Tear fluid proteomics multimarkers for diabetic retinopathy screening

Applications of artificial intelligence and bioinformatics methodologies in the analysis of ocular biofluid markers: a scoping review

PURPOSE

This scoping review summarizes the applications of artificial intelligence (AI) and bioinformatics methodologies in analysis of ocular biofluid markers. The secondary objective was to explore supervised and unsupervised AI techniques and their predictive accuracies. We also evaluate the integration of bioinformatics with AI tools.

METHODS

This scoping review was conducted across five electronic databases including EMBASE, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics were included.

RESULTS

A total of 10,262 articles were retrieved from all databases and 177 studies met the inclusion criteria. The most commonly studied ocular diseases were diabetic eye diseases, with 50 papers (28%), while glaucoma was explored in 25 studies (14%), age-related macular degeneration in 20 (11%), dry eye disease in 10 (6%), and uveitis in 9 (5%). Supervised learning was used in 91 papers (51%), unsupervised AI in 83 (46%), and bioinformatics in 85 (48%). Ninety-eight papers (55%) used more than one class of AI (e.g. > 1 of supervised, unsupervised, bioinformatics, or statistical techniques), while 79 (45%) used only one. Supervised learning techniques were often used to predict disease status or prognosis, and demonstrated strong accuracy. Unsupervised AI algorithms were used to bolster the accuracy of other algorithms, identify molecularly distinct subgroups, or cluster cases into distinct subgroups that are useful for prediction of the disease course. Finally, bioinformatic tools were used to translate complex biomarker profiles or findings into interpretable data.

CONCLUSION

AI analysis of biofluid markers displayed diagnostic accuracy, provided insight into mechanisms of molecular etiologies, and had the ability to provide individualized targeted therapeutic treatment for patients. Given the progression of AI towards use in both research and the clinic, ophthalmologists should be broadly aware of the commonly used algorithms and their applications. Future research may be aimed at validating algorithms and integrating them in clinical practice.

In vitro Assay to Examine the Function of Tears on Corneal Epithelial Cells

Tears contain numerous secreted factors, enzymes, and proteins that help in maintaining the homeostatic condition of the eye and also protect it from the external environment. However, alterations to these enzymes and/or proteins during pathologies such as mechanical injury and viral or fungal infections can disrupt the normal ocular homeostasis, further contributing to disease development. Several tear film components have a significant role in curbing disease progression and promoting corneal regeneration. Additionally, several factors related to disease progression are secreted into the tear film, thereby serving as a valuable reservoir of biomarkers. Tears are readily available and can be collected via non-invasive techniques or simply from contact lenses. Tears can thus serve as a valuable and easy source for studying disease-specific biomarkers. Significant advancements have been made in recent years in the field of tear film proteomics, lipidomics, and transcriptomics to allow a better understanding of how tears can be utilized to gain insight into the etiology of diseases. These advancements have enabled us to study the pathophysiology of various disease states using tear samples. However, the mechanisms by which tears help to maintain corneal homeostasis and how they are able to form the first line of defense against pathogens remain poorly understood and warrant detailed in vitro studies. Herein, we have developed an in vitro assay to characterize the functional importance of patient isolated tears and their components on corneal epithelial cells. This novel approach closely mimics real physiological conditions and could help the researchers gain insight into the underlying mechanisms of ocular pathologies and develop new treatments. Key features • This method provides a new technique for analyzing the effect of tear components on human corneal epithelial cells. • The components of the tears that are altered in response to diseases can be used as a biomarker for detecting ocular complications. • This procedure can be further employed as an in vitro model for assessing the efficacy of drugs and discover potential therapeutic interventions.

Exploring various novel diagnostic and therapeutic approaches in treating diabetic retinopathy

Diabetic retinopathy is regarded as a common manifestation of diabetes mellitus, being a prominent cause of visual impairment and blindness. This microvascular complication is marked by the appearance of microaneurysms, elevated vascular permeability, capillary blockage, and proliferation of neovasculature. The etiology behind retinopathy is ambiguous and the efficacy of current treatment strategies is minimal. Early diagnosis of this complication using a biomarker with high sensitivity and specificity is very essential for providing better therapeutic strategies. The current available therapeutic options are limited with various adverse effects. Laser treatment is not beneficial in all the situations, economic constraints being the major challenge. Surgical interventions are employed when pharmacotherapy and laser treatment fail. New pharmacological treatments are becoming a necessity for treating the condition. This review highlights the use of various diagnostic tools, emerging biomarkers for early detection of diabetic retinopathy, pathological mechanisms associated with the disease, current therapeutic approaches used and future strategies for more enhanced treatment options and more potent pharmacological actions.

Tear proteomic analysis of young glasses, orthokeratology, and soft contact lens wearers

Contact lens-related ocular surface complications occur more often in teenagers and young adults. The purpose of this study was to determine changes in tear proteome of young patients wearing glasses (GL), orthokeratology lenses (OK), and soft contact lenses (SCL). Twenty-two young subjects (10-26 years of age) who were established GL, OK, and SCL wearers were recruited. Proteomic data were collected using a data-independent acquisition-parallel accumulation serial fragmentation workflow. In total, 3406 protein groups were identified, the highest number of proteins identified in Schirmer strip tears to date. Eight protein groups showed higher abundance, and 11 protein groups showed lower abundance in the SCL group compared to the OK group. In addition, the abundance of 82 proteins significantly differed in children compared to young adult GL wearers, among which 67 proteins were higher, and 15 proteins were lower in children. These 82 proteins were involved in inflammation, immune, and glycoprotein metabolic biological processes. In summary, this work identified over 3000 proteins in Schirmer Strip tears. The results indicated that tear proteomes were altered by orthokeratology and soft contact wear and age, which warrants further larger-scale study on the ocular surface responses of teenagers and young adults separately to contact lens wear. SIGNIFICANCE: In this work, we examined the tear proteomes of young patients wearing glasses, orthokeratology lenses, and soft contact lenses using a data-independent acquisition-parallel accumulation serial fragmentation (diaPASEF) workflow and identified 3406 protein groups in Schirmer strip tears. Nineteen protein groups showed significant abundance changes between orthokeratology and soft contact lens wearers. Moreover, eighty-two protein groups significantly differed in abundance in children and young adult glasses wearers. As a pilot study, this work provides a deep coverage of tear proteome and suggests the need to investigate ocular responses to contact lens wear separately for children and young adults.

