Skip to contents

Getting Started with CellTFusion

CellTFusion.Rmd

Overview

CellTFusion integrates immune cell-type deconvolution with transcription factor (TF)–gene regulatory networks to characterize immune cell states in the tumor microenvironment from bulk RNA-seq data.

The pipeline takes raw counts and optional clinical metadata as input, and produces cell group scores — biologically coherent clusters of samples defined by shared TF activity and cell-type composition patterns.

Pipeline steps

Step Function Article
Cell-type deconvolution multideconv::compute.deconvolution() Feature Computation
TF activity inference compute.TFs.activity() Feature Computation
TF module construction compute.WTCNA() Feature Computation
Pathway activity scoring compute.pathway.activity() Feature Computation
Cell group construction construct_cell_groups() Cell Group Construction
Statistical association scores.stat.analysis() Statistical Analysis
Full pipeline (one call) CellTFusion() One-step Pipeline
ML model training pipeML::compute_features.training.ML() Machine Learning

Quick start

Load the pre-packaged example data and run the full pipeline in one call:

raw.counts <- CellTFusion::raw.counts.tuto
traitdata  <- CellTFusion::traitdata.tuto
res <- CellTFusion(
  raw.counts     = raw.counts,
  normalized     = TRUE,
  coldata        = traitdata,
  trait          = "Best.Confirmed.Overall.Response",
  trait.positive = "CR",
  deconv_methods = c("Quantiseq", "Epidish"),
  file_name      = "TestRun",
  corr           = 0.7,
  pval           = 0.05,
  return         = FALSE
)

For a step-by-step walkthrough of each stage, follow the articles listed in the table above.

Installation 

# Install from GitHub
remotes::install_github("VeraPancaldiLab/CellTFusion")

References