This article is more than 5 years old. Information may no longer be current.
Multidimensional predictive model reveals complexity of immune response in IBD
Click Here to Manage Email Alerts
A multi-omics predictive model revealed new insights into the complex immune response network in inflammatory bowel disease, which could potentially lead to new therapeutic targets, according to new data published in Nature Genetics.
“These results demonstrate how much we stand to gain by organizing massive amounts of molecular and clinical data using advanced machine learning approaches that in turn can be queried to generate novel disease insights,” Eric E. Schadt, PhD, CEO of the health information company Sema4, and Dean for Precision Medicine at Icahn School of Medicine at Mount Sinai, said in a press release. “Our predictive model serves as a repository of knowledge and understanding that facilitates learning more about the development and progression of IBD, including identifying master regulators of disease that can be explored as targets for treatment.”
To develop this “first-ever predictive model,” researchers collected data on clinical factors and molecular data including DNA variation, gene expression and regulatory elements using intestinal tissue samples from three independent groups of patients in various stages of IBD. These included treatment-naive pediatric patients from the RISK cohort, anti-TNF refractory patients from a clinical trial of Stelara (ustekinumab, Janssen), and patients with advanced IBD.
The investigators then integrated these data sets using a machine learning strategy to precisely model the biological networks involved in the immune component of the disease. Of note, they characterized interactions between genes and regulatory elements to map the entire immune response network, and experimentally validated the top 12 genes predicted to modulate the network, which were previously identified in genome-wide association studies. This validated set of “key driver” genes represents novel regulators of IBD processes, and “integrated circuits of genetic, molecular, and clinical traits that can be directly queried to interrogate and refine the regulatory framework defining IBD,” investigators wrote.
“By creating multiscale predictive models of the immune component of IBD across different stages of disease, this work helps move us towards a more comprehensive understanding of the complex molecular network of this disease,” Scott Snapper, MD, PhD, professor of medicine at Harvard Medical School and chair of the national scientific advisory board of the Crohn’s and Colitis Foundation, who was not involved in the study, said in the press release. “I look forward to accessing this new knowledge base as highly informative to the collective efforts of the IBD research community to identity new targets and ultimately, novel treatments of IBD.” – by Adam Leitenberger
Disclosures: Some of the researchers report they were employed by Janssen at the time of this study.
Read more about
Click Here to Manage Email Alerts