to extract prostate fluid metabolic fingerprint (PSF-MF) is employed and combined with the clinical features of patients, such as prostate-specific antigen (PSA), to establish a multi-modal diagnosis assisted by machine learning. This approach yields an impressive area under the curve (AUC) of 0.87 to diagnose patients with h-GS, surpassing the results of single-modal diagnosis using only PSF-MF or PSA, respectively. Additionally, using various screening methods, six key metabolites that exhibit greater diagnostic efficacy (AUC = 0.96) are identified. These findings also provide insights into related metabolic pathways, which may provide valuable information for further elucidation of the pathological mechanisms underlying h-GS PCa.

Diagnosis of Esophageal Squamous Cell Carcinoma by High-Performance Serum Metabolic Fingerprints: A Retrospective Study

Esophageal squamous cell carcinoma (ESCC) is a highly prevalent and aggressive malignancy, and timely diagnosis of ESCC contributes to an increased cancer survival rate. However, current detection methods for ESCC mainly rely on endoscopic examination, limited by a relatively low participation rate. Herein, ferric-particle-enhanced laser desorption/ionization mass spectrometry (FPELDI MS) is utilized to record the serum metabolic fingerprints (SMFs) from a retrospective cohort (523 non-ESCC participants and 462 ESCC patients) to build diagnostic models toward ESCC. The PFELDI MS achieved high speed (≈30 s per sample), desirable reproducibility (coefficients of variation < 15%), and high throughput (985 samples with ≈124 200 data points for each spectrum). Desirable diagnostic performance with area-under-the-curves (AUCs) of 0.925-0.966 is obtained through machine learning of SMFs. Further, a metabolic biomarker panel is constructed, exhibiting superior diagnostic sensitivity (72.2-79.4%, p < 0.05) as compared with clinical protein biomarker tests (4.3-22.9%). Notably, the biomarker panel afforded an AUC of 0.844 (95% confidence interval [CI]: 0.806-0.880) toward early ESCC diagnosis. This work highlighted the potential of metabolic analysis for accurate screening and early detection of ESCC and offered insights into the metabolic characterization of diseases including but not limited to ESCC.

Designed Nanomaterials-Assisted Proteomics and Metabolomics Analysis for In Vitro Diagnosis

In vitro diagnosis (IVD) is pivotal in modern medicine, enabling early disease detection and treatment optimization. Omics technologies, particularly proteomics and metabolomics, offer profound insights into IVD. Despite its significance, omics analyses for IVD face challenges, including low analyte concentrations and the complexity of biological environments. In addition, the direct omics analysis by mass spectrometry (MS) is often hampered by issues like large sample volume requirements and poor ionization efficiency. Through manipulating their size, surface charge, and functionalization, as well as the nanoparticle-fluid incubation conditions, nanomaterials have emerged as a promising solution to extract biomolecules and enhance the desorption/ionization efficiency in MS detection. This review delves into the last five years of nanomaterial applications in omics, focusing on their role in the enrichment, separation, and ionization analysis of proteins and metabolites for IVD. It aims to provide a comprehensive update on nanomaterial design and application in omics, highlighting their potential to revolutionize IVD.

Artificial intelligence in glaucoma: opportunities, challenges, and future directions

Artificial intelligence (AI) has shown excellent diagnostic performance in detecting various complex problems related to many areas of healthcare including ophthalmology. AI diagnostic systems developed from fundus images have become state-of-the-art tools in diagnosing retinal conditions and glaucoma as well as other ocular diseases. However, designing and implementing AI models using large imaging data is challenging. In this study, we review different machine learning (ML) and deep learning (DL) techniques applied to multiple modalities of retinal data, such as fundus images and visual fields for glaucoma detection, progression assessment, staging and so on. We summarize findings and provide several taxonomies to help the reader understand the evolution of conventional and emerging AI models in glaucoma. We discuss opportunities and challenges facing AI application in glaucoma and highlight some key themes from the existing literature that may help to explore future studies. Our goal in this systematic review is to help readers and researchers to understand critical aspects of AI related to glaucoma as well as determine the necessary steps and requirements for the successful development of AI models in glaucoma.

