Inflammatory bowel disease (IBD) is a complex disorder that involves chronic inflammation of the digestive tract. IBD has mainly two subtypes, Crohn’s disease (CD) and ulcerative colitis (UC). IBD affects around 6.8 million globally, and < 1.3 million people in Europe. IBD can be devastating, resulting in significantly reduced quality of life.
There are multiple factors, such as genetics, environmental factors, microbiome, and immune system that cause IBD; but the molecular mechanisms behind IBD are still elusive. A significant proportion of patient fails to respond to therapy. Therefore, it is important to identify non-responders to standard therapy, so alternative treatments can be applied sooner.

In this work, a biological interpretable quantitative model was developed that predicts therapy response in UC patients. This model characterizes the individuals based on how strongly they respond to their immune systems’ alarm signals. These signals are interpreted through a complex network of protein molecules that determine how cells respond. We propose a mathematical model of how these networks process signals differently in each individual and relate this to which drugs patients respond to.