Evaluating the clinical utility of measuring levels of factor H and the related proteins

After years of disappointing clinical results, the tide has finally changed and complement targeted-therapies have become a validated and accepted treatment option for several diseases. These accomplishments have revitalized the field and brought renewed attention to the prospects that complement therapeutics can offer. Streamlining diagnostics and therapeutics is imperative in this new era of clinical use of complement therapeutics. However, the incredible success in therapeutics has not been accompanied by the development of novel standardized tools for complement testing. Complement biomarkers can assist in the risk assessment and diagnosis of diseases as well as the prediction of disease progression and treatment response. Recently, a group of complement proteins has been suggested to be highly relevant in various complement-associated disorders, namely the human factor H (FH) protein family. This family of closely related proteins consists of FH, FH-like protein 1, and five factor H-related proteins, and they have been linked to eye, kidney, infectious, vascular, and autoimmune diseases as well as cancer. The goal of this review is to provide a comprehensive overview of the available data on circulating levels of FH and its related proteins in different pathologies. In addition, we examined the current literature to determine the clinical utility of measuring levels of the FH protein family in health and disease. Finally, we discuss future steps that are needed to make their clinical translation a reality.

Mass spectrometry-based tear proteomics for noninvasive biomarker discovery

The lacrimal film has attracted increasing interest in the last decades as a potential source of biomarkers of physiopathological states, due to its accessibility, moderate complexity, and responsiveness to ocular and systemic diseases. High-performance liquid chromatography-mass spectrometry (LC-MS) has led to effective approaches to tear proteomics, despite the intrinsic limitations in sample amounts. This review focuses on the recent progress in strategy and technology, with an emphasis on the potential for personalized medicine. After an introduction on lacrimal-film composition, examples of applications to biomarker discovery are discussed, comparing approaches based on pooled-sample and single-tear analysis. Then, the most critical steps of the experimental pipeline, that is, tear collection, sample fractionation, and LC-MS implementation, are discussed with reference to proteome-coverage optimization. Advantages and challenges of the alternative procedures are highlighted. Despite the still limited number of studies, tear quantitative proteomics, including single-tear investigation, could offer unique contributions to the identification of low-invasiveness, sustained-accessibility biomarkers, and to the development of personalized approaches to therapy and diagnosis.

Putative Biomarkers in Tears for Diabetic Retinopathy Diagnosis

Purpose

Tear fluid biomarkers may offer a non-invasive strategy for detecting diabetic patients with increased risk of developing diabetic retinopathy (DR) or increased disease progression, thus helping both improving diagnostic accuracy and understanding the pathophysiology of the disease. Here, we assessed the tear fluid of nondiabetic individuals, diabetic patients with no DR, and diabetic patients with nonproliferative DR (NPDR) or with proliferative DR (PDR) to find putative biomarkers for the diagnosis and staging of DR.

Methods

Tear fluid samples were collected using Schirmer test strips from a cohort with 12 controls and 54 Type 2 Diabetes (T2D) patients, and then analyzed using mass spectrometry (MS)-based shotgun proteomics and bead-based multiplex assay. Tear fluid-derived small extracellular vesicles (EVs) were analyzed by transmission electron microscopy, Western Blotting, and nano tracking.

Results

Proteomics analysis revealed that among the 682 reliably quantified proteins in tear fluid, 42 and 26 were differentially expressed in NPDR and PDR, respectively, comparing to the control group. Data are available via ProteomeXchange with identifier PXD033101. By multicomparison analyses, we also found significant changes in 32 proteins. Gene ontology (GO) annotations showed that most of these proteins are associated with oxidative stress and small EVs. Indeed, we also found that tear fluid is particularly enriched in small EVs. T2D patients with NPDR have higher IL-2/-5/-18, TNF, MMP-2/-3/-9 concentrations than the controls. In the PDR group, IL-5/-18 and MMP-3/-9 concentrations were significantly higher, whereas IL-13 was lower, compared to the controls.

Conclusions

Overall, the results show alterations in tear fluid proteins profile in diabetic patients with retinopathy. Promising candidate biomarkers identified need to be validated in a large sample cohort.

Lab-on-a-chip technologies for minimally invasive molecular sensing of diabetic retinopathy

Diabetic retinopathy (DR) is the most common diabetic eye disease and the worldwide leading cause of vision loss in working-age adults. It progresses from mild to severe non-proliferative or proliferative DR based on several pathological features including the magnitude of blood-retinal barrier breakdown and neovascularization. Available pharmacological and retinal laser photocoagulation interventions are mostly applied in the advanced stages of DR and are inefficient in halting disease progression in a significantly high percentage of patients. Yet, recent evidence has shown that some therapies could potentially limit DR progression if applied at early stages, highlighting the importance of early disease diagnostics. In the past few decades, different imaging modalities have proved their utility for examining retinal and optic nerve changes in patients with retinal diseases. However, imaging based-methodologies solely rely on morphological examination of the retinal vascularization and are not suitable for recurrent and personalized patient evaluation. This raises the need for new technologies to enable accurate and early diagnosis of DR. In this review, we critically discuss the potential clinical benefit of minimally-invasive molecular biomarker identification and profiling of diabetic patients who are at risk of developing DR. We provide a comparative overview of conventional and recently developed lab-on-a-chip technologies for quantitative assessment of potential DR molecular biomarkers and discuss their advantages, current limitations and challenges for future practical implementation and continuous patient monitoring at the point-of-care.

Colorimetric and Electrochemical Screening for Early Detection of Diabetes Mellitus and Diabetic Retinopathy-Application of Sensor Arrays and Machine Learning

In this review, a selection of works on the sensing of biomarkers related to diabetes mellitus (DM) and diabetic retinopathy (DR) are presented, with the scope of helping and encouraging researchers to design sensor-array machine-learning (ML)-supported devices for robust, fast, and cost-effective early detection of these devastating diseases. First, we highlight the social relevance of developing systematic screening programs for such diseases and how sensor-arrays and ML approaches could ease their early diagnosis. Then, we present diverse works related to the colorimetric and electrochemical sensing of biomarkers related to DM and DR with non-invasive sampling (e.g., urine, saliva, breath, tears, and sweat samples), with a special mention to some already-existing sensor arrays and ML approaches. We finally highlight the great potential of the latter approaches for the fast and reliable early diagnosis of DM and DR.