Host-Guest Self-Assembled Interfacial Nanoarrays for Precise Metabolic Profiling

Accurate and rapid metabolic profiling of cerebrospinal fluid (CSF) is urgently needed but remains challenging for clinical diagnosis of central nervous system diseases and biomarker discovery. Matrix-assisted laser desorption ionization mass spectrometry (MALDI-MS) holds promise for metabolic analysis. Its low signal reproducibility, however, severely restricts acquisition of quantitative MS data in clinical practice. Herein, a multifunctional self-assembled AuNPs array (MSANA)-based LDI-MS platform for direct amino acids analysis and metabolic profiling in patient CSF samples is developed. MSANA featuring a highly ordered and closely packed two-dimensional nanostructure permits capture and direct analysis of aromatic amino acids by LDI-MS with high selectivity and micromolar sensitivity. Meanwhile, the MSANA-based LDI-MS platform exhibits excellent reproducibility (RSD < 10%), largely outperforming the direct matrix spotting approach widely used now (RSD < 44%). The platform is successfully used in metabolic profiling of CSF (1 µL) within minutes for discrimination of medulloblastoma patients from non-tumor controls. Taken together, the MSANA-based LDI-MS platform shows potential clinical values toward large-scale metabolic diagnostics and pathogenic mechanism study.

Comprehensive Metabolic Fingerprints Characterize Neuromyelitis Optica Spectrum Disorder by Nanoparticle-Enhanced Laser Desorption/Ionization Mass Spectrometry

Timely screening of neuromyelitis optica spectrum disorder (NMOSD) and differential diagnosis from myelin oligodendrocyte glycoprotein associated disorder (MOGAD) are the keys to improving the quality of life of patients. Metabolic disturbance occurs with the development of NMOSD. Still, advanced tools are required to probe the metabolic phenotype of NMOSD. Here, we developed a fast nanoparticle-enhanced laser desorption/ionization mass spectrometry assay for multiplexing metabolic fingerprints (MFs) from trace plasma and cerebrospinal fluid (CSF) samples in 30 s. Machine learning of the plasma MFs achieved the timely screening of NMOSD from healthy donors with an area under receiver operator characteristic curve (AUROC) of 0.998, and it comprehensively revealed the dysregulated neurotransmitter and energy metabolisms. Combining comprehensive MFs from both plasma and CSF, we constructed an integrated panel for differential diagnosis of NMOSD versus MOGAD with an AUROC of 0.923. This approach demonstrated performance superior to that of human experts in classifying two diseases, especially in antibody assay-limited regions. Together, this approach provides an advanced nanomaterial-based tool for identifying vulnerable populations below the antibody threshold of aquaporin-4 positivity.

Hollow multishelled heterostructures with enhanced performance for laser desorption/ionization mass spectrometry based metabolic diagnosis

High-performance metabolic diagnosis-based laser desorption/ionization mass spectrometry (LDI-MS) improves the precision diagnosis of diseases and subsequent treatment. Inorganic matrices are promising for the detection of metabolites by LDI-MS, while the structure and component impacts of the matrices on the LDI process are still under investigation. Here, we designed a multiple-shelled ZnMn2O4/(Co, Mn)(Co, Mn)2O4 (ZMO/CMO) as the matrix from calcined MOF-on-MOF for detecting metabolites in LDI-MS and clarified the synergistic impacts of multiple-shells and the heterostructure on LDI efficiency. The ZMO/CMO heterostructure allowed 3-5 fold signal enhancement compared with ZMO and CMO with the same morphology. Furthermore, the ZMO/CMO heterostructure with a triple-shelled hollow structure displayed a 3-fold signal enhancement compared to its nanoparticle counterpart. Taken together, the triple-shelled hollow ZMO/CMO exhibits 102-fold signal enhancement compared to the commercial matrix products (e.g., DHB and DHAP), allowing for sensitive metabolic profiling in bio-detection. We directly extracted metabolic patterns by the optimized triple-shelled hollow ZMO/CMO particle-assisted LDI-MS within 1 s using 100 nL of serum and used machine learning as the readout to distinguish hepatocellular carcinoma from healthy controls with the area under the curve value of 0.984. Our approach guides us in matrix design for LDI-MS metabolic analysis and drives the development of a nanomaterial-based LDI-MS platform toward precision diagnosis.

Efficient Metabolic Fingerprinting of Follicular Fluid Encodes Ovarian Reserve and Fertility

Ovarian reserve (OR) and fertility are critical in women's healthcare. Clinical methods for encoding OR and fertility rely on the combination of tests, which cannot serve as a multi-functional platform with limited information from specific biofluids. Herein, metabolic fingerprinting of follicular fluid (MFFF) from follicles is performed, using particle-assisted laser desorption/ionization mass spectrometry (PALDI-MS) to encode OR and fertility. PALDI-MS allows efficient MFFF, showing fast speed (≈30 s), high sensitivity (≈60 fmol), and desirable reproducibility (coefficients of variation <15%). Further, machine learning of MFFF is applied to diagnose diminished OR (area under the curve of 0.929) and identify high-quality oocytes/embryos (p < 0.05) by a single PALDI-MS test. Meanwhile, metabolic biomarkers from MFFF are identified, which also determine oocyte/embryo quality (p < 0.05) from the sampling follicles toward fertility prediction in clinics. This approach offers a powerful platform in women's healthcare, not limited to OR and fertility.

