Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

ProSPr: Protein Structure Prediction

License

NotificationsYou must be signed in to change notification settings

dellacortelab/prospr

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ProSPr distance map prediction (above diagonal) vs. ground truth (below diagonal) for CASP14 target T1034.

drawing

This repository contains an open-source protein distance prediction network, ProSPr, released under the MIT license.

Running ProSPr

After downloading the code, a conda environment with all required dependencies can be created by running

conda env create -f dependencies/prospr-env.yml

Once activated

# Make a prediction:python3 prospr.py predict --a3m ./data/evaluate/T1034.a3m# Or train a new networkpython3 prospr.py train

For more information, run

python3 prospr.py -h

to print the help text.

Docker

Alternatively to conda, you can use Docker. To run the code in a Docker container, run the following after cloning this repository:

cd prospr# Build the docker imagedocker build -t prospr-dev dependencies# Run a docker container interactivelydocker run -it --gpus all --name myname-prospr-dev --rm -v $(pwd):/code prospr-dev# Then, inside the docker container, make a prediction:cd codepython3 prospr.py predict --a3m ./data/evaluate/T1034.a3m# Or train a new networkpython3 prospr.py train

The manuscript corresponding to this work is available here:Evaluation of Deep Neural Network ProSPr for Accurate Protein Distance Predictions on CASP14 Targets

To cite:

@Article{ijms222312835,AUTHOR = {Stern, Jacob and Hedelius, Bryce and Fisher, Olivia and Billings, Wendy M. and Della Corte, Dennis},TITLE = {Evaluation of Deep Neural Network ProSPr for Accurate Protein Distance Predictions on CASP14 Targets},JOURNAL = {International Journal of Molecular Sciences},VOLUME = {22},YEAR = {2021},NUMBER = {23},ARTICLE-NUMBER = {12835},URL = {https://www.mdpi.com/1422-0067/22/23/12835},PubMedID = {34884640}

Authors:Wendy Billings, Jacob Stern, Bryce Hedelius, Todd Millecam, David Wingate, Dennis Della Corte
Brigham Young University

Contact:dennis.dellacorte@byu.edu

About

ProSPr: Protein Structure Prediction

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors5

Languages


[8]ページ先頭

©2009-2026 Movatter.jp