rCISSVAE: Clustering-Informed Shared-Structure VAE for Imputation

Implements the Clustering-Informed Shared-Structure Variational Autoencoder ('CISS-VAE'), a deep learning framework for missing data imputation introduced in Khadem Charvadeh et al. (2025) <doi:10.1002/sim.70335>. The model accommodates all three types of missing data mechanisms: Missing Completely At Random (MCAR), Missing At Random (MAR), and Missing Not At Random (MNAR). While it is particularly well-suited to MNAR scenarios, where missingness patterns carry informative signals, 'CISS-VAE' also functions effectively under MAR assumptions.

Version:	0.0.4
Depends:	R (≥ 4.2.0)
Imports:	reticulate, purrr, gtsummary, rlang, ComplexHeatmap
Suggests:	testthat (≥ 3.0.0), dplyr, knitr, rmarkdown, tidyverse, kableExtra, MASS, fastDummies, palmerpenguins, glue, withr, ggplot2
Published:	2026-01-23
DOI:	10.32614/CRAN.package.rCISSVAE (may not be active yet)
Author:	Yasin Khadem Charvadeh [aut], Kenneth Seier [aut], Katherine S. Panageas [aut], Danielle Vaithilingam [aut, cre], Mithat Gönen [aut], Yuan Chen [aut]
Maintainer:	Danielle Vaithilingam <vaithid1 at mskcc.org>
BugReports:	https://github.com/CISS-VAE/rCISS-VAE/issues
License:	MIT + file LICENSE
URL:	https://ciss-vae.github.io/rCISS-VAE/
NeedsCompilation:	no
CRAN checks:	rCISSVAE results

Documentation:

Reference manual:	rCISSVAE.html , rCISSVAE.pdf
Vignettes:	Handling Binary and Categorical Variables (source, R code) 'Masking certain entries from imputation model' (source, R code) "Saving and Using Saved Models" (source, R code) Using Optuna Dashboard with rCISSVAE (source, R code) Summary Functions (source, R code) rCISSVAE Vignette (source, R code) Manual Virtual Environment Setup Tutorial (source, R code)

Downloads:

Package source:	rCISSVAE_0.0.4.tar.gz
Windows binaries:	r-devel: rCISSVAE_0.0.4.zip, r-release: not available, r-oldrel: not available
macOS binaries:	r-release (arm64): rCISSVAE_0.0.4.tgz, r-oldrel (arm64): rCISSVAE_0.0.4.tgz, r-release (x86_64): rCISSVAE_0.0.4.tgz, r-oldrel (x86_64): rCISSVAE_0.0.4.tgz

Linking:

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