Non-viral gene therapy using RNA interference with PDGFR-α mediated epithelial-mesenchymal transformation for proliferative vitreoretinopathy

Fibrotic eye diseases, a series of severe oculopathy, that will destroy normal ocular refractive media and imaging structures. It is characterized by the transformation of the epithelial cells into mesenchyme cells. Proliferative vitreoretinopathy (PVR) is one of these representative diseases. In this investigation, polyethylene glycol grafted branched Polyethyleneimine (PEI-g-PEG) was used as a non-viral gene vector in gene therapy of PVR to achieve anti-fibroblastic effects in vitro and in vivo by interfering with platelet-derived growth factor alpha receptor (PDGFR-α) in the epithelial-mesenchymal transition (EMT) of retinal pigment epithelium (RPE) cells. The plasmid was wrapped by electrostatic conjugation. Physical characterization of the complexes indicated that the gene complexes were successfully prepared. In vitro, cellular experiments showed excellent biocompatibility of PEI-g-PEG, efficient cellular uptake of the gene complexes, and successful expression of the corresponding fragments. Through gene silencing technique, PEI-g-PEG/PDGFR-α shRNA successfully inhibited the process of EMT in vitro. Furthermore, in vivo animal experiments suggested that this method could effectively inhibit the progression of fibroproliferative membranes of PVR. Herein, a feasible and promising clinical idea was provided for developing non-viral gene vectors and preventing fibroblastic eye diseases by RNA interference (RNAi) technology.

Diagnosis of Parkinson's Disease via the Metabolic Fingerprint in Saliva by Deep Learning

Parkinson's disease (PD) is the second cause of the neurodegenerative disorder, affecting over 6 million people worldwide. The World Health Organization estimated that population aging will cause global PD prevalence to double in the coming 30 years. Optimal management of PD shall start at diagnosis and requires both a timely and accurate method. Conventional PD diagnosis needs observations and clinical signs assessment, which are time-consuming and low-throughput. A lack of body fluid diagnostic biomarkers for PD has been a significant challenge, although substantial progress has been made in genetic and imaging marker development. Herein, a platform that noninvasively collects saliva metabolic fingerprinting (SMF) by nanoparticle-enhanced laser desorption-ionization mass spectrometry with high-reproducibility and high-throughput, using ultra-small sample volume (down to 10 nL), is developed. Further, excellent diagnostic performance is achieved with an area-under-the-curve of 0.8496 (95% CI: 0.7393-0.8625) by constructing deep learning model from 312 participants. In conclusion, an alternative solution is provided for the molecular diagnostics of PD with SMF and metabolic biomarker screening for therapeutic intervention.

Tear nanoDSF Denaturation Profile Is Predictive of Glaucoma

Primary open-angle glaucoma (POAG) is a frequent blindness-causing neurodegenerative disorder characterized by optic nerve and retinal ganglion cell damage most commonly due to a chronic increase in intraocular pressure. The preservation of visual function in patients critically depends on the timeliness of detection and treatment of the disease, which is challenging due to its asymptomatic course at early stages and lack of objective diagnostic approaches. Recent studies revealed that the pathophysiology of glaucoma includes complex metabolomic and proteomic alterations in the eye liquids, including tear fluid (TF). Although TF can be collected by a non-invasive procedure and may serve as a source of the appropriate biomarkers, its multi-omics analysis is technically sophisticated and unsuitable for clinical practice. In this study, we tested a novel concept of glaucoma diagnostics based on the rapid high-performance analysis of the TF proteome by differential scanning fluorimetry (nanoDSF). An examination of the thermal denaturation of TF proteins in a cohort of 311 ophthalmic patients revealed typical profiles, with two peaks exhibiting characteristic shifts in POAG. Clustering of the profiles according to peaks maxima allowed us to identify glaucoma in 70% of cases, while the employment of artificial intelligence (machine learning) algorithms reduced the amount of false-positive diagnoses to 13.5%. The POAG-associated alterations in the core TF proteins included an increase in the concentration of serum albumin, accompanied by a decrease in lysozyme C, lipocalin-1, and lactotransferrin contents. Unexpectedly, these changes were not the only factor affecting the observed denaturation profile shifts, which considerably depended on the presence of low-molecular-weight ligands of tear proteins, such as fatty acids and iron. Overall, we recognized the TF denaturation profile as a novel biomarker of glaucoma, which integrates proteomic, lipidomic, and metallomic alterations in tears, and monitoring of which could be adapted for rapid non-invasive screening of the disease in a clinical setting.

