PanGIA Analysis System Is a Novel Machine Learning Framework for Non-Invasive Rare Disease Diagnosis Using Urinary Biomolecular Signatures
Year: 2025
Type: article
Abstract: Introduction: The rare prevalence of some metabolic disorders makes widespread, regular testing economically unfeasible. A comprehensive, low cost, and non-invasive biopsy solution for rare metabolic disorders is needed to promote diagnosis of such conditions before symptoms manifest. Herein we report a proof-of-concept framework based on machine learning to predict metabolic dysregulation. The PanGIA Analysis System (PAS) is a machine learning powered framework similar to Google Gemini or ChatGPT aimed at learning biochemical signatures.
Source: The Journal of Liquid Biopsy
Authors: Abhignyan Nagesetti, Francis Lim, Nicholas Gonzalez, Miguel Javiel, Pablo Hernandez, Kyle Ambert, Robert Cardwell, Obdulio Piloto
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $2,080
OpenAlex ID: W4416630998