Artificial intelligence at the national eye institute.

PURPOSE OF REVIEW: This review highlights the artificial intelligence, machine learning, and deep learning initiatives supported by the National Institutes of Health (NIH) and the National Eye Institute (NEI) and calls attention to activities and goals defined in the NEI Strategic Plan as well as opportunities for future activities and breakthroughs in ophthalmology. RECENT FINDINGS: Ophthalmology is at the forefront of artificial intelligence-based innovations in biomedical research that may lead to improvement in early detection and surveillance of ocular disease, prediction of progression, and improved quality of life. Technological advances have ushered in an era where unprecedented amounts of information can be linked that enable scientific discovery. However, there remains an unmet need to collect, harmonize, and share data in a machine actionable manner. Similarly, there is a need to ensure that efforts promote health and research equity by expanding diversity in the data and workforce. SUMMARY: The NIH/NEI has supported the development artificial intelligence-based innovations to advance biomedical research. The NIH/NEI has defined activities to achieve these goals in the NIH Strategic Plan for Data Science and the NEI Strategic Plan and have spearheaded initiatives to facilitate research in these areas.

Genotype-phenotype associations in a large PRPH2-related retinopathy cohort.

Molecular variant interpretation lacks disease gene-specific cohorts for determining variant enrichment in disease versus healthy populations. To address the molecular etiology of retinal degeneration, specifically the PRPH2-related retinopathies, we reviewed genotype and phenotype information obtained from 187 eyeGENE® participants from 161 families. Clinical details were provided by referring clinicians participating in the eyeGENE® Network. The cohort was sequenced for variants in PRPH2. Variant complementary DNA clusters and cohort frequency were compared to variants in public databases to help us to determine pathogenicity by current American College of Medical Genetics and Genomics/Association for Molecular Pathology interpretation criteria. The most frequent variant was c.828+3A>T, which affected 28 families (17.4%), and 25 of 79 (31.64%) variants were novel. The majority of missense variants clustered in the D2 intracellular loop of the peripherin-2 protein, constituting a hotspot. Disease enrichment was noted for 23 (29.1%) of the variants. Hotspot and disease-enrichment evidence modified variant classification for 16.5% of variants. The missense allele p.Arg172Trp was associated with a younger age of onset. To the best of our knowledge, this is the largest patient cohort review of PRPH2-related retinopathy. Large disease gene-specific cohorts permit gene modeling for hotspot and disease-enrichment analysis, providing novel variant classification evidence, including for novel missense variants.

Genetic testing for inherited eye conditions in over 6,000 individuals through the eyeGENE network.

Genetic testing in a multisite clinical trial network for inherited eye conditions is described in this retrospective review of data collected through eyeGENE®, the National Ophthalmic Disease Genotyping and Phenotyping Network. Participants in eyeGENE were enrolled through a network of clinical providers throughout the United States and Canada. Blood samples and clinical data were collected to establish a phenotype:genotype database, biorepository, and patient registry. Data and samples are available for research use, and participants are provided results of clinical genetic testing. eyeGENE utilized a unique, distributed clinical trial design to enroll 6,403 participants from 5,385 families diagnosed with over 30 different inherited eye conditions. The most common diagnoses given for participants were retinitis pigmentosa (RP), Stargardt disease, and choroideremia. Pathogenic variants were most frequently reported in ABCA4 (37%), USH2A (7%), RPGR (6%), CHM (5%), and PRPH2 (3%). Among the 5,552 participants with genetic testing, at least one pathogenic or likely pathogenic variant was observed in 3,448 participants (62.1%), and variants of uncertain significance in 1,712 participants (30.8%). Ten genes represent 68% of all pathogenic and likely pathogenic variants in eyeGENE. Cross-referencing current gene therapy clinical trials, over a thousand participants may be eligible, based on pathogenic variants in genes targeted by those therapies. This article is the first summary of genetic testing from thousands of participants tested through eyeGENE, including reports from 5,552 individuals. eyeGENE provides a launching point for inherited eye research, connects researchers with potential future study participants, and provides a valuable resource to the vision community.

Data Harmonization, Standardization, and Collaboration for Diabetic Retinal Disease (DRD) Research: Report From the 2024 Mary Tyler Moore Vision Initiative Workshop on Data.

The 2024 Mary Tyler Moore Vision Initiative (MTM Vision) Workshop on Data convened to discuss best practices and specific considerations for building a comprehensive, shareable MTM Vision data lake. The workshop aimed to accelerate the development of new indications, therapies, and regulatory pathways for diabetic retinal disease (DRD) by standardizing and harmonizing clinical data and ocular 'omics analyses. Standardization of data collection, the use of common data elements, and data interoperability were emphasized, alongside federated learning approaches to promote data sharing and collaboration while maintaining data privacy and security. The integration of molecular data with other multimodal data types was recognized as a promising strategy for leveraging machine learning and AI approaches to advancing therapeutics development and improving treatment outcomes for DRD patients. Partnerships with entities such as the National Eye Institute, part of the National Institutes of Health, foundations, and industry were deemed vital for the successful implementation of these initiatives.

