Package: TorchDecon
Type: Package
Title: Deep Learning-Based Cell Type Deconvolution Using torch
Version: 1.0.0
Date: 2026-01-26
Authors@R: person("Zaoqu", "Liu", email = "liuzaoqu@163.com", role = c("aut", "cre"), comment = c(ORCID = "0000-0002-0452-742X"))
Description: A deep neural network ensemble approach for cell type
        deconvolution of bulk RNA-seq data. TorchDecon uses simulated
        bulk samples generated from single-cell RNA-seq data to train
        deep neural networks that predict cell type fractions. This
        package is an R-native implementation based on the Scaden
        algorithm, built on the torch framework (LibTorch C++ backend)
        for GPU acceleration and cross-platform compatibility.
        Seamlessly integrates with Seurat objects (v4 and v5
        compatible).
License: MIT + file LICENSE
URL: https://github.com/Zaoqu-Liu/TorchDecon
BugReports: https://github.com/Zaoqu-Liu/TorchDecon/issues
Encoding: UTF-8
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.3.3
Depends: R (>= 4.0.0)
Imports: torch (>= 0.9.0), Seurat (>= 4.0.0), SeuratObject (>= 4.0.0),
        Matrix, data.table, future, future.apply, progressr, cli,
        methods, stats, utils
Suggests: testthat (>= 3.0.0), knitr, rmarkdown, ggplot2, Rcpp
Config/testthat/edition: 3
VignetteBuilder: knitr
Config/pak/sysreqs: cmake libglpk-dev make libicu-dev libpng-dev
        libuv1-dev libxml2-dev libssl-dev python3 zlib1g-dev
Repository: https://zaoqu-liu.r-universe.dev
Date/Publication: 2026-01-26 02:33:01 UTC
RemoteUrl: https://github.com/Zaoqu-Liu/TorchDecon
RemoteRef: main
RemoteSha: 139bac3eecffa73b3f979e2a96463fa13f6f05f6
NeedsCompilation: no
Packaged: 2026-07-03 15:56:06 UTC; root
Author: Zaoqu Liu [aut, cre] (ORCID: <https://orcid.org/0000-0002-0452-742X>)
Maintainer: Zaoqu Liu <liuzaoqu@163.com>