Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/aqlaboratory/hsm
Code associated with "Biophysical prediction of protein-peptide interactions and signaling networks using machine learning."
https://github.com/aqlaboratory/hsm
Last synced: 2 months ago
JSON representation
Code associated with "Biophysical prediction of protein-peptide interactions and signaling networks using machine learning."
- Host: GitHub
- URL: https://github.com/aqlaboratory/hsm
- Owner: aqlaboratory
- License: mit
- Created: 2019-10-24T22:48:58.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2024-04-26T18:13:25.000Z (9 months ago)
- Last Synced: 2024-08-09T13:20:28.305Z (5 months ago)
- Language: Jupyter Notebook
- Homepage: https://proteinpeptide.io
- Size: 31 MB
- Stars: 67
- Watchers: 6
- Forks: 21
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- StarryDivineSky - aqlaboratory/hsm - 肽相互作用和信号网络进行生物物理预测 (药物-靶标 药物-药物 化合物-蛋白质 相互作用 / 网络服务_其他)
README
# hsm - Biophysical prediction of protein-peptide interactions and signaling networks using machine learning.
This repository implements the hierarchical statistical mechanical (HSM) model described in the paper [Biophysical prediction of protein-peptide interactions and signaling networks using machine learning](https://doi.org/10.1038/s41592-019-0687-1).
An **associated website** is available at [proteinpeptide.io](https://proteinpeptide.io). The website is built to facilitate interactions with results from the model including: (1) specific domain-peptide and protein-protein predictions, (2) the resulting networks, and (3) structures colored using the inferred energy functions from the model. Code for the website is available via the parallel repo: [aqlaboratory/hsm-web](https://github.com/aqlaboratory/hsm-web). Note that the results on the website were obtained using an [old model](#model-updates).
This file documents how this package might be [used](#usage), the [location of associated data](#data), and [other metadata](#reference).
## Usage
The model was implemented in Python (>= 3.5) primarily using TensorFlow (>= 1.14) ([Software Requirements](#requirements)). To work with this repository, either download pre-processed data (see below) or include new data. The folder contains three major directories: `train/`, `predict/`, and `publication_analysis/`. Each directory is accompanied by a `README.md` file detailing usage.
To train / re-train new models, use the `train.py` script in `train/`. To make predictions using a model, use one of two scripts, `predict_domains.py` and `predict_proteins.py`, for predicting either domain-peptide interactions or protein-protein interactions. Scripts are designed with a CLI and should be used from the command line:
```bash
python [SCRIPT] [OPTIONS]
```
Options for any script may be listed using the `-h/--help` flag.
To reproduce analysis and figures presented in the paper [Biophysical prediction of protein-peptide interactions and signaling networks using machine learning](https://doi.org/10.1038/s41592-019-0687-1), use the scripts in `publication_analysis/`.
Pre-trained models are released with this repo. An alternative use case would be to train / re-train a new model in the `train/` code and make new predictions using the `predict/` code.
### Model updates
We identified an issue in the original datasets used to train the model published in [Biophysical prediction of protein-peptide interactions and signaling networks using machine learning](https://doi.org/10.1038/s41592-019-0687-1). We have released corrected datasets on [figshare (doi:10.6084/m9.figshare.22105529)](https://doi.org/10.6084/m9.figshare.22105529) (published on February 16, 2023), and replaced the original models released with this repo with corrected ones (on January 9, 2023). Please verify that you use the corrected models for all predictions (see documentation in `predict/`).
## Data
All associated data may be downloaded from [figshare (doi:10.6084/m9.figshare.22105529)](https://doi.org/10.6084/m9.figshare.22105529).
## Requirements
- Python (>= 3.5)
- TensorFlow (1.14)
- numpy (1.18)
- scipy (1.4)
- scikit-learn (0.20)
- tqdm (4.41) (Progressbar. Not strictly necessary for functionality; needed to ensure package runs.)
## Reference
Please reference the associated publication:
Cunningham, J.M., Koytiger, G., Sorger, P.K., & AlQuraishi, M. "Biophysical prediction of protein-peptide interactions and signaling networks using machine learning." *Nature Methods* (2020). [doi:10.1038/s41592-019-0687-1](https://doi.org/10.1038/s41592-019-0687-1). ([citation.bib](misc/citation.bib))
See also, a **website** at [proteinpeptide.io](https://proteinpeptide.io) for exploring the associated analyses (code: [aqlaboratory/hsm-web](https://github.com/aqlaboratory/hsm-web)). Note that the results on the website were obtained using an [old model](#model-updates).
## Funding
This work was supported by the following sources:
| **Funder** | **Grant number** |
| ---------- | ---------------- |
| NIH | U54-CA225088 |
| NIH | P50-GM107618 |
| DARPA / DOD | W911NF-14-1-0397 |
## License
This repository is released under an [MIT License](LICENSE)