Abstract: Asthma is a common, under-diagnosed disease affecting all ages. Mild to moderate asthma is particularly difficult to diagnose given currently available tools. A nasal biomarker of asthma is of high interest given the accessibility of the nose and shared airway biology between the upper and lower respiratory tract. A machine learning pipeline identified an asthma gene panel of 275 unique nasally-expressed genes interpreted via different classification models. This asthma gene panel can be utilized to reliably diagnose asthma in patients, including mild to moderate asthma, in a non-invasive manner and to distinguish asthma from other respiratory disorders, allowing appropriate treatment of the patient's asthma.