A Meta-Analysis of Wearable Contact Lenses for Medical Applications: Role of Electrospun Fiber for Drug Delivery

In recent years, wearable contact lenses for medical applications have attracted significant attention, as they enable continuous real-time recording of physiological information via active and noninvasive measurements. These devices play a vital role in continuous monitoring of intraocular pressure (IOP), noninvasive glucose monitoring in diabetes patients, drug delivery for the treatment of ocular illnesses, and colorblindness treatment. In specific, this class of medical devices is rapidly advancing in the area of drug loading and ocular drug release through incorporation of electrospun fibers. The electrospun fiber matrices offer a high surface area, controlled morphology, wettability, biocompatibility, and tunable porosity, which are highly desirable for controlled drug release. This article provides an overview of the advances of contact lens devices in medical applications with a focus on four main applications of these soft wearable devices: (i) IOP measurement and monitoring, (ii) glucose detection, (iii) ocular drug delivery, and (iv) colorblindness treatment. For each category and application, significant challenges and shortcomings of the current devices are thoroughly discussed, and new areas of opportunity are suggested. We also emphasize the role of electrospun fibers, their fabrication methods along with their characteristics, and the integration of diverse fiber types within the structure of the wearable contact lenses for efficient drug loading, in addition to controlled and sustained drug release. This review article also presents relevant statistics on the evolution of medical contact lenses over the last two decades, their strengths, and the future avenues for making the essential transition from clinical trials to real-world applications.

Metabolomics of various samples advancing biomarker discovery and pathogenesis elucidation for diabetic retinopathy

Diabetic retinopathy (DR) is a universal microvascular complication of diabetes mellitus (DM), which is the main reason for global sight damage/loss in middle-aged and/or older people. Current clinical analyses, like hemoglobin A1c, possess some importance as prognostic indicators for DR severity, but no effective circulating biomarkers are used for DR in the clinic currently, and studies on the latent pathophysiology remain lacking. Recent developments in omics, especially metabolomics, continue to disclose novel potential biomarkers in several fields, including but not limited to DR. Therefore, based on the overview of metabolomics, we reviewed progress in analytical technology of metabolomics, the prominent roles and the current status of biomarkers in DR, and the update of potential biomarkers in various DR-related samples via metabolomics, including tear as well as vitreous humor, aqueous humor, retina, plasma, serum, cerebrospinal fluid, urine, and feces. In this review, we underscored the in-depth analysis and elucidation of the common biomarkers in different biological samples based on integrated results, namely, alanine, lactate, and glutamine. Alanine may participate in and regulate glucose metabolism through stimulating N-methyl-D-aspartate receptors and subsequently suppressing insulin secretion, which is the potential pathogenesis of DR. Abnormal lactate could cause extensive oxidative stress and neuroinflammation, eventually leading to retinal hypoxia and metabolic dysfunction; on the other hand, high-level lactate may damage the structure and function of the retinal endothelial cell barrier via the G protein-coupled receptor 81. Abnormal glutamine indicates a disturbance of glutamate recycling, which may affect the activation of Müller cells and proliferation via the PPP1CA-YAP-GS-Gln-mTORC1 pathway.

Comparison of VEGF level in tears post phacoemulsification between non-proliferative diabetic retinopathy and non-diabetic patients

Background

Progression of diabetic retinopathy post cataract surgery is related to the increased level of vascular endothelial growth factor (VEGF) in ocular fluid post operatively. The aim of this study was to compare the VEGF level in tears post phacoemulsification between non-proliferative diabetic retinopathy (NPDR) and non-diabetic patients.

Methods

This was a prospective cohort study and was conducted from June 2017 to May 2019. Patients with underlying NPDR who were planned for phacoemulsification were recruited in this study. Non-diabetic patients who were planned for phacoemulsification were included as control group. Tears samples were collected using Schirmer strip two weeks prior to operation, at day (D) 7 and D30 post phacoemulsification. Tears samples were analyzed for VEGF level.

Results

A total of 65 patients were recruited in this study (NPDR: 32 and control: 33). There was significant increase of VEGF levels in tears from pre operation to D7 post phacoemulsification in NPDR (p < 0.001) and control (p < 0.001). There was also significant reduction of tear VEGF level from D7 to D30 post phacoemulsification in both groups (p < 0.001 in NPDR and p = 0.027 in control). The tear VEGF level was significantly higher in NPDR group compared to control at D7 post phacoemulsification (149.4 SD 55.2 pg/mL vs 109.7 SD 48.7 pg/mL, p = 0.003).

Conclusion

VEGF level in tears showed significant elevation post early cataract surgery in NPDR compared to non-diabetic patient. Therefore, tears VEGF level may provide as a non-invasive method to predict progression of diabetic retinopathy post operation among diabetic patients.

Bio-chemical markers of chronic, non-infectious disease in the human tear film

The tear film is a thin, moist layer covering the ocular surface and is laden with proteins, peptides, lipids, mucins, electrolytes and cellular debris which function to maintain the healthy status of the ocular surface. In many cases of ocular or systemic disease, the integrity of this layer is changed and/or the balance of its constituents is disturbed. Since tears are easy and quick to collect and can be stored for long periods, they have the potential to be a valuable source of information relevant to many disease states. The purpose of this review is to collate information on the known biomarkers of systemic disease that have been identified in tears. The range of conditions covered includes diabetes mellitus, diabetic retinopathy, diabetic peripheral neuropathy, multiple sclerosis, Parkinson's disease, Alzheimer's disease, migraine, systemic sclerosis, cystic fibrosis, thyroid disorders and cancer.

