# scCross
A Deep Learning-Based Model for the integration, cross-dataset cross-modality generation, self augmentation and matched multi-omics simulation of single-cell multi-omics data. Our model excels at maintaining in-silico perturbations during cross-modality generation and harnessing these perturbations to identify key genes.
For detailed instructions, comprehensive documentation, and helpful tutorials, please visit:
* [https://sccross.readthedocs.io](https://sccross.readthedocs.io/en/latest/)
## Overview
<img title="Model Overview" alt="Alt text" src="/figures/main.png">
Single-cell multi-omics provides deep biological insights, but data scarcity and modality integration remain significant challenges. We introduce scCross, harnessing variational autoencoder and generative adversarial network (VAE-GAN) principles, meticulously designed to integrate diverse single-cell multi-omics data. Incorporating biological priors, scCross adeptly aligns modalities with enhanced relevance. Its standout feature is generating cross-modality single-cell data and in-silico perturbations, enabling deeper cellular state examinations and drug explorations. Applied to dual and triple-omics datasets, scCross maps data into a unified latent space, surpassing existing methods. By addressing data limitations and offering novel biological insights, scCross promises to advance single-cell research and therapeutic discovery.
## Key Capabilities
1. Combine more than three single-cell multi-omics datasets, whether they are matched or unmatched, into a unified latent space. This space can be used for downstream analysis, even when dealing with over 4 million cells of varying types.
2. Generate cross-compatible single-cell data between two or more different omics. Trained and tested on independent referenced multi-omics datasets is also feasible.
3. Augment single-cell omics data through self-improvement techniques.
4. Simulate single-cell multi-omics data that match a specific cellular state, irrespective of the type and quantity of omics data involved.
5. Accurately identify key genes by comparing two different cell clusters using in-silico perturbation methods.
6. Maintain genomic integrity during omics perturbations and cross-generations effectively.
## Installation
You may install scCross by the following command:
```
pip install sccross
```
## Example workthroughs
Example workthroughs for each dataset in our study can be found in the [examples](https://github.com/mcgilldinglab/scCross/tree/main/examples) forder.
## Codeocean
We employ [codeocean](https://codeocean.com/capsule/4757520/tree/v1) reproducible platform to help you get into our codes.
Raw data
{
"_id": null,
"home_page": null,
"name": "sccross",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": "bioinformatics, deep-learning, single-cell, single-cell-multiomics",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/72/1a/c9fef9f1417afd624e7865d61c19efca9da5eed26967519f0ec600d508ea/sccross-1.0.5.3.tar.gz",
"platform": null,
"description": "# scCross\nA Deep Learning-Based Model for the integration, cross-dataset cross-modality generation, self augmentation and matched multi-omics simulation of single-cell multi-omics data. Our model excels at maintaining in-silico perturbations during cross-modality generation and harnessing these perturbations to identify key genes.\n\nFor detailed instructions, comprehensive documentation, and helpful tutorials, please visit:\n \n* [https://sccross.readthedocs.io](https://sccross.readthedocs.io/en/latest/)\n\n\n## Overview\n<img title=\"Model Overview\" alt=\"Alt text\" src=\"/figures/main.png\">\nSingle-cell multi-omics provides deep biological insights, but data scarcity and modality integration remain significant challenges. We introduce scCross, harnessing variational autoencoder and generative adversarial network (VAE-GAN) principles, meticulously designed to integrate diverse single-cell multi-omics data. Incorporating biological priors, scCross adeptly aligns modalities with enhanced relevance. Its standout feature is generating cross-modality single-cell data and in-silico perturbations, enabling deeper cellular state examinations and drug explorations. Applied to dual and triple-omics datasets, scCross maps data into a unified latent space, surpassing existing methods. By addressing data limitations and offering novel biological insights, scCross promises to advance single-cell research and therapeutic discovery.\n\n## Key Capabilities\n\n1. Combine more than three single-cell multi-omics datasets, whether they are matched or unmatched, into a unified latent space. This space can be used for downstream analysis, even when dealing with over 4 million cells of varying types.\n\n2. Generate cross-compatible single-cell data between two or more different omics. Trained and tested on independent referenced multi-omics datasets is also feasible.\n\n3. Augment single-cell omics data through self-improvement techniques.\n\n4. Simulate single-cell multi-omics data that match a specific cellular state, irrespective of the type and quantity of omics data involved.\n\n5. Accurately identify key genes by comparing two different cell clusters using in-silico perturbation methods.\n\n6. Maintain genomic integrity during omics perturbations and cross-generations effectively.\n\n\n\n\n\n\n\n## Installation\n\n\nYou may install scCross by the following command:\n\n```\npip install sccross\n```\n\n## Example workthroughs\nExample workthroughs for each dataset in our study can be found in the [examples](https://github.com/mcgilldinglab/scCross/tree/main/examples) forder.\n\n## Codeocean\n\nWe employ [codeocean](https://codeocean.com/capsule/4757520/tree/v1) reproducible platform to help you get into our codes.\n",
"bugtrack_url": null,
"license": null,
"summary": "Single cell multi-omics cross modal generation, multi-omics simulation and perturbation",
"version": "1.0.5.3",
"project_urls": {
"Github": "https://github.com/Xiuhui-Yang/scCross"
},
"split_keywords": [
"bioinformatics",
" deep-learning",
" single-cell",
" single-cell-multiomics"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "40fd5caa7bae96d050d696de27ee87ca140f36adfb7f8f73f7e6ba36ae4d0cb1",
"md5": "91191ce86436f9665c4516edd0365b4f",
"sha256": "757ff56af026c23c4a735e3c7039025027c2cbc9b796e0ad619e15d95c103798"
},
"downloads": -1,
"filename": "sccross-1.0.5.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "91191ce86436f9665c4516edd0365b4f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 47779,
"upload_time": "2024-11-12T06:08:48",
"upload_time_iso_8601": "2024-11-12T06:08:48.002757Z",
"url": "https://files.pythonhosted.org/packages/40/fd/5caa7bae96d050d696de27ee87ca140f36adfb7f8f73f7e6ba36ae4d0cb1/sccross-1.0.5.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "721ac9fef9f1417afd624e7865d61c19efca9da5eed26967519f0ec600d508ea",
"md5": "2225830a1d108615aaa29d06ac7a188b",
"sha256": "371d4162852c939347ef0961e4fb745083ad55fc86bac7b36b2d209f8c1f96e5"
},
"downloads": -1,
"filename": "sccross-1.0.5.3.tar.gz",
"has_sig": false,
"md5_digest": "2225830a1d108615aaa29d06ac7a188b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 45252,
"upload_time": "2024-11-12T06:08:48",
"upload_time_iso_8601": "2024-11-12T06:08:48.978741Z",
"url": "https://files.pythonhosted.org/packages/72/1a/c9fef9f1417afd624e7865d61c19efca9da5eed26967519f0ec600d508ea/sccross-1.0.5.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-12 06:08:48",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Xiuhui-Yang",
"github_project": "scCross",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "sccross"
}
JSON
