Cell type Identification using Transcription factor Analysis and Chromatin accessibility
cellitac is a machine learning pipeline for classifying cell types from Single-Cell ATAC + RNA Multiome data using transcription factor analysis and chromatin accessibility features.
⚠️ Before running cellitac, please read the full system requirements and installation instructions below.
- OS: Linux or macOS (Windows not supported)
- Python: 3.9 – 3.12 (not 3.13+)
- R: 4.4.3 or higher
- Conda: required for bioconda installation (Miniconda or Anaconda)
conda install -c bioconda -c conda-forge cellitacpip install cellitacIf using PyPI, install R packages manually in R:
install.packages("Seurat")
install.packages("Signac")
install.packages("hdf5r")
install.packages("BiocManager")
BiocManager::install("SingleR")
BiocManager::install("celldex")
BiocManager::install("EnsDb.Hsapiens.v75")| Package | Version |
|---|---|
| Python | 3.11.13 |
| numpy | 2.4.2 |
| pandas | 2.3.3 |
| scikit-learn | 1.8.0 |
| xgboost | 3.2.0 |
| imbalanced-learn | 0.14.1 |
| matplotlib | 3.9.1 |
| seaborn | 0.13.2 |
| plotly | 6.5.2 |
| networkx | 3.6.1 |
| openpyxl | 3.1.5 |
| rpy2 | 3.5.11 |
For manual installation:
pip install -r Python_requirements.txtOr install individually:
pip install pandas==2.3.3 numpy==2.4.2 scikit-learn==1.8.0 xgboost==3.2.0 \
imbalanced-learn==0.14.1 matplotlib==3.9.1 seaborn==0.13.2 plotly==6.5.2 \
networkx==3.6.1 openpyxl==3.1.5 rpy2==3.5.11| Package | Source |
|---|---|
| R | 4.4.3 |
| Seurat | CRAN |
| Signac | CRAN |
| SingleR | Bioconductor |
| celldex | Bioconductor |
| EnsDb.Hsapiens.v75 | Bioconductor |
| hdf5r | CRAN |
| Matrix | CRAN |
For automated R installation, run install_R_packages.R in R or RStudio:
source("install_R_packages.R")cellitac --help
cellitac-preprocess --help
cellitac-model --help