dicepro: Semi-Supervised Deconvolution of Bulk RNA-Seq Data with Hyperparameter Optimization

Performs semi-supervised deconvolution of bulk RNA sequencing (RNA-seq) data. Known cell-type proportions are estimated using supervised methods – 'CIBERSORTx' (CSx), 'CIBERSORT' (CS), 'FARDEEP' (Fast And Robust DEconvolution of Expression Profiles), and 'DCQ' (Digital Cell Quantifier) – while unknown components are inferred using non-negative matrix factorization ('NMF') with limited-memory Broyden-Fletcher-Goldfarb-Shanno with bounds ('L-BFGS-B') optimization. Hyperparameters are selected automatically using a Pareto-frontier-based approach with knee-point detection, allowing application when the reference signature matrix is incomplete. More details about 'DICEpro' can be found in Ba et al. (2026) <doi:10.64898/2026.06.17.732876>.

Version: 1.0.2
Depends: R (≥ 4.1.0)
Imports: Rcpp (≥ 1.0.12), lbfgsb3c, KraljicMatrix, ggplot2, patchwork, FARDEEP, ComICS, lme4, e1071, preprocessCore, parallel
LinkingTo: Rcpp (≥ 1.0.12), RcppEigen
Suggests: knitr, rmarkdown, testthat (≥ 3.0.0)
Published: 2026-06-30
DOI: 10.32614/CRAN.package.dicepro (may not be active yet)
Author: Kalidou BA [aut, cre], Boris P. Hejblum [aut]
Maintainer: Kalidou BA <sistm.soft.maintain at gmail.com>
BugReports: https://github.com/kalidouBA/dicepro/issues
License: MIT + file LICENSE
URL: https://github.com/kalidouBA/dicepro
NeedsCompilation: yes
Materials: README, NEWS
CRAN checks: dicepro results

Documentation:

Reference manual: dicepro.html , dicepro.pdf
Vignettes: dicepro - Hyperparameter Search Space Visualization (source, R code)
dicepro - Real Data Workflow (BlueCode + CellMixtures) (source, R code)
dicepro - Simulated Data Workflow (source, R code)

Downloads:

Package source: dicepro_1.0.2.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): dicepro_1.0.2.tgz, r-oldrel (x86_64): not available

Linking:

Please use the canonical form https://CRAN.R-project.org/package=dicepro to link to this page.