Journal Article

Artificial intelligence guided discovery of a barrier-protective therapy in inflammatory bowel disease

Stec, Dominik L., Mittal, Yash, Sayed, Ibrahim M., Das, Soumita, Pranadinata, Rama F., Fuller, Mackenzie, Ibeawuchi, Stella-Rita, Ghosh, Pradipta, Chang, John T., Sandborn, William J., Swanson, Lee, Tindle, Courtney, Sahoo, Debashis, Katkar, Gajanan D.

2021

Overview

Modeling human diseases as networks simplify complex multi-cellular processes, helps understand patterns in noisy data that humans cannot find, and thereby improves precision in prediction. Using Inflammatory Bowel Disease (IBD) as an example, here we outline an unbiased AI-assisted approach for target identification and validation. A network was built in which clusters of genes are connected by directed edges that highlight asymmetric Boolean relationships. Using machine-learning, a path of continuum states was pinpointed, which most effectively predicted disease outcome. This path was enriched in gene-clusters that maintain the integrity of the gut epithelial barrier. We exploit this insight to prioritize one target, choose appropriate pre-clinical murine models for target validation and design patient-derived organoid models. Potential for treatment efficacy is confirmed in patient-derived organoids using multivariate analyses. This AI-assisted approach identifies a first-in-class gut barrier-protective agent in IBD and predicted Phase-III success of candidate agents. Traditional drug discovery process use differential, Bayesian and other network based approaches. We developed a Boolean approach for building disease maps and prioritizing pre-clinical models to discover a first-in-class therapy to restore and protect the leaky gut barrier in inflammatory bowel disease.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 14/1 / 38/61 / 38/77 / 631/114 / 692/4020/1503/257/1389 / 692/4020/1503/257/1402 / 82/51 / 82/80 / Agents (artificial intelligence) / AMP-Activated Protein Kinases - antagonists & inhibitors / AMP-Activated Protein Kinases - metabolism / Animal models / Animals / Artificial Intelligence / Bayesian analysis / Boolean / Boolean algebra / Cellular communication / Cohort Studies / Colitis - genetics / Dextran Sulfate / Disease Models, Animal / Gene Expression Regulation / Gene mapping / Humanities and Social Sciences / Humans / Inflammatory bowel disease / Inflammatory bowel diseases / Inflammatory Bowel Diseases - genetics / Inflammatory Bowel Diseases - pathology / Inflammatory Bowel Diseases - therapy / Intestinal Mucosa - pathology / Intestine / Learning algorithms / Likelihood Functions / Machine Learning / Mathematical models / Mice / Mice, Inbred C57BL / Mice, Knockout / Molecular Targeted Therapy / multidisciplinary / Multigene Family / Organoids / Organoids - pathology / Patients / Reproducibility of Results / Science / Science (multidisciplinary) / Target recognition / Treatment Outcome