Machine Learning Techniques for Personalised Medicine Approaches in Immune-Mediated Chronic Inflammatory Diseases: Applications and Challenges

In the past decade, the emergence of machine learning (ML) applications has led to significant advances towards implementation of personalised medicine approaches for improved health care, due to the exceptional performance of ML models when utilising complex big data. The immune-mediated chronic inflammatory diseases are a group of complex disorders associated with dysregulated immune responses resulting in inflammation affecting various organs and systems. The heterogeneous nature of these diseases poses great challenges for tailored disease management and addressing unmet patient needs. Applying novel ML techniques to the clinical study of chronic inflammatory diseases shows promising results and great potential for precision medicine applications in clinical research and practice. In this review, we highlight the clinical applications of various ML techniques for prediction, diagnosis and prognosis of autoimmune rheumatic diseases, inflammatory bowel disease, autoimmune chronic kidney disease, and multiple sclerosis, as well as ML applications for patient stratification and treatment selection. We highlight the use of ML in drug development, including target identification, validation and drug repurposing, as well as challenges related to data interpretation and validation, and ethical concerns related to the use of artificial intelligence in clinical research.

Integrating SWATH-MS proteomics and transcriptome analysis to preliminarily identify three DEGs as biomarkers for proliferative diabetic retinopathy

PURPOSE

We intended to preliminarily find differentially expressed proteins that play crucial roles in proliferative diabetic retinopathy (PDR), and lay the foundation for subsequent further research on the mechanism.

EXPERIMENTAL DESIGN

Here, we developed a new strategy integrated the sequential windowed acquisition of all theoretical fragment ion (SWATH) mass spectra (MS) with multi-dataset joint analysis to screen for the PDR plasma biomarker. The annotation of the given gene list was performed with ClueGO function analysis. Additionally, the protein-protein interaction relationship was also revealed by the STRING database.

RESULTS

In SWATH-MS assays, we identified 23 upregulated and 13 downregulated proteins in PDR plasma. In the mRNA database analysis, 375 genes were identified as differentially expressed genes in GSE102485. Only three genes (FCGR3A, DPEP2, and ADGRF5) were characterized as upregulated in both the dataset and the SWATH-MS list. The area under the ROC curve (AUC) of FCGR3A, DPEP2, and ADGRF5 in distinguishing PDR from others was 0.739, 0.770, and 0.739.

CONCLUSIONS AND CLINICAL RELEVANCE

We provide a novel strategy for biomarker screening and identified plasma FCGR3A, DPEP2, and ADGRF5 as potential biomarkers for patients with PDR. Identifying the key molecules of the disease is essential for the development of new therapeutic molecules and new uses of existing drugs.

Reduced Level of Tear Antimicrobial and Immunomodulatory Proteins as a Possible Reason for Higher Ocular Infections in Diabetic Patients

(1) Background: Diabetes mellitus is one of the most common metabolic disorders and a risk factor for bacterial ocular infections. Our aim was to examine the antibacterial activity of tears from patients with diabetes mellitus with and without diabetic retinopathy and to link this activity to the level of tear proteins. (2) Methods: Non-stimulated basal tears were collected from 39 eyes of 35 subjects. The antibacterial activity of tear pools was tested against pathogenic Staphylococcus aureus ATCC 29213, Escherichia coli ATCC 26922 and Pseudomonas aeruginosa ATCC 27853 strains. The levels of 10 antimicrobial and immunomodulatory proteins were analyzed in the individual tear samples of the studied groups by SRM-based targeted mass spectrometry analysis. (3) Results: Disease stage-specific antimicrobial effect was observed in case of Staphylococcus aureus ATCC 29213 strain, and a non-disease specific inhibitory effect was observed in case of Pseudomonas aeruginosa ATCC 27853 strain. Changes in the levels of the studied antimicrobial and immunomodulatory proteins in the tears of the studied groups were also observed. (4) Conclusions: The higher ocular infection rate observed in diabetic patients may be the consequence of the decreased antimicrobial activity of tears possibly caused by the changes in the levels of antimicrobial and immunomodulatory proteins.

The acute phase response protein SERPINA3 is increased in tear fluid from the unaffected eyes of patients with unilateral acute anterior uveitis

BACKGROUND

To identify candidate tear fluid biomarkers in patients with unilateral acute anterior uveitis (AAU) that can aid in the differentiation between these patients and patients with bacterial keratitis or healthy controls.

METHODS

Thirteen patients (40.1 ± 16.2 years of age) with unilateral AAU, seven patients with unilateral bacterial keratitis (40.2 ± 15.3 years of age), and 14 healthy subjects (41.1 ± 11.6 years of age) were included. The tear proteome of affected eyes was compared with that of the unaffected eye or healthy controls. Proteins were identified by liquid chromatography tandem mass spectrometry and enzyme-linked immunosorbent assay.

RESULTS

Relative protein ratios were detected and calculated for 272 unique proteins. Compared with healthy controls and the unaffected eye, the top upregulated proteins in AAU eyes were submaxillary gland androgen regulated protein 3B (SMR3B) and SMR3A. Similarly, the top upregulated proteins in bacterial keratitis were S100 calcium-binding protein A9 and orosomucoid 2. The acute phase response protein Serpin Family A Member 3 (SERPINA3) was increased in the healthy eye of AAU patients (P = 0.019) compared with healthy controls. Laser flare measurements in affected eyes of AAU patients showed positive logarithmic correlation with SERPINA3 in tear samples of the unaffected eye (P = 0.022). The use of SERPINA3 as a tear biomarker yielded a sensitivity of 85% and a specificity of 71% in detecting patients with AAU in the study population.

CONCLUSIONS

The acute phase response protein SERPINA3 was increased in tear samples of unaffected eyes of patients with unilateral AAU compared with healthy controls. This study highlights SERPINA3 as a potential biomarker for AAU. Future research should explore the dynamic properties of SERPINA3 in the tear fluid of active and quiescent uveitis eyes.

Proteomic Analysis of Tear Film Obtained from Diabetic Dogs

Simple Summary

Canine diabetes is a serious disease, which can lead to severe complications, eventually even death. Currently, all the diagnostic procedures are the invasive ones, with blood collection remaining as a golden standard for both initial diagnosis, and later follow-up. Tears can be obtained in a non-invasive manner, which makes them a perfect candidate for a screening tool in canine diabetes. In this study we aimed to analyze the protein composition of the tears collected from the healthy animals and compared it to the diabetic group. There are significant differences between these two groups, and we believe that the identified proteins hold promise as a potential diagnostic tool, which can be later on used both in clinical practice, and for better understanding of the disease.

