https://github.com/chunribu/miidl
A Python package for biomarkers identification powered by interpretable deep learning
https://github.com/chunribu/miidl
bioinformatics biomarkers interpretable-deep-learning
Last synced: 5 months ago
JSON representation
A Python package for biomarkers identification powered by interpretable deep learning
- Host: GitHub
- URL: https://github.com/chunribu/miidl
- Owner: chunribu
- License: mit
- Created: 2021-08-16T01:33:32.000Z (almost 5 years ago)
- Default Branch: main
- Last Pushed: 2022-10-04T11:52:36.000Z (over 3 years ago)
- Last Synced: 2024-08-11T03:18:01.555Z (almost 2 years ago)
- Topics: bioinformatics, biomarkers, interpretable-deep-learning
- Language: Python
- Homepage: https://chunribu.github.io/miidl/
- Size: 444 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# [MIIDL](https://chunribu.github.io/miidl)
[](https://github.com/chunribu/) [](https://anaconda.org/bioconda/miidl) [](https://anaconda.org/bioconda/miidl) [](https://pypi.org/project/miidl/) [](https://anaconda.org/bioconda/miidl) [](https://arxiv.org/abs/2109.12204) [](https://anaconda.org/bioconda/miidl)
**MIIDL** `/ˈmaɪdəl/` is a Python package for microbial biomarkers identification powered by interpretable deep learning.
---
### [Getting Started](https://github.com/chunribu/miidl/blob/main/Tutorials.ipynb)
👋Welcome!
[🔗This guide](https://github.com/chunribu/miidl/blob/main/Tutorials.ipynb) will provide you with a specific example that using `miidl` to detect microbial biomarkers of colorectal cancer and predict clinical outcomes.
After that, you will learn how to use this tool properly.
---
### Installation
```bash
pip install miidl
```
or
```bash
conda install miidl captum -c pytorch -c conda-forge -c bioconda
```
---
### Features
+ One-stop profiling
+ Multiple strategies for biological data
+ More interpretable, not a "black box"
---
### Workflow
#### 1) Quality Control
The very first procedure is filtering features according to a threshold of observation (non-missing) rate (0.3 by default).
#### 2) Normalization
`miidl` offers plenty of normalization methods to transform data and make samples more comparable.
#### 3) Imputation
By default, this step is inactivated, as `miidl` is designed to solve problems including sparseness. But imputation can be useful in some cases. Commonly used methods are available if needed.
#### 4) Reshape
The pre-processed data also need to be zero-completed to a certain length, so that a CNN model can be applied.
#### 5) Modeling
A CNN classifier is trained for discrimination. [PyTorch](https://pytorch.org) is needed.
#### 6) Interpretation
[Captum](https://captum.ai/) is dedicated to model interpretability for PyTorch. This step depends heavily on captum.
---
### Contact
If you have further thoughts or queries, please feel free to email at jianjiang.bio@gmail.com or open an issue!
---
### Citation
```
@misc{jiang2021miidl,
title={MIIDL: a Python package for microbial biomarkers identification powered by interpretable deep learning},
author={Jian Jiang},
year={2021},
eprint={2109.12204},
archivePrefix={arXiv},
primaryClass={q-bio.QM}
}
```
---
### License
MIIDL is released under the [MIT license](https://github.com/chunribu/miidl/blob/main/LICENSE).