Metadata-Version: 2.1
Name: scMDCF
Version: 0.0.2
Summary: scMDCF Enables Cross-modality Cell Heterogeneity Elucidation and Interaction between Multiomic Profiles at Single-cell Resolution
Home-page: https://github.com/DARKpmm/scMDCF
Author: Yue Cheng
Author-email: chengyue22@mails.jlu.edu.cn
Classifier: Programming Language :: Python :: 3.9
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Description-Content-Type: text/markdown
Requires-Dist: anndata ==0.10.5.post1
Requires-Dist: array-api-compat ==1.4.1
Requires-Dist: contourpy ==1.2.0
Requires-Dist: cycler ==0.12.1
Requires-Dist: exceptiongroup ==1.2.0
Requires-Dist: filelock ==3.13.1
Requires-Dist: fonttools ==4.49.0
Requires-Dist: fsspec ==2024.2.0
Requires-Dist: get-annotations ==0.1.2
Requires-Dist: h5py ==3.10.0
Requires-Dist: importlib-resources ==6.1.1
Requires-Dist: Jinja2 ==3.1.3
Requires-Dist: joblib ==1.3.2
Requires-Dist: kiwisolver ==1.4.5
Requires-Dist: llvmlite ==0.42.0
Requires-Dist: MarkupSafe ==2.1.5
Requires-Dist: matplotlib ==3.8.3
Requires-Dist: mpmath ==1.3.0
Requires-Dist: natsort ==8.4.0
Requires-Dist: networkx ==3.2.1
Requires-Dist: numba ==0.59.0
Requires-Dist: numpy ==1.26.4
Requires-Dist: nvidia-cublas-cu12 ==12.1.3.1
Requires-Dist: nvidia-cuda-cupti-cu12 ==12.1.105
Requires-Dist: nvidia-cuda-nvrtc-cu12 ==12.1.105
Requires-Dist: nvidia-cuda-runtime-cu12 ==12.1.105
Requires-Dist: nvidia-cudnn-cu12 ==8.9.2.26
Requires-Dist: nvidia-cufft-cu12 ==11.0.2.54
Requires-Dist: nvidia-curand-cu12 ==10.3.2.106
Requires-Dist: nvidia-cusolver-cu12 ==11.4.5.107
Requires-Dist: nvidia-cusparse-cu12 ==12.1.0.106
Requires-Dist: nvidia-nccl-cu12 ==2.19.3
Requires-Dist: nvidia-nvjitlink-cu12 ==12.3.101
Requires-Dist: nvidia-nvtx-cu12 ==12.1.105
Requires-Dist: packaging ==23.2
Requires-Dist: pandas ==2.2.1
Requires-Dist: patsy ==0.5.6
Requires-Dist: pillow ==10.2.0
Requires-Dist: pynndescent ==0.5.11
Requires-Dist: pyparsing ==3.1.1
Requires-Dist: python-dateutil ==2.8.2
Requires-Dist: pytz ==2024.1
Requires-Dist: scanpy ==1.9.8
Requires-Dist: scikit-learn ==1.4.1.post1
Requires-Dist: scipy ==1.12.0
Requires-Dist: seaborn ==0.13.2
Requires-Dist: session-info ==1.0.0
Requires-Dist: six ==1.16.0
Requires-Dist: statsmodels ==0.14.1
Requires-Dist: stdlib-list ==0.10.0
Requires-Dist: sympy ==1.12
Requires-Dist: threadpoolctl ==3.3.0
Requires-Dist: torch ==2.2.1
Requires-Dist: tqdm ==4.66.2
Requires-Dist: triton ==2.2.0
Requires-Dist: typing-extensions ==4.9.0
Requires-Dist: tzdata ==2024.1
Requires-Dist: umap-learn ==0.5.5
Requires-Dist: zipp ==3.17.0

# scMDCF
`scMDCF` is a python package containing tools for clustering single cell multi-omics data based on cross-modality contrastive learning to learn the common latent representation and assign clustering.
# Overview
Single-cell multi-omics (scMulti-omics) technologies enable simultaneous measurements of diverse modalities within individual cells and have the potential to comprehensively unravel cellular functions and interactions. Despite this promise, the complexity, high-dimensionality, and heterogeneity of the datasets pose significant challenges to integrative analysis. Here, we develop a single-cell multi-omics deep learning model (scMDCF) based on contrastive learning that is designed to efficiently characterize different types of omics data and capture potential features in the data through deep embedding for a complete and integrated analysis. In scMDCF, we propose a cross-modality contrastive learning module to unify representations from various omics types to ensure consistency, while the cross-modality feature fusion module utilizes conditional entropy to preserve the heterogeneity information. Extensive empirical studies have confirmed that scMDCF outperforms other state-of-the-art scMulti-omics models across various types of scMulti-omics data. In particular, scMDCF demonstrates advanced capability in determining the vital cell-type specific peak-gene associations and cis-regulatory elements from SNARE-seq data as well as surmizing immune regulation within cellular differentiation pathways from CITE-seq data. In addition, we demonstrate that in the post-SARS-CoV-2 vaccination dataset, scMDCF successfully provides annotations on the specific vaccine-induced B cell subpopulations in each modality and reveals the dynamic interactions and regulatory mechanisms within the post-vaccination immune system after vaccination.
![The framework plot of scMDCF]("https://github.com/DARKpmm/scMDCF/blob/main/scMDCF.png")
# System Requirements
## Hardware requirements
`scMDCF` package requires only a standard computer with enough RAM to support the in-memory operations.
## Software requirements
### OS requirements
This package is supported for *Linux*. The package has been tested on the following systems:
* Linux: Ubuntu 18.04
### Python Dependencies
`scMDCF` mainly depends on the Python scientific stack.
    numpy
    pytorch
    scanpy
    pandas
    scikit-learn
For specific setting, please see <a href="https://github.com/DARKpmm/scMDCF/blob/main/requirements.txt">requirements</a>.
# Installation Guide
## Install from PyPi
    conda create -n scMDCF_env python=3.9.16
    conda activate scMDCF_env
    pip install -r requirements.txt
# Usage
`scMDCF` is a deep embedding learning method for single-cell multi-omics data clustering, which can be used to:
* CITE-seq dataset clustering. The example can be seen in the <a href="https://github.com/DARKpmm/scMDCF/blob/main/scMDCF/main_CITE.py">main_CITE.py</a>
* SNARE-seq (paired RNA-seq and ATAC-seq) dataset clustering. The example can be seen in the <a href="https://github.com/DARKpmm/scMDCF/blob/main/scMDCF/main_SNARE.py">main_SNARE.py</a>
* Analysis of the post-SARS-CoV-2 vaccination CITE-seq dataset. The example can be seen in the 
* Analysis of the SNARE-seq dataset. The example can be seen in the
# Data Availability
The datasets we used can be download in
# License
This project is covered under the **MIT License**.
