Python framework for interpretable protein prediction
Project description
Welcome to the AAanalysis documentation
AAanalysis (Amino Acid analysis) is a Python framework for interpretable sequence-based protein prediction, providing the following algorithms:
AAclust: k-optimized clustering wrapper framework to select redundancy-reduced sets of numerical scales (e.g., amino acid scales)
CPP: Comparative Physicochemical Profiling, a feature engineering algorithm comparing two sets of protein sequences to identify the set of most distinctive features.
dPULearn: deterministic Positive-Unlabeled (PU) Learning algorithm to enable training on unbalanced and small datasets.
Moreover, AAanalysis provides functions for loading protein benchmark datasets (load_data), amino acid scale sets (load_scales), and their in-depth two-level classification (AAontology).
Install
AAanalysis can be installed either from PyPi or conda-forge:
pip install -u aaanalysis
or
conda install -c conda-forge aaanalysis
You can also use the GitHub repository and install dependencies using poetry:
git clone https://github.com/breimanntools/aaanalysis
cd aaanalysis
poetry install
Contributions
We welcome bug reports, feature requests, and code contributions.
Issues: Found a bug or have a feature idea? Please open an issue on our GitHub Repository.
Code: Want to contribute code? Submit a Pull Request.
Docs: See an error or room for improvement? Contributions to documentation are welcome.
For questions or suggestions, email stephanbreimann@gmail.com.
Citations
If you use ‘AAanalysis’ in your work, please cite the respective publication as follows:
- AAclust:
[Citation details and link if available]
- AAontology:
Breimann, Kamp, Steiner, Frishman (2023), AAontology: An ontology of amino acid scales for interpretable machine learning, bioRxiv.
- CPP:
[Citation details and link if available]
- dPULearn:
[Citation details and link if available]
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for aaanalysis-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 154869609b335f4631588fca42485fa525a01550970109fae5100d7b4a5827dc |
|
MD5 | fbe0a17de49c5477a8680013b89f4762 |
|
BLAKE2b-256 | cfa65f1e9c1448e66027200377f64f74825e333a64c448f34c3454a6799e38c5 |