Overview
Research Vision
The Rashid Lab develops statistical methods and computational tools that bridge genomics, clinical trials, and precision medicine.
Our portfolio spans four interconnected research themes, each pairing methodological advances with translational applications at UNC Lineberger Comprehensive Cancer Center.
- Precision medicine engines for biomarker-driven trials
- Transcriptomic + epigenomic software for regulatory discovery
- Generative AI for missing data, imaging, and adaptive monitoring
- Trial innovation + mentorship to move methods into practice
Research Portfolio Map (2011-2025)
Interactive Research Portfolio (2011-2025)
Tip: Hover over nodes to see paper details. Click and drag to explore connections.
Research Themes
Cancer Precision Medicine
Statistical engines for biomarker-driven treatment selection, subtyping, and patient stratification.
- PurIST single-sample classifier powering PDAC trials.
- Stroma-aware subtyping and multi-omic GLMMs across cancers.
- Between-study reproducibility frameworks for biomarkers.
Transcriptomic, Epigenomic, and Bioinformatics Tool Development
Open-source software for RNA-seq, ChIP/ATAC, and multi-omic discovery across regulatory programs.
- CompDTUReg, FSCseq, and related RNA-seq toolkits.
- epigraHMM/mixNBHMM for multi-condition enrichment.
- Allele-specific and isoform-level inference pipelines.
Generative AI and Deep Learning
Generative and deep-learning architectures for missing data, semi-supervised learning, and computational pathology.
- NIMIWAE and dlglm for non-ignorable missingness.
- Semi-supervised matrix factorization for subtyping.
- Generative copilots for trial matching and EHR analytics.
Adaptive Trial Design & Real-Time Biomarker Integration
Bayesian platform designs that ingest ctDNA, imaging, and clinical signals to guide oncology decisions.
- ARPA-H ADAPT and TBCRC evolutionary designs.
- Biomarker-aware randomization with serial ctDNA.
- Master protocols for cooperative group studies.
Cross-Cutting Methodological Innovations
Rigor & Reproducibility
Quantification-aware modeling, heterogeneity frameworks, and documented toolkits.
Clinical Translation
Embedded with UNC oncologists and cooperative groups to run adaptive, biomarker-rich trials.
Open Software
10+ CRAN/Bioconductor packages with tutorials, vignettes, and active maintenance.
Funding & Support
Flagship awards:
- ARPA-H ADAPT Platform – $30M metastatic breast cancer trial (2025–2031).
- NIH/NCI Breast SPORE – Core B co-lead powering multi-site analytics (2024–2029).
- NIH/NCI Pancreatic SPORE – Core C co-lead for IQS pipelines (2022–2027).
- DOD PCARP TrialMatch LLM – ctDNA-aware navigation AI (2024–2026).
Collaborative Network
UNC Lineberger
Jen Jen Yeh, Lisa Carey, Chuck Perou, and Ben Vincent co-drive pancreatic, breast, and immunotherapy trials.
National Consortia
Alliance, TBCRC, and PDAC Stromal Consortia leverage our adaptive designs and biomarker analytics.
Methodology Partners
Joseph Ibrahim, Michael Kosorok, Mike Love, Katie Hoadley, and collaborators extend the statistical toolkit.