How SYGNAL works
Developed by our co-founder Dr. Nitin Baliga at the Institute for Systems Biology (ISB), SYGNAL uses network quantization to amplify meaningful signals within complex and noisy tumor profiles. Much like Google Maps uses reference maps and dynamic traffic information to predict optimal routes, SPOT-AI employs proprietary disease network maps to single out an individual patient’s molecular tumor profile and identifies the unique causal mechanisms that drive the progression of the disease. This allows the Sygnomics Analytics Test (SAT) to predict the disease progression risk and recommend the most effective treatments.
Choosing the right treatments and expanding treatment options
SPOT-AI is able to offer risk predictions for both solid tumors such as glioblastoma and liquid tumors like multiple myeloma.
For glioblastoma, there simply aren’t many successful therapies available.
For multiple myeloma, while there are a variety of treatments available, they aren’t personalized.
Expanding the view of the patient’s cancer landscape
Traditional approaches to disease risk prediction (a combination of histology and stage vs. how fast it will progress) and treatment matching often fail because they oversimplify cancer’s complexity. In contrast, SPOT-AI analyzes the entire disease network within each patient’s tumor, enabling truly personalized treatments.