Ocular Imaging Challenges, Current State, and a Path to Interoperability: A HIMSS-SIIM Enterprise Imaging Community Whitepaper.

Office-based testing, enhanced by advances in imaging technology, is routinely used in eye care to non-invasively assess ocular structure and function. This type of imaging coupled with autonomous artificial intelligence holds immense opportunity to diagnose eye diseases quickly. Despite the wide availability and use of ocular imaging, there are several factors that hinder optimization of clinical practice and patient care. While some large institutions have developed end-to-end digital workflows that utilize electronic health records, enterprise imaging archives, and dedicated diagnostic viewers, this experience has not yet made its way to smaller and independent eye clinics. Fractured interoperability practices impact patient care in all healthcare domains, including eye care where there is a scarcity of care centers, making collaboration essential among providers, specialists, and primary care who might be treating systemic conditions with profound impact on vision. The purpose of this white paper is to describe the current state of ocular imaging by focusing on the challenges related to interoperability, reporting, and clinical workflow.

Advancing Toward a Common Data Model in Ophthalmology: Gap Analysis of General Eye Examination Concepts to Standard Observational Medical Outcomes Partnership (OMOP) Concepts.

Purpose: Evaluate the degree of concept coverage of the general eye examination in one widely used electronic health record (EHR) system using the Observational Health Data Sciences and Informatics Observational Medical Outcomes Partnership (OMOP) common data model (CDM). Design: Study of data elements. Participants: Not applicable. Methods: Data elements (field names and predefined entry values) from the general eye examination in the Epic foundation system were mapped to OMOP concepts and analyzed. Each mapping was given a Health Level 7 equivalence designation-equal when the OMOP concept had the same meaning as the source EHR concept, wider when it was missing information, narrower when it was overly specific, and unmatched when there was no match. Initial mappings were reviewed by 2 graders. Intergrader agreement for equivalence designation was calculated using Cohen's kappa. Agreement on the mapped OMOP concept was calculated as a percentage of total mappable concepts. Discrepancies were discussed and a final consensus created. Quantitative analysis was performed on wider and unmatched concepts. Main Outcome Measures: Gaps in OMOP concept coverage of EHR elements and intergrader agreement of mapped OMOP concepts. Results: A total of 698 data elements (210 fields, 488 values) from the EHR were analyzed. The intergrader kappa on the equivalence designation was 0.88 (standard error 0.03, P < 0.001). There was a 96% agreement on the mapped OMOP concept. In the final consensus mapping, 25% (1% fields, 31% values) of the EHR to OMOP concept mappings were considered equal, 50% (27% fields, 60% values) wider, 4% (8% fields, 2% values) narrower, and 21% (52% fields, 8% values) unmatched. Of the wider mapped elements, 46% were missing the laterality specification, 24% had other missing attributes, and 30% had both issues. Wider and unmatched EHR elements could be found in all areas of the general eye examination. Conclusions: Most data elements in the general eye examination could not be represented precisely using the OMOP CDM. Our work suggests multiple ways to improve the incorporation of important ophthalmology concepts in OMOP, including adding laterality to existing concepts. There exists a strong need to improve the coverage of ophthalmic concepts in source vocabularies so that the OMOP CDM can better accommodate vision research. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

eyeGENE(R): a novel approach to combine clinical testing and researching genetic ocular disease.

PURPOSE OF REVIEW: Molecular genetics is revolutionizing the diagnosis and treatment of inherited eye diseases. The National Eye Institute of the National Institutes of Health (NIH), in an effort to facilitate future basic and clinical research in inherited eye disease, created The National Ophthalmic Disease Genotyping and Phenotyping Network (eyeGENE). This review describes the process and utility of the eyeGENE program as it relates to ophthalmic clinical practice. RECENT FINDINGS: Over the last few years, genetic testing of specific genes associated with inherited eye conditions is becoming the standard practice. Vision research and human clinical trials relying on molecular genetic testing of individuals with inherited eye conditions are becoming more common. Eye healthcare professionals must consider the options to assist patients in obtaining genetic testing results and locating trials or studies that may have benefit. SUMMARY: eyeGENE is a DNA repository and patient registry for inherited eye diseases coupled to phenotypic descriptors and molecular genetic information. Through eyeGENE, healthcare professionals throughout the United States and Canada can obtain Clinical Laboratory Improvement Amendments-certified clinical molecular genetic results on their patients. Researchers may request access to a de-identified database of phenotype and genotype information about eyeGENE participants and DNA aliquots for their research studies. eyeGENE also offers participants the option of being included in a patient registry, whereby they may be re-contacted if an approved clinical study for which they might qualify is offered.

Ergot cluster-encoded catalase is required for synthesis of chanoclavine-I in Aspergillus fumigatus.

