Decrypting Necrotising Enterocolitis And Pediatric Intestinal Development Through Advanced Computational Biology and Machine Learning Approaches

The rapid advancement of genomics technologies has transformed our understanding of biology but has also led to increasingly complex datasets. The future of this field involves analysing more cells and molecules and integrating diverse data types, which presents significant challenges in data interpretation. Simultaneously, application of machine learning models have shown immense potential in managing these complexities, particularly in single-cell biology, through applications like gene regulatory network reconstructions and predictive modelling. Despite this, a significant gap remains between computational models and their translation into biological and clinical applications. This project aims to bridge this gap by developing both generalizable tools and data-driven, domain-specific models. Focusing on high dimensional data generated across a series of experiments designed to address unanswered questions in human intestinal development and necrotizing enterocolitis (NEC), this setting provides a unique opportunity to collect invaluable datasets for both computational methods development and advancing understanding of NEC. NEC, a severe inflammatory condition in premature infants, involves complex inflammatory pathways and microbial dysbiosis. Current treatments are limited due to an incomplete understanding of its molecular mechanisms. This project seeks to fill these gaps by leveraging spatial transcriptomics and multi-omics approaches coupled with state-of-the-art AI methods to improve NEC understanding.