Abstract

Canine diabetes mellitus is a significant health burden, followed with numerous systemic complications, including diabetic cataracts and retinopathy, leading to blindness. Diabetes should be considered as a disease damaging all the body organs, including gastrointestinal tract, through a complex combination of vascular and metabolic pathologies, leading to impaired gut function. Tear film can be obtained in a non-invasive way, which makes it a feasible biomarker source. In this study we compared proteomic changes ongoing in tear film of diabetic dogs. The study group consisted of 15 diabetic dogs, and 13 dogs served as a control group. After obtaining tear film with Schirmer strips, we performed 2-dimensional electrophoresis, followed by Delta2D software analysis, which allowed to select statistically significant differentially expressed proteins. After their identification with MALDI-TOF (matrix assisted laser desorption and ionisation time of flight) spectrometry we found one up-regulated protein in tear film of diabetic dogs—SRC kinase signaling inhibitor 1 (SRCIN1). Eight proteins were down-regulated: phosphatidylinositol-4 kinase type 2 alpha (PI4KIIα), Pro-melanin concentrating hormone (Pro-MCH), Flotillin-1, Protein mono-ADP ribosyltransferase, GRIP and coiled coil domain containing protein 2, tetratricopeptide repeat protein 36, serpin, and Prelamin A/C. Identified proteins were analyzed by Panther Gene Ontology software, and their possible connections with diabetic etiopathology were discussed. We believe that this is the first study to target tear film proteome in canine diabetes. We believe that combined with traditional examination, the tear film proteomic analysis can be a new source of biomarkers both for clinical practice, and experimental research.

Tear Proteomic Predictive Biomarker Model for Ocular Graft Versus Host Disease Classification

Purpose

Diagnosis of ocular graft-versus-host disease (oGVHD) is hampered by a lack of clinically-validated biomarkers. This study aims to predict disease severity on the basis of tear protein expression in mild oGVHD.

Methods

Forty-nine patients with and without chronic oGVHD after AHCT were recruited to a cross-sectional observational study. Patients were stratified using NIH guidelines for oGVHD severity: NIH 0 (none; n = 14), NIH 1 (mild; n = 9), NIH 2 (moderate; n = 16), and NIH 3 (severe; n = 10). The proteomic profile of tears was analyzed using liquid chromatography-tandem mass spectrometry. Random forest and penalized logistic regression were used to generate classification and prediction models to stratify patients according to disease severity.

Results

Mass spectrometry detected 785 proteins across all samples. A random forest model used to classify patients by disease grade achieved F1-measure values for correct classification of 0.95 (NIH 0), 0.8 (NIH 1), 0.74 (NIH 2), and 0.83 (NIH 3). A penalized logistic regression model was generated by comparing patients without oGVHD and those with mild oGVHD and applied to identify potential biomarkers present early in disease. A panel of 13 discriminant markers achieved significant diagnostic accuracy in identifying patients with moderate-to-severe disease.

Conclusions

Our work demonstrates the utility of tear protein biomarkers in classifying oGVHD severity and adds further evidence indicating ocular surface inflammation as a main driver of oGVHD clinical phenotype.

Translational Relevance

Expression levels of a 13-marker tear protein panel in AHCT patients with mild oGVHD may predict development of more severe oGVHD clinical phenotypes.

Proteomic Biomarkers of Retinal Inflammation in Diabetic Retinopathy

Diabetic retinopathy (DR), a sight-threatening neurovasculopathy, is the leading cause of irreversible blindness in the developed world. DR arises as the result of prolonged hyperglycemia and is characterized by leaky retinal vasculature, retinal ischemia, retinal inflammation, angiogenesis, and neovascularization. The number of DR patients is growing with an increase in the elderly population, and therapeutic approaches are limited, therefore, new therapies to prevent retinal injury and enhance repair are a critical unmet need. Besides vascular endothelial growth factor (VEGF)-induced vascular proliferation, several other mechanisms are important in the pathogenesis of diabetic retinopathy, including vascular inflammation. Thus, combining anti-VEGF therapy with other new therapies targeting these pathophysiological pathways of DR may further optimize treatment outcomes. Technological advancements have allowed for high-throughput proteomic studies examining biofluids such as aqueous humor, vitreous humor, tear, and serum. Many DR biomarkers have been identified, especially proteins involved in retinal inflammatory processes. This review attempts to summarize the proteomic biomarkers of DR-associated retinal inflammation identified over the last several years.

Combined Targeted Analysis of Metabolites and Proteins in Tear Fluid With Regard to Clinical Applications

Purpose

To establish a robust workflow for combined mass spectrometry–based analysis of metabolites and proteins in tear fluid with regard to clinical applicability.

Methods

Tear fluid was taken from 12 healthy volunteers at different time points using specially designed Schirmer strips. Following the liquid extraction of metabolites from standardized punches, the remaining material was processed for bottom-up proteomics. Targeted metabolite profiling was performed adapting a metabolomics kit, which targets 188 metabolites from four different analyte classes. Proteomics was performed of the identical samples targeting 15 tear proteins relevant to ocular health.

Results

Sixty metabolites could be consistently determined in all tear samples (98 metabolites were detectable in average) covering acylcarnitines, amino acids, biogenic amines, and glycerophospholipids. Following normalization, the majority of metabolites exhibited intraindividual variances of less than 20%, both regarding different times of sampling, and the individual eye. The targeted analysis of tear proteins revealed a mean intraindividual variation of 23% for the three most abundant proteins. Even extreme differences in tear secretion rates resulted in interindividual variability below 30% for 65 metabolites and two proteins.

Conclusions

The newly established workflow can be used for combined targeted detection of metabolites and proteins in one punch of a Schirmer strip in a clinical setting.

Translational Relevance

Our data about intra- and interindividual as well as intereye variation provide a valuable basis for the design of clinical studies, and for the applicability of multiplexed “omics” to well accessible tear fluid with regard to future routine use.

Quantitative proteomics analysis of vitreous body from type 2 diabetic patients with proliferative diabetic retinopathy

Background

To compare the abundance of vitreous proteins between the patients with proliferative diabetic retinopathy (PDR) and idiopathic macular hole (IMH).

