We have developed a next-generation, high-throughput peptide microarray using a bead-based Luminex assay, which is more sensitive than current tests. Our diagnostic methodology applies machine learning techniques to a database of epitope signatures from real food allergy patients for more precise diagnosis, monitoring and determination of allergic response.
Food allergies occur when the body’s immune system is sensitive to a protein found in a particular food, known as an allergen. IgE and IgG4 antibodies react with allergens, initiating an inflammatory response, which can result in anaphylaxis in the most severe cases. Our technology uses a Component Resolved Diagnostic approach, which subdivides allergenic proteins found in specific foods into smaller peptides, called epitopes, and then measures the reactivity of a patient’s IgE/IgG4 levels to these epitopes. Identifying the binding site of each antibody on each target epitope antigen, known as epitope mapping, creates a patient allergy profile or epitope signature that can be used by providers to better assess and manage patients’ food allergies. Our team has already created a growing database of nearly 1,000 epitope signatures to refine the algorithms underlying the technology’s precision.
The AllerGenis platform is poised to reshape the testing landscape with increased resolution and capacity.
The density of information produced by the AllerGenis platform via epitope mapping technology provides the greatest resolution for analysis, assessment and management validated against OFC, with demonstrated superiority to commonly used diagnostic options.
Historically, it was thought we develop allergies to a specific protein, yet now we know the chemistry and immune response is more granular. For instance, studying IgE to whole peanut extract or even its components does not provide the specificity of the true response at the molecular level. Therefore, a higher resolution allergy test panel can identify the specific epitopes within a protein responsible for an allergic response in a patient.
The quantity of information produced by epitope mapping provides the greatest resolution for analysis with the ability to deliver definitive diagnostic, prognostic and predictive results reporting, when compared to simply looking at whole extracts or components.
Our proprietary epitope mapping platform is based on technology originally developed by Hugh Sampson, MD, of the Elliot and Roslyn Jaffe Food Allergy Institute of the Icahn School of Medicine at Mount Sinai and has been validated against the food allergy diagnosis gold standard (oral food challenge) in three separate cohorts and more than 1,000 patients. We are creating the largest food allergy knowledge-base populated by individual patient epitope signatures derived from our epitope mapping technology, clinical history and patient reported outcomes. Machine learning is applied to analyze the database, understand allergy subtypes, and identify unique biomarkers for the purpose of refining algorithms, resulting in improved patient care and outcomes. Algorithms may also be used to monitor and predict outcomes of future immunotherapies for food allergies.