Genes required for ergot alkaloid biosynthesis are clustered in the genomes of several fungi. Several conserved ergot cluster genes have been hypothesized, and in some cases demonstrated, to encode early steps of the pathway shared among fungi that ultimately make different ergot alkaloid end products. The deduced amino acid sequence of one of these conserved genes (easC) indicates a catalase as the product, but a role for a catalase in the ergot alkaloid pathway has not been established. We disrupted easC of Aspergillus fumigatus by homologous recombination with a truncated copy of that gene. The resulting mutant (ΔeasC) failed to produce the ergot alkaloids typically observed in A. fumigatus, including chanoclavine-I, festuclavine, and fumigaclavines B, A, and C. The ΔeasC mutant instead accumulated N-methyl-4-dimethylallyltryptophan (N-Me-DMAT), an intermediate recently shown to accumulate in Claviceps purpurea strains mutated at ccsA (called easE in A. fumigatus) (Lorenz et al. Appl Environ Microbiol 76:1822-1830, 2010). A ΔeasE disruption mutant of A. fumigatus also failed to accumulate chanoclavine-I and downstream ergot alkaloids and, instead, accumulated N-Me-DMAT. Feeding chanoclavine-I to the ΔeasC mutant restored ergot alkaloid production. Complementation of either ΔeasC or ΔeasE mutants with the respective wild-type allele also restored ergot alkaloid production. The easC gene was expressed in Escherichia coli, and the protein product displayed in vitro catalase activity with H(2)O(2) but did not act, in isolation, on N-Me-DMAT as substrate. The data indicate that the products of both easC (catalase) and easE (FAD-dependent oxidoreductase) are required for conversion of N-Me-DMAT to chanoclavine-I.

Identification of Deep-Intronic Splice Mutations in a Large Cohort of Patients With Inherited Retinal Diseases.

High throughput sequencing technologies have revolutionized the identification of mutations responsible for a diverse set of Mendelian disorders, including inherited retinal disorders (IRDs). However, the causal mutations remain elusive for a significant proportion of patients. This may be partially due to pathogenic mutations located in non-coding regions, which are largely missed by capture sequencing targeting the coding regions. The advent of whole-genome sequencing (WGS) allows us to systematically detect non-coding variations. However, the interpretation of these variations remains a significant bottleneck. In this study, we investigated the contribution of deep-intronic splice variants to IRDs. WGS was performed for a cohort of 571 IRD patients who lack a confident molecular diagnosis, and potential deep intronic variants that affect proper splicing were identified using SpliceAI. A total of six deleterious deep intronic variants were identified in eight patients. An in vitro minigene system was applied to further validate the effect of these variants on the splicing pattern of the associated genes. The prediction scores assigned to splice-site disruption positively correlated with the impact of mutations on splicing, as those with lower prediction scores demonstrated partial splicing. Through this study, we estimated the contribution of deep-intronic splice mutations to unassigned IRD patients and leveraged in silico and in vitro methods to establish a framework for prioritizing deep intronic variant candidates for mechanistic and functional analyses.

Sample Confirmation Testing: A Short Tandem Repeat-Based Quality Assurance and Quality Control Procedure for the eyeGENE Biorepository.

Quality assurance and quality control (QA/QC) procedures are vital to good biorepository management. The National Eye Institute (NEI) core CLIA-certified laboratory of the eyeGENE(®) Network receives blood from individuals with inherited eye conditions and isolates DNA for clinical genetic diagnostic testing and research. Clinical genetic test results are returned to the affected individuals, making it imperative that sample integrity is preserved throughout laboratory processing. A clinically validated, short tandem repeat (STR)-based approach, termed Sample Confirmation Testing (SCT), was developed to ensure that no significant laboratory errors occurred during processing. SCT uses modified protocols from commercial kits to create and compare STR profiles for each participant's original blood and derived DNA. This QA/QC procedure has been performed on 47% of the more than 6000 participants in the eyeGENE Biorepository and has identified significant laboratory errors in 0.4% of samples tested. SCT improves the quality of the data returned to affected individuals and the data distributed to researchers using eyeGENE samples by ensuring the integrity of the samples and aiding in curation of the biorepository. This approach serves as a model for other repositories to improve sample quality and management procedures.

Structural analysis of a peptide synthetase gene required for ergopeptine production in the endophytic fungus Neotyphodium lolii.

Lysergyl peptide synthetase 1 catalyzes the assembly of toxic ergopeptines from activated D-lysergic acid and three amino acids. The gene encoding this enzyme in the endophytic fungus Neotyphodium lolii was analyzed and compared to a homologous gene from the ergot fungus Claviceps purpurea. Each gene contained two introns, which were found in the same relative position within two modules of the gene. The 5' ends of the two genes were unusually divergent. Signature sequences determining substrate specificity were similar in adenylation domains that recognized identical amino acids but differed within the adenylation domain for the amino acid that varies between the major ergopeptines of the two fungi. Homologues were detected in several related endophytic fungi; the tall fescue endophyte Neotyphodium coenophialum contained a divergent, second copy of the gene. Our results provide new information on the structure and distribution of this important peptide synthetase involved in ergot alkaloid biosynthesis.