Methods

In this study, we performed mass spectrometry-based label-free quantitative proteomics analysis of vitreous samples from type 2 diabetic patients with PDR (n = 9) and IMH subjects (n = 9) and identified the abundance of 610 proteins.

Results

Out of 610 proteins, 64 proteins (Group A) were unique to PDR patients, while 212 proteins (Group B) could be identified in IMH vitreous only. Among the other 334 proteins that could be detected in both PDR and IMH eyes, 62 proteins differed significantly (p < 0.05, fold change > 2), which included 52 proteins (Group C) and 10 proteins (Group D) over- and under-expressed in PDR vitreous compared with the control. All proteins in these four groups were counted as significant proteins in our study.

Conclusions

We identified and quantified 610 proteins in total, which included 338 significant proteins in our study. Protein distribution analysis demonstrated a clear separation of protein expression in PDR and IMH. The protein function analysis illustrated that immunity and transport related proteins might be associated with PDR.

Classification of optic disc shape in glaucoma using machine learning based on quantified ocular parameters

PURPOSE

This study aimed to develop a machine learning-based algorithm for objective classification of the optic disc in patients with open-angle glaucoma (OAG), using quantitative parameters obtained from ophthalmic examination instruments.

METHODS

This study enrolled 163 eyes of 105 OAG patients (age: 62.3 ± 12.6, mean deviation of Humphrey field analyzer: -8.9 ± 7.5 dB). The eyes were classified into Nicolela's 4 optic disc types by 3 glaucoma specialists. Randomly, 114 eyes were selected for training data and 49 for test data. A neural network (NN) was trained with the training data and evaluated with the test data. We used 91 types of quantitative data, including 7 patient background characteristics, 48 quantified OCT (swept-source OCT; DRI OCT Atlantis, Topcon) values, including optic disc topography and circumpapillary retinal nerve fiber layer thickness (cpRNFLT), and 36 blood flow parameters from laser speckle flowgraphy, to build the machine learning classification model. To extract the important features among 91 parameters, minimum redundancy maximum relevance and a genetic feature selection were used.

RESULTS

The validated accuracy against test data for the NN was 87.8% (Cohen's Kappa = 0.83). The important features in the NN were horizontal disc angle, spherical equivalent, cup area, age, 6-sector superotemporal cpRNFLT, average cup depth, average nasal rim disc ratio, maximum cup depth, and superior-quadrant cpRNFLT.

CONCLUSION

The proposed machine learning system has proved to be good identifiers for different disc types with high accuracy. Additionally, the calculated confidence levels reported here should be very helpful for OAG care.

The potential impact of recent insights into proteomic changes associated with glaucoma

INTRODUCTION

Glaucoma, a major ocular neuropathy, is still far from being understood on a molecular scale. Proteomic workflows revealed glaucoma associated alterations in different eye components. By using state-of-the-art mass spectrometric (MS) based discovery approaches large proteome datasets providing important information about glaucoma related proteins and pathways could be generated. Corresponding proteomic information could be retrieved from various ocular sample species derived from glaucoma experimental models or from original human material (e.g. optic nerve head or aqueous humor). However, particular eye tissues with the potential for understanding the disease's molecular pathomechanism remains underrepresented. Areas covered: The present review provides an overview of the analysis depth achieved for the glaucomatous eye proteome. With respect to different eye regions and biofluids, proteomics related literature was found using PubMed, Scholar and UniProtKB. Thereby, the review explores the potential of clinical proteomics for glaucoma research. Expert commentary: Proteomics will provide important contributions to understanding the molecular processes associated with glaucoma. Sensitive discovery and targeted MS approaches will assist understanding of the molecular interplay of different eye components and biofluids in glaucoma. Proteomic results will drive the comprehension of glaucoma, allowing a more stringent disease hypothesis within the coming years.

Machine Learning and Data Mining Methods in Diabetes Research

The remarkable advances in biotechnology and health sciences have led to a significant production of data, such as high throughput genetic data and clinical information, generated from large Electronic Health Records (EHRs). To this end, application of machine learning and data mining methods in biosciences is presently, more than ever before, vital and indispensable in efforts to transform intelligently all available information into valuable knowledge. Diabetes mellitus (DM) is defined as a group of metabolic disorders exerting significant pressure on human health worldwide. Extensive research in all aspects of diabetes (diagnosis, etiopathophysiology, therapy, etc.) has led to the generation of huge amounts of data. The aim of the present study is to conduct a systematic review of the applications of machine learning, data mining techniques and tools in the field of diabetes research with respect to a) Prediction and Diagnosis, b) Diabetic Complications, c) Genetic Background and Environment, and e) Health Care and Management with the first category appearing to be the most popular. A wide range of machine learning algorithms were employed. In general, 85% of those used were characterized by supervised learning approaches and 15% by unsupervised ones, and more specifically, association rules. Support vector machines (SVM) arise as the most successful and widely used algorithm. Concerning the type of data, clinical datasets were mainly used. The title applications in the selected articles project the usefulness of extracting valuable knowledge leading to new hypotheses targeting deeper understanding and further investigation in DM.

The Role of Retinal Imaging and Portable Screening Devices in Tele-ophthalmology Applications for Diabetic Retinopathy Management

In the years since its introduction, retinal imaging has transformed our capability to visualize the posterior pole of the eye. Increasing practical advances in mobile technology, regular monitoring, and population screening for diabetic retinopathy management offer the opportunity for further development of cost-effective applications through remote assessment of the diabetic eye using portable retinal cameras, smart-phone-based devices and telemedicine networks. Numerous retinal imaging methods and mobile technologies in tele-ophthalmology applications have been reported for diabetic retinopathy screening and management. They provide several advantages of automation, sensitivity, specificity, portability, and miniaturization for the development of point-of-care diagnostics for eye complications in diabetes. The aim of this paper is to review the role of retinal imaging and mobile technologies in tele-ophthalmology applications for diabetic retinopathy screening and management. At large, although improvements in current technology and telemedicine services are still needed, telemedicine has demonstrated to be a worthy tool to support health caregivers in the effective management and prevention of diabetes and its complications.

