damiano-sg/diffpalm

Differentiable Pairing using Alignment-based Language Models

DiffPALM

Paralog matching method described in “Pairing interacting protein sequences using masked language modeling” (Lupo, Sgarbossa, and Bitbol, 2023). The MSA Transformer model used here was introduced in (Rao el al, 2021).

Install

Clone this repository on your local machine by running and move inside the root folder. We recommend creating and activating a dedicated conda or virtualenv Python virtual environment.

git clone [email protected]:Bitbol-Lab/DiffPALM.git

and move inside the root folder. We recommend creating and activating a dedicated conda or virtualenv Python virtual environment. Then, make an editable install of the package:

python -m pip install -e .

How to use

See the _example_prokaryotic.ipynb notebook for an example of paired MSA optimization in the case of well-known prokaryotic datasets, for which ground truth matchings are given by genome proximity.

Citation

Our work can be cited using the following BibTeX entry:

@article{lupo2023pairing,
  title={Pairing interacting protein sequences using masked language modeling},
  author={Lupo, Umberto and Sgarbossa, Damiano and Bitbol, Anne-Florence},
  year={2023},
  journal={bioRxiv},
  doi={10.1101/2023.08.14.553209 }
}

nbdev

This project has been developed using nbdev.