Clinical decision-support tools, R packages, and legacy utilities developed by the lab. Each card links to its repository, distribution, and the paper that describes it.

Decision Support Tools & Patents

PurIST Pancreatic Classifier

Single-sample PDAC subtype assay used in cooperative trials.

  • Clinical Tool
  • 3 patents
  • Active
  • US 11,053,550 (Jul 2021) — Gene-expression based subtyping of PDAC
  • US App. 17/336,600 (Apr 2022) — Methods for prognostic / diagnostic subtyping
  • US 12,000,003 (Jun 2024) — Platform-independent single-sample classifier
  • Rashid et al., Clin Cancer Res (2020)
  • Li et al., J Mol Diagnostics (2024)

R Packages

BATON

Bayesian adaptive trial operating-characteristic tuning for platform trials.

  • In Development
  • 2025

evolveTrial

Adaptive monitoring and simulation tools for evolutionary clinical trial designs.

  • In Development
  • 2025

deSurv

De-biased survival estimators pairing flexible ML bases with biomarker-rich trial data.

  • In Development
  • 2025

dlglm

Deeply learned GLMs handling non-ignorable missingness.

  • GitHub
  • 2024
  • Lim et al., JCGS (2024)

NIMIWAE

Variational autoencoder for non-ignorable missing data.

  • GitHub
  • 2024
  • Lim et al., Stat Biopharm Res (2024)

glmmPen

Penalized GLMM selection for biomarker discovery.

  • CRAN
  • 2024
  • Heiling et al., The R Journal (2024)

CompDTUReg

Differential transcript usage with quantification uncertainty.

  • GitHub
  • 2023
  • Young et al., Biostatistics (2023)

epigraHMM

Multi-sample enrichment detection for ChIP/ATAC.

  • Bioconductor
  • 2022
  • Baldoni et al., Biometrics (2022)

FSCseq

Model-based feature selection + clustering for RNA-seq.

  • GitHub
  • 2021
  • Lim et al., Ann Appl Stat (2021)

Legacy & Specialized Tools

  • mixNBHMM — Differential peak calling for multi-condition epigenomic data. (GitHub)
  • ZIMHMM — Consensus enrichment calling across ChIP-seq replicates. (GitHub)
  • ZINBA — Zero-inflated negative binomial algorithm detecting NGS-enriched regions. (Archived; formerly hosted on Google Code)
  • hmmcov — HMM / AR-HMM procedures with variable selection for epigenetic enrichment. (Archived; formerly hosted on Google Code)
  • BASeG — Bivariate association studies linking expression and epigenetic marks with shared genetics. (Rashid et al., Ann Appl Stat, 2016)

Code Repositories

All software is actively maintained on GitHub. Contributions, issues, and feature requests are welcome, and the full repository + contributor stats live on the Repositories page.

Collaborative Development

Many packages are developed in close collaboration with lab members and trainees:

  • Hillary Heiling: glmmPen lead developer
  • David Lim: dlglm, NIMIWAE, FSCseq lead developer
  • Pedro Baldoni: epigraHMM, mixNBHMM, ZIMHMM lead developer
  • Scott Van Buren: CompDTUReg lead developer
  • Amber Young: CompDTUReg co-developer; current PhD student working on semi-supervised matrix factorization for PDAC subtyping

Support & Contact

For technical support, please open an issue on the relevant GitHub repository. For collaboration inquiries, contact naim@unc.edu.