# SEE
## Installation
```
conda create -n scce python=3.8 libffi=3.3
pip install scce
```
## Paper Content
### Get the code
```
git clone https://github.com/LMH0066/SEE.git --depth=1
```
### Prepare the environment
The see environment can be installed via conda:
```
conda env create -f environment.yml
```
### Directory structure
```
.
|-- script # Obtain training data through public data
|-- train # Main code for training model
|-- analyse # Experiments
| |-- 3DMax #
| |-- AD # Case analysis of Alzheimer's disease
| |-- Data Analysis(PDGFRA).ipynb # Case study of raw data
| |-- analyse_util.py # Some common functions used in the analysis process
| |-- bulk # Case analysis of bulk RNA
| |-- loss-effectiveness # FocalLoss effectiveness
| |-- quality # Method evaluation
| |-- related-genes # Importance analysis of input features
| \`-- velocity # Case analysis of pseudo-time
|-- environment.yml
\`-- README.md
```
### Train
#### train
```
CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --nproc_per_node=1 train_model.py -t /folder/to/train_file -e /folder/to/eval_file -o /folder/to/output_folder -g gene_name
```
#### validate
```
python validate.py -e /folder/to/eval_file -m /path/to/model -g gene_name -o /folder/to/output_file -s output_size
```
### Analyse
All the analysis results in the paper can be found in the code under the 'analyse' folder.
Raw data
{
"_id": null,
"home_page": "https://github.com/LMH0066/SEE",
"name": "scce",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<4.0",
"maintainer_email": "",
"keywords": "bioinformatics,deep-learning,single-cell",
"author": "liminghong.dev",
"author_email": "lmh0066@outlook.com",
"download_url": "https://files.pythonhosted.org/packages/b7/36/159f01f3bb82cc30c5c617848db128cf54b694a3860274f4ae2758c3ade8/scce-0.1.2.tar.gz",
"platform": null,
"description": "# SEE\n## Installation\n```\nconda create -n scce python=3.8 libffi=3.3\npip install scce\n```\n## Paper Content\n### Get the code\n```\ngit clone https://github.com/LMH0066/SEE.git --depth=1\n```\n### Prepare the environment\nThe see environment can be installed via conda:\n```\nconda env create -f environment.yml\n```\n### Directory structure\n```\n.\n|-- script # Obtain training data through public data\n|-- train # Main code for training model\n|-- analyse # Experiments\n| |-- 3DMax # \n| |-- AD # Case analysis of Alzheimer's disease\n| |-- Data Analysis(PDGFRA).ipynb # Case study of raw data\n| |-- analyse_util.py # Some common functions used in the analysis process\n| |-- bulk # Case analysis of bulk RNA\n| |-- loss-effectiveness # FocalLoss effectiveness\n| |-- quality # Method evaluation\n| |-- related-genes # Importance analysis of input features\n| \\`-- velocity # Case analysis of pseudo-time\n|-- environment.yml\n\\`-- README.md\n```\n### Train\n#### train\n```\nCUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --nproc_per_node=1 train_model.py -t /folder/to/train_file -e /folder/to/eval_file -o /folder/to/output_folder -g gene_name\n```\n#### validate\n```\npython validate.py -e /folder/to/eval_file -m /path/to/model -g gene_name -o /folder/to/output_file -s output_size\n```\n### Analyse\nAll the analysis results in the paper can be found in the code under the 'analyse' folder.\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "a Single-cell method for predicting Chromatin Conformation based on gene Expression",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/LMH0066/SEE",
"Repository": "https://github.com/LMH0066/SEE"
},
"split_keywords": [
"bioinformatics",
"deep-learning",
"single-cell"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "1e33a891986bf423efd310dd6fcf9c6356f9b446bf1d92d1792002b7f40399c1",
"md5": "31448a664126a1d57adc67cf47b15b80",
"sha256": "4b026796095b66999ef8debfaf7a09df332d88b1621801f53a78cd20d43e687d"
},
"downloads": -1,
"filename": "scce-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "31448a664126a1d57adc67cf47b15b80",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<4.0",
"size": 23634,
"upload_time": "2023-07-24T09:48:39",
"upload_time_iso_8601": "2023-07-24T09:48:39.199549Z",
"url": "https://files.pythonhosted.org/packages/1e/33/a891986bf423efd310dd6fcf9c6356f9b446bf1d92d1792002b7f40399c1/scce-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b736159f01f3bb82cc30c5c617848db128cf54b694a3860274f4ae2758c3ade8",
"md5": "4d33c57de77a5cf177511d307cc3f72e",
"sha256": "b98b91b90b67d6070399ada2228cfaca7474af4ea75116c8f1c798b117ad8823"
},
"downloads": -1,
"filename": "scce-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "4d33c57de77a5cf177511d307cc3f72e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<4.0",
"size": 19753,
"upload_time": "2023-07-24T09:48:41",
"upload_time_iso_8601": "2023-07-24T09:48:41.442433Z",
"url": "https://files.pythonhosted.org/packages/b7/36/159f01f3bb82cc30c5c617848db128cf54b694a3860274f4ae2758c3ade8/scce-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-07-24 09:48:41",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "LMH0066",
"github_project": "SEE",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "scce"
}