Skip to content

Rational discovery of antimicrobial peptides by means of artificial intelligence.

Notifications You must be signed in to change notification settings

BCV-Uniandes/AMPs-Net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence

Paola Ruiz Puentes, Maria C. Henao, Javier Cifuentes, Carolina Muñoz-Camargo, Luis H. Reyes, Juan C. Cruz and Pablo Arbeláez.

This repository contains the official implementation of AMPs-Net: Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence.

Paper

Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence.
Paola Ruiz Puentes1,2, Maria C. Henao3, Javier Cifuentes2, Carolina Muñoz-Camargo2,Luis H. Reyes3, Juan C. Cruz2, Pablo Arbeláez1
Membranes MDPI, 2022.

1 Center for Research and Formation in Artificial Intelligence .(CINFONIA), Universidad de los Andes, Bogotá 111711, Colombia.
2 Department of Biomedical Engineering, Universidad de los Andes, Bogotá 111711, Colombia.
3 Grupo de Diseño de Productos y Procesos (GDPP), Department of Chemical and Food Engineering, Universidad de los Andes, Bogota 111711, Colombia.

Installation

The following steps are required in order to run AMPs-Net:

$ export PATH=/usr/local/cuda-11.0/bin:$PATH 
$ export LD_LIBRARY_PATH=/usr/local/cuda-11.0/lib64:$LD_LIBRARY_PATH 

$ conda create --name amps_env 
$ conda activate amps_env 

$ bash amps_env.sh

Models

We provide pretrained models available for download in the following link. Last update on the models on the 01/01/2023.

Usage

To train each of the components of our method: please refer to run_AMP.sh and run_multilabel.sh.

To perform inference on your data please refer to: run_inference_AMP.sh and run_inference_multilabel.sh.

To setup your data on the proper format for our models please refer to generate_metadata.sh. Your dataset should be a csv file with a column name Sequence and your peptides in their AA sequence. Follow the example in data/datasets/Inference.

To perform inference with your models please modify L34-37 from inference.py. (Change Checkpoint.pth to Checkpoint__valid_best.pth)

Citation

We hope you find our paper useful. To cite us, please use the following BibTeX entry:

@article{RuizPuentes2022,
  doi = {10.3390/membranes12070708},
  url = {https://doi.org/10.3390/membranes12070708},
  year = {2022},
  month = jul,
  publisher = {{MDPI} {AG}},
  volume = {12},
  number = {7},
  pages = {708},
  author = {Paola Ruiz Puentes and Maria C. Henao and Javier Cifuentes and Carolina Mu{\~{n}}oz-Camargo and Luis H. Reyes and Juan C. Cruz and Pablo Arbel{\'{a}}ez},
  title = {Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence},
  journal = {Membranes}
}

About

Rational discovery of antimicrobial peptides by means of artificial intelligence.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published