Sana Syed
Duke University, NC·Medicine & Clinical Research·Early-career
Crohn's disease is a chronic inflammation of the gut that is becoming more common in children aged 10 to 18. It can stunt growth and development.
- Fields
Medicine & Clinical Research
Computer Science
Microbiology & Immunology
- Topics
Crohn's disease
inflammatory bowel disease
ileum
- Grants
- 3 known grants, through Aug 2030
What they work on
- Build a computational metabolic network reconstruction specific to the ileum, the part of the small intestine most affected by Crohn's disease, to serve as a reference model of healthy and diseased gut metabolism.
- Map transcriptomic data from a large pediatric Crohn's cohort onto the ileal metabolic model to find metabolic shifts linked to stricturing and treatment-resistant subtypes, validating with RNA sequencing of a new multi-site cohort and with metabolomics and lipidomics.
- Profile the gene activity and metabolites of ileal organoids grown from pediatric Crohn's patients, to test whether these lab-grown tissues are a good stand-in for studying metabolic shifts and interventions.
- Train and validate machine learning models that predict Crohn's disease outcomes from biopsy histopathology images, using saliency maps and gene correlation analysis to identify the tissue features driving predictions.
- Integrate deep image features with routine clinical metadata into a predictive model of Crohn's outcomes, and benchmark it against a compiled set of published prediction models.
- Use single-cell RNA sequencing and spatial transcriptomics to define a gene-activity signature of Crohn's disease and link specific genetic profiles to hallmark tissue changes in diseased bowel.
More about the research
Some children have mild disease that responds to standard drugs. Others develop severe forms that narrow the bowel (strictures), tear through its wall (penetrating disease), or resist treatment and require surgery. Doctors cannot yet tell at diagnosis which path a child will take. The research aims to predict these outcomes early by combining large patient datasets with computational tools: models of gut metabolism, machine learning on biopsy images, and gene-activity measurements. It also trains young clinician-researchers to apply these data science methods to immune diseases of the gut.
Why it matters
Children with Crohn's disease could benefit from earlier, more personalized care. Strong anti-inflammatory drugs could go to those likely to develop strictures, penetrating disease, or treatment resistance, while sparing children with milder disease unnecessary side effects. Metabolic biomarkers and biopsy-based machine learning models could help doctors sort patients at diagnosis and may point to metabolic pathways as treatment targets.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Mentoring in Data Science for Big Data and omics in Immunologic Diseases
NIH · Sep 2025 – Aug 2030
Population-Based Characterization of Metabolic Pathways to Predict Pediatric Crohn's Disease Outcomes
NIH · Apr 2025 – Apr 2027
Predicting Clinical Phenotypes in Crohn's Disease Using Machine Learning and Single-Cell 'omics
NIH · Mar 2025 – Apr 2027
Closest labs
Ling-shiang Chuang
Icahn School of Medicine at Mount Sinai, NY·Genetics
Profile perianal fistula tissue from Crohn's disease patients with single-cell multiome ATAC plus transcriptome and spatial transcriptomics, which measure open DNA, gene activity and location cell by cell.
Brad Constant
University of Colorado Denver/Anschutz Medical Campus, CO·Medicine & Clinical Research·Early-career
Compare the effectiveness of anti-TNF and anti-interleukin biologics in children with Crohn's disease, using causal inference methods in a validated multicenter retrospective cohort.
Kathryn Torok
University of Pittsburgh, PA·Medicine & Clinical Research
Identify cell-specific gene activity signatures and their spatial relationships in skin from children with jSSc and jLS versus healthy controls, using single-cell RNA sequencing and spatial transcriptomics.
The school
Duke University: 61 labs on PI Pages, $1.6B a year on research, 417 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.