SEARCHING SYSTEM FOR BIOSIGNATURE EXTRACTION AND BIOMARKER DISCOVERY

An automated system and method is provided for biotype extraction and biomarker discovery from task-based fMRI imaging data. The system and method may include automatically mapping a localizome, such as a task-condition/contrast/population-specific brain functional localizome, based on fMRI data and automatically selecting and sorting brain regions or brain nodes to produce a subset of functional brain regions or brain nodes. A report may then be generated indicating that the subject has a particular brain circuit pattern of activity and connectivity associated with one or more symptoms of the given mental disorder, treatments, or associated with normal brain functions, based upon the extracted biosignatures by searching for the optimal multivariate classifier with least dimensionality in the brain functional localizome. These biosignatures and biomarkers that reveal hidden, implicit, and latent brain circuit patterns provoked by fMRI tasks, can also provide for the development of non-invasive diagnostics and targeted therapeutics in neuropsychiatric diseases.