| Name | impeller JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | https://github.com/aicb-ZhangLabs/Impeller |
| Summary | Impeller is a package for spatial transcriptomics imputation using path-based graph neural networks. |
| upload_time | 2024-08-16 05:40:16 |
| maintainer | None |
| docs_url | None |
| author | Ziheng Duan |
| requires_python | >=3.6 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Impeller
Impeller is a sophisticated package designed for imputing spatial transcriptomics data using path-based graph neural networks. It supports a variety of datasets and integrates powerful processing and machine learning techniques.
## Installation
Install the Impeller package using pip with the following command:
```bash
pip install Impeller
```
## Usage
The Impeller package simplifies the process of downloading, processing, and training models on spatial transcriptomics data. Follow the steps below to utilize the package effectively.
### Download Example Data
The package supports three datasets: '10XVisium', 'Stereoseq', and 'SlideseqV2'. Begin by downloading the dataset of your choice:
```python
from Impeller import download_example_data
# Replace '10XVisium' with 'Stereoseq' or 'SlideseqV2' to download other datasets
download_example_data('10XVisium')
```
### Load and Process Data
Once the data is downloaded, you can load and process it for analysis:
```python
from Impeller import load_and_process_example_data
# Ensure to specify the same dataset you downloaded
data, val_mask, test_mask, x, original_x = load_and_process_example_data('10XVisium')
```
### Train Model
After loading and processing the data, you can initialize the model's arguments and start training:
```python
from Impeller import create_args, train
args = create_args()
test_l1_distance, test_cosine_sim, test_rmse = train(args, data, val_mask, test_mask, x, original_x)
print(f"Final L1 distance: {test_l1_distance}, Cosine similarity: {test_cosine_sim}, RMSE: {test_rmse}.")
```
### Only Inference
You can use Impeller to perform inference on your custom data (you'll need to provide a mask indicating which genes in which cells you want to impute). Below is a demo for inference only (replace the following adata and inference_mask with your own data):
```python
from Impeller import load_example_data, process_inference_data
adata, _, inference_mask = load_example_data(example_dataset = '10XVisium')
data = process_inference_data(adata)
from Impeller import inference
Impeller_imputed_data = inference(args, data, inference_mask)
```
### Naive Baseline
We also provide a simple baseline implementation using K-Nearest Neighbors (KNN):
```python
from Impeller import SpatialKNNImputer
knn_imputer = SpatialKNNImputer(adata, n_neighbors=5)
knn_imputed_data = knn_imputer.impute(inference_mask)
```
Raw data
{
"_id": null,
"home_page": "https://github.com/aicb-ZhangLabs/Impeller",
"name": "impeller",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": null,
"author": "Ziheng Duan",
"author_email": "duanziheng1206@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/78/4d/466b5a7fbd271f4fdb65e94d8699804ad0be61df4e998b2f936196c9e803/impeller-0.1.2.tar.gz",
"platform": null,
"description": "# Impeller\n\nImpeller is a sophisticated package designed for imputing spatial transcriptomics data using path-based graph neural networks. It supports a variety of datasets and integrates powerful processing and machine learning techniques.\n\n## Installation\n\nInstall the Impeller package using pip with the following command:\n\n```bash\npip install Impeller\n```\n\n## Usage\nThe Impeller package simplifies the process of downloading, processing, and training models on spatial transcriptomics data. Follow the steps below to utilize the package effectively.\n\n### Download Example Data\nThe package supports three datasets: '10XVisium', 'Stereoseq', and 'SlideseqV2'. Begin by downloading the dataset of your choice:\n\n```python\nfrom Impeller import download_example_data\n\n# Replace '10XVisium' with 'Stereoseq' or 'SlideseqV2' to download other datasets\ndownload_example_data('10XVisium')\n```\n\n### Load and Process Data\nOnce the data is downloaded, you can load and process it for analysis:\n```python \nfrom Impeller import load_and_process_example_data\n\n# Ensure to specify the same dataset you downloaded\ndata, val_mask, test_mask, x, original_x = load_and_process_example_data('10XVisium')\n```\n\n### Train Model\nAfter loading and processing the data, you can initialize the model's arguments and start training:\n```python \nfrom Impeller import create_args, train\n\nargs = create_args()\ntest_l1_distance, test_cosine_sim, test_rmse = train(args, data, val_mask, test_mask, x, original_x)\nprint(f\"Final L1 distance: {test_l1_distance}, Cosine similarity: {test_cosine_sim}, RMSE: {test_rmse}.\")\n```\n\n### Only Inference\nYou can use Impeller to perform inference on your custom data (you'll need to provide a mask indicating which genes in which cells you want to impute). Below is a demo for inference only (replace the following adata and inference_mask with your own data):\n```python \nfrom Impeller import load_example_data, process_inference_data\n\nadata, _, inference_mask = load_example_data(example_dataset = '10XVisium')\ndata = process_inference_data(adata)\n\nfrom Impeller import inference\n\nImpeller_imputed_data = inference(args, data, inference_mask)\n```\n\n### Naive Baseline\nWe also provide a simple baseline implementation using K-Nearest Neighbors (KNN):\n```python \nfrom Impeller import SpatialKNNImputer\n\nknn_imputer = SpatialKNNImputer(adata, n_neighbors=5)\nknn_imputed_data = knn_imputer.impute(inference_mask)\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "Impeller is a package for spatial transcriptomics imputation using path-based graph neural networks.",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/aicb-ZhangLabs/Impeller"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f22986aabdf17a3891a9e541ff64619926b47b5dd982f49c9d740b1af62b2e74",
"md5": "2c8a2121768d480d6dcd6efd663964ea",
"sha256": "178f56f676a1786a83a1c227b5e88068b433971baeaa60b2c452363c54079147"
},
"downloads": -1,
"filename": "impeller-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2c8a2121768d480d6dcd6efd663964ea",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 10712,
"upload_time": "2024-08-16T05:40:14",
"upload_time_iso_8601": "2024-08-16T05:40:14.115239Z",
"url": "https://files.pythonhosted.org/packages/f2/29/86aabdf17a3891a9e541ff64619926b47b5dd982f49c9d740b1af62b2e74/impeller-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "784d466b5a7fbd271f4fdb65e94d8699804ad0be61df4e998b2f936196c9e803",
"md5": "00abd04c4d2cdeff1d84bb3221e7edd6",
"sha256": "51236702e4d73383333951ff6c4031085fce7c74b4cf115e2f49bd13494dbb74"
},
"downloads": -1,
"filename": "impeller-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "00abd04c4d2cdeff1d84bb3221e7edd6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 8759,
"upload_time": "2024-08-16T05:40:16",
"upload_time_iso_8601": "2024-08-16T05:40:16.308812Z",
"url": "https://files.pythonhosted.org/packages/78/4d/466b5a7fbd271f4fdb65e94d8699804ad0be61df4e998b2f936196c9e803/impeller-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-16 05:40:16",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "aicb-ZhangLabs",
"github_project": "Impeller",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "impeller"
}