A review on automatic analysis techniques for color fundus photographs

In this paper, we give a review on automatic image processing tools to recognize diseases causing specific distortions in the human retina. After a brief summary of the biology of the retina, we give an overview of the types of lesions that may appear as biomarkers of both eye and non-eye diseases. We present several state-of-the-art procedures to extract the anatomic components and lesions in color fundus photographs and decision support methods to help clinical diagnosis. We list publicly available databases and appropriate measurement techniques to compare quantitatively the performance of these approaches. Furthermore, we discuss on how the performance of image processing-based systems can be improved by fusing the output of individual detector algorithms. Retinal image analysis using mobile phones is also addressed as an expected future trend in this field.

Tear biomarkers for keratoconus

Keratoconus is a progressive corneal thinning, ectatic condition, which affects vision. Recent advances in corneal topography measurements has helped advance proper diagnosis of this condition and increased research and clinical interests in the disease etiopathogenesis. Considerable progress has been achieved in understanding the progression of the disease and tear fluid has played a major role in the progress. This review discusses the importance of tear fluid as a source of biomarker for keratoconus and how advances in technology have helped map the complexity of tears and thereby molecular readouts of the disease. Expanding knowledge of the tear proteome, lipidome and metabolome opened up new avenues to study keratoconus and to identify probable prognostic or diagnostic biomarkers for the disease. A multidimensional approach of analyzing tear fluid of patients layering on proteomics, lipidomics and metabolomics is necessary in effectively decoding keratoconus and thereby identifying targets for its treatment.

Tear fluid biomarkers in ocular and systemic disease: potential use for predictive, preventive and personalised medicine

In the field of predictive, preventive and personalised medicine, researchers are keen to identify novel and reliable ways to predict and diagnose disease, as well as to monitor patient response to therapeutic agents. In the last decade alone, the sensitivity of profiling technologies has undergone huge improvements in detection sensitivity, thus allowing quantification of minute samples, for example body fluids that were previously difficult to assay. As a consequence, there has been a huge increase in tear fluid investigation, predominantly in the field of ocular surface disease. As tears are a more accessible and less complex body fluid (than serum or plasma) and sampling is much less invasive, research is starting to focus on how disease processes affect the proteomic, lipidomic and metabolomic composition of the tear film. By determining compositional changes to tear profiles, crucial pathways in disease progression may be identified, allowing for more predictive and personalised therapy of the individual. This article will provide an overview of the various putative tear fluid biomarkers that have been identified to date, ranging from ocular surface disease and retinopathies to cancer and multiple sclerosis. Putative tear fluid biomarkers of ocular disorders, as well as the more recent field of systemic disease biomarkers, will be shown.

Diabetic retinopathy: Proteomic approaches to help the differential diagnosis and to understand the underlying molecular mechanisms

Diabetic retinopathy is the most common diabetic eye disease and a leading cause of blindness among patients with diabetes. The appearance and the severity of the symptoms correlate with the duration of diabetes and poor blood glucose level management. Diabetic retinopathy is also categorized as a chronic low-level inflammatory disease; the high blood glucose level promotes the accumulation of the advanced glycation end products and leads to the stimulation of monocytes and macrophages. Examination of protein level alterations in tears using state-of the art proteomics techniques have identified several proteins as possible biomarkers for the different stages of the diabetic retinopathy. Some of the differentially expressed tear proteins have a role in the barrier function of tears linking the diabetic retinopathy with another eye complication of diabetes, namely the diabetic keratopathy resulting in impaired wound healing. Understanding the molecular events leading to the eye complications caused by hyperglycemia may help the identification of novel biomarkers as well as therapeutic targets in order to improve quality of life of diabetic patients.

BIOLOGICAL SIGNIFICANCE

Diabetic retinopathy (DR), the leading cause of blindness among diabetic patients can develop without any serious symptoms therefore the early detection is crucial. Because of the increasing prevalence there is a high need for improved screening methods able to diagnose DR as soon as possible. The non-invasive collection and the relatively high protein concentration make the tear fluid a good source for biomarker discovery helping the early diagnosis. In this work we have reviewed the administration of advanced proteomics techniques used in tear biomarker studies and the identified biomarkers with potential to improve the already existing screening methods for DR detection.

Machine Learning Techniques in Clinical Vision Sciences

This review presents and discusses the contribution of machine learning techniques for diagnosis and disease monitoring in the context of clinical vision science. Many ocular diseases leading to blindness can be halted or delayed when detected and treated at its earliest stages. With the recent developments in diagnostic devices, imaging and genomics, new sources of data for early disease detection and patients' management are now available. Machine learning techniques emerged in the biomedical sciences as clinical decision-support techniques to improve sensitivity and specificity of disease detection and monitoring, increasing objectively the clinical decision-making process. This manuscript presents a review in multimodal ocular disease diagnosis and monitoring based on machine learning approaches. In the first section, the technical issues related to the different machine learning approaches will be present. Machine learning techniques are used to automatically recognize complex patterns in a given dataset. These techniques allows creating homogeneous groups (unsupervised learning), or creating a classifier predicting group membership of new cases (supervised learning), when a group label is available for each case. To ensure a good performance of the machine learning techniques in a given dataset, all possible sources of bias should be removed or minimized. For that, the representativeness of the input dataset for the true population should be confirmed, the noise should be removed, the missing data should be treated and the data dimensionally (i.e., the number of parameters/features and the number of cases in the dataset) should be adjusted. The application of machine learning techniques in ocular disease diagnosis and monitoring will be presented and discussed in the second section of this manuscript. To show the clinical benefits of machine learning in clinical vision sciences, several examples will be presented in glaucoma, age-related macular degeneration, and diabetic retinopathy, these ocular pathologies being the major causes of irreversible visual impairment.

Molecular Markers of Diabetic Retinopathy: Potential Screening Tool of the Future?