A novel biosensing platform for detection of glaucoma biomarker GDF15 via an integrated BLI-ELASA strategy

Glaucoma is a leading cause of irreversible blindness worldwide. Early discovery and prioritized intervention significantly impact its prognosis. Precise monitoring of the biomarker GDF15 contributes towards effective diagnosis and assessment of glaucoma. In this study, we demonstrate that GDF15 monitoring can also aid screening for glaucoma risk and early diagnosis. We obtained an aptamer (APT2TM) with high affinity, high specificity, and high stability for binding to both human-derived and rat-derived GDF15. Simulation results showed that the binding capabilities of APT2TM are mainly affected by the interplay between van der Waals forces and polar solvation energy, and that salt bridges and hydrogen bonds play critical roles. We then integrated an enzyme-linked aptamer sandwich assay (ELASA) into a biolayer interferometry (BLI) system to develop an automated, high-throughput, real-time monitoring BLI-ELASA biosensing platform. This platform exhibited a wide linear detection window (10-810 pg/mL range) and high sensitivity for GDF15 (detection limit of 5-6 pg/mL). Moreover, we confirmed its excellent performance when applied to GDF15 quantification in real samples from glaucomatous rats and clinical patients. We believe that this technology represents a robust, convenient, and cost-effective approach for risk screening, early diagnosis, and animal modeling evaluation of glaucoma in the near future.

Diagnosis of Unruptured Intracranial Aneurysm by High-Performance Serum Metabolic Fingerprints

Unruptured intracranial aneurysm (UIA) is a high-risk cerebrovascular saccular dilatation, the effective medical management of which depends on high-performance diagnosis. However, most UIAs are diagnosed incidentally during neurovascular imaging modalities, which are time-consuming and harmful (e.g., radiation). Serum metabolic fingerprints is a promising alternative for early diagnosis of UIA. Here, nanoparticle enhanced laser desorption/ionization mass spectrometry is applied to obtain high-performance UIA-specific serum metabolic fingerprints. Diagnostic performance with an area-under-the-curve (AUC) of 0.842 (95% confidence interval (CI): 0.783-0.891) is achieved by the constructed machine learning (ML) model, including ML algorithm selection and feature selection. Lactate, glutamine, homoarginine, and 3-methylglutaconic acid are identified as the metabolic biomarker panel, which showed satisfactory diagnosis (AUC of 0.812, 95% CI: 0.727-0.897) and effective growth risk assessment (p<0.05, two-tailed t-test) of UIAs. This work aims to promote the diagnostics of UIAs and metabolic biomarker screening for medical management.

Deep Learning of Dual Plasma Fingerprints for High-Performance Infection Classification

Infection classification is the key for choosing the proper treatment plans. Early determination of the causative agents is critical for disease control. Host responses analysis can detect variform and sensitive host inflammatory responses to ascertain the presence and type of the infection. However, traditional host-derived inflammatory indicators are insufficient for clinical infection classification. Fingerprints-based omic analysis has attracted increasing attention globally for analyzing the complex host systemic immune response. A single type of fingerprints is not applicable for infection classification (area under curve (AUC) of 0.550-0.617). Herein, an infection classification platform based on deep learning of dual plasma fingerprints (DPFs-DL) is developed. The DPFs with high reproducibility (coefficient of variation <15%) are obtained at low sample consumption (550 nL native plasma) using inorganic nanoparticle and organic matrix assisted laser desorption/ionization mass spectrometry. A classifier (DPFs-DL) for viral versus bacterial infection discrimination (AUC of 0.775) and coronavirus disease 2019 (COVID-2019) diagnosis (AUC of 0.917) is also built. Furthermore, a metabolic biomarker panel of two differentially regulated metabolites, which may serve as potential biomarkers for COVID-19 management (AUC of 0.677-0.883), is constructed. This study will contribute to the development of precision clinical care for infectious diseases.

Clinical Tear Fluid Proteomics—A Novel Tool in Glaucoma Research

Tear fluid forms the outermost layer of the ocular surface and its characteristics and composition have been connected to various ocular surface diseases. As tear proteomics enables the non-invasive investigation of protein levels in the tear fluid, it has become an increasingly popular approach in ocular surface and systemic disease studies. Glaucoma, which is a set of multifactorial diseases affecting mainly the optic nerve and retinal ganglion cells, has also been studied using tear proteomics. In this condition, the complete set of pathophysiological changes occurring in the eye is not yet fully understood, and biomarkers for early diagnosis and accurate treatment selection are needed. More in-depth analyses of glaucoma tear proteomics have started to emerge only more recently with the implementation of LC-MS/MS and other modern technologies. The aim of this review was to examine the published data of the tear protein changes occurring during glaucoma, its topical treatment, and surgical interventions.