Diabetic retinopathy (DR) is among the leading causes of new onset blindness in adults. Effective treatment may delay the onset and progression of this disease provided it is diagnosed early. At present retinopathy can only be diagnosed via formal examination of the eye by a trained specialist, which limits the population that can be effectively screened. An easily accessible, reliable screening biomarker of diabetic retinopathy would be of tremendous benefit in detecting the population in need of further assessment and treatment. This review highlights specific biomarkers that show promise as screening markers to detect early diabetic retinopathy or even to detect patients at increased risk of DR at the time of diagnosis of diabetes. The pathobiology of DR is complex and multifactorial giving rise to a wide array of potential biomarkers. This review provides an overview of these pathways and looks at older markers such as advanced glycation end products (AGEs), inflammatory markers, vascular endothelial growth factor (VEGF) as well as other newer proteins with a role in the pathogenesis of DR including neuroprotective factors such as brain derived neurotrophic factor (BDNF) and Pigment Epithelium Derived Factor (PEDF); SA100A12, pentraxin 3, brain natriuretic peptide, apelin 3, and chemerin as well as various metabolites such as lipoprotein A, folate, and homocysteine. We also consider the possible role of proteins identified through proteomics work whose levels are altered in the sera of patients with DR as screening markers though their role in pathophysiology remains to be characterized. The role of microRNA as a promising new screening marker is also discussed.

Biomarkers in Diabetic Retinopathy

There is a global diabetes epidemic correlating with an increase in obesity. This coincidence may lead to a rise in the prevalence of type 2 diabetes. There is also an as yet unexplained increase in the incidence of type 1 diabetes, which is not related to adiposity. Whilst improved diabetes care has substantially improved diabetes outcomes, the disease remains a common cause of working age adult-onset blindness. Diabetic retinopathy is the most frequently occurring complication of diabetes; it is greatly feared by many diabetes patients. There are multiple risk factors and markers for the onset and progression of diabetic retinopathy, yet residual risk remains. Screening for diabetic retinopathy is recommended to facilitate early detection and treatment. Common biomarkers of diabetic retinopathy and its risk in clinical practice today relate to the visualization of the retinal vasculature and measures of glycemia, lipids, blood pressure, body weight, smoking, and pregnancy status. Greater knowledge of novel biomarkers and mediators of diabetic retinopathy, such as those related to inflammation and angiogenesis, has contributed to the development of additional therapeutics, in particular for late-stage retinopathy, including intra-ocular corticosteroids and intravitreal vascular endothelial growth factor inhibitors ('anti-VEGFs') agents. Unfortunately, in spite of a range of treatments (including laser photocoagulation, intraocular steroids, and anti-VEGF agents, and more recently oral fenofibrate, a PPAR-alpha agonist lipid-lowering drug), many patients with diabetic retinopathy do not respond well to current therapeutics. Therefore, more effective treatments for diabetic retinopathy are necessary. New analytical techniques, in particular those related to molecular markers, are accelerating progress in diabetic retinopathy research. Given the increasing incidence and prevalence of diabetes, and the limited capacity of healthcare systems to screen and treat diabetic retinopathy, there is need to reliably identify and triage people with diabetes. Biomarkers may facilitate a better understanding of diabetic retinopathy, and contribute to the development of novel treatments and new clinical strategies to prevent vision loss in people with diabetes. This article reviews key aspects related to biomarker research, and focuses on some specific biomarkers relevant to diabetic retinopathy.

Unraveling the molecular repertoire of tears as a source of biomarkers: beyond ocular diseases

Proteomics and metabolomics investigations of body fluids present several challenges for biomarker discovery of several diseases. The search for biomarkers is actually conducted in different body fluids, even if the ideal biomarker can be found in an easily accessible biological fluid, because, if validated, the biomarker could be sought in the healthy population. In this regard, tears could be considered an optimum material obtained by noninvasive procedures. In the past years, the scientific community has become more interested in the study of tears for the research of new biomarkers not only for ocular diseases. In this review, we provide a discussion on the current state of biomarkers research in tears and their relevance for clinical practice, and report the main results of clinical proteomics studies on systemic and eye diseases. We summarize the main methods for tear samples analyses and report recent advances in "omics" platforms for tears investigations. Moreover, we want to take stock of the emerging field of metabolomics and lipidomics as a new and integrated approach to study protein-metabolites interplay for biomarkers research, where tears represent a still unexplored and attractive field.

Combined Methods for Diabetic Retinopathy Screening, Using Retina Photographs and Tear Fluid Proteomics Biomarkers

Background. It is estimated that 347 million people suffer from diabetes mellitus (DM), and almost 5 million are blind due to diabetic retinopathy (DR). The progression of DR can be slowed down with early diagnosis and treatment. Therefore our aim was to develop a novel automated method for DR screening. Methods. 52 patients with diabetes mellitus were enrolled into the project. Of all patients, 39 had signs of DR. Digital retina images and tear fluid samples were taken from each eye. The results from the tear fluid proteomics analysis and from digital microaneurysm (MA) detection on fundus images were used as the input of a machine learning system. Results. MA detection method alone resulted in 0.84 sensitivity and 0.81 specificity. Using the proteomics data for analysis 0.87 sensitivity and 0.68 specificity values were achieved. The combined data analysis integrated the features of the proteomics data along with the number of detected MAs in the associated image and achieved sensitivity/specificity values of 0.93/0.78. Conclusions. As the two different types of data represent independent and complementary information on the outcome, the combined model resulted in a reliable screening method that is comparable to the requirements of DR screening programs applied in clinical routine.

Glycomic characterization of basal tears and changes with diabetes and diabetic retinopathy

As a secreted fluid, the state of tear glycosylation is particularly important in the role of immunity of the ocular surface. Tears are a valuable source of non-invasive biomarkers for disease and there are continued efforts to characterize their components thoroughly. In this study, a small volume of basal tears (5 μL) was collected from healthy controls, patients with diabetes without retinopathy and patients with diabetes and retinopathy. The detailed N- and O-linked tear protein glycome was characterized and the relative abundance of each structure determined. Of the 50 N-linked glycans found, 89% were complex with 50% containing a bisecting N-acetylglucosamine, 65% containing a core fucose whilst 33% were sialylated. Of the 8 O-linked glycans detected, 3 were of cores 1 and 5 of core 2 type, with a majority of them being sialylated (90%). Additionally, these glycan structures were profiled across the three diabetic disease groups. Whilst the higher abundant structures did not alter across the three groups, only five low abundance N-linked glycans and 1 O-linked glycan did alter with the onset of diabetes mellitus and diabetic retinopathy (DR). These results suggest the conservation of glycan types on basal tear proteins between individuals and point to only small changes in glycan expression on the proteins in tears with the development of diabetes and DR.