Data

Tools

Indexes

Applications

Experiments

Open Source Science

proteinn-structure-predictor

A transformer network trained to predict end-to-end single sequence protein structure as a set of angles given amino acid sequences.

https://github.com/danielathome19/proteinn-structure-predictor

Science Score: 57.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 4 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.3%) to scientific vocabulary

Keywords

attention end-to-end pdb protein-sequences protein-structure protein-structure-prediction protein-transformer proteins single-sequence transformer
Last synced: 6 months ago · JSON representation ·

Repository

A transformer network trained to predict end-to-end single sequence protein structure as a set of angles given amino acid sequences.

Basic Info
  • Host: GitHub
  • Owner: danielathome19
  • License: apache-2.0
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 12.5 MB
Statistics
  • Stars: 5
  • Watchers: 2
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Topics
attention end-to-end pdb protein-sequences protein-structure protein-structure-prediction protein-transformer proteins single-sequence transformer
Created almost 3 years ago · Last pushed 11 months ago
Metadata Files
Readme License Citation

README.md

About

ProteiNN is a Transformer network trained to predict end-to-end single-sequence protein structure by amino acid sequences. To find out more, check out the provided research paper:

  • "Deep Learning for Protein Structure Prediction: Advancements in Structural Bioinformatics" (DOI: 10.1101/2023.04.26.538026)
  • Also contained in the "PaperAndPresentation" folder is the research paper.

Usage

Run main.py to choose from either "train", "predict", or "metrics" modes; train will retrain the model and predict will provide users the option to enter an amino acid sequence to predict the structure of (which will be output as a PDB file). Metrics mode will load the trained model and report its classification metrics (e.g., precision, recall, F1 score, etc.) on the test dataset.

NOTE: if you have any issues with the code not working as is, it may be due to the version of the sidechainnet_casp12_30.pkl file that the sidechainnet library downloads. Please contact me if you would like a copy of the version that I used to train the model.

Bugs/Features

Bugs are tracked using the GitHub Issue Tracker.

Please use the issue tracker for the following purpose: * To raise a bug request; do include specific details and label it appropriately. * To suggest any improvements in existing features. * To suggest new features or structures or applications.

License

The code is licensed under Apache License 2.0.

Citation

If you use this code for your research, please cite this project: bibtex @software{Szelogowski_ProteiNN-Structure-Predictor_2023, author = {Szelogowski, Daniel}, doi = {10.1101/2023.04.26.538026}, month = {April}, title = {{ProteiNN-Structure-Predictor}}, license = {Apache-2.0}, url = {https://github.com/danielathome19/ProteiNN-Structure-Predictor}, version = {1.0.0}, year = {2023} }

Owner

  • Name: Daniel J. Szelogowski
  • Login: danielathome19
  • Kind: user
  • Location: Wisconsin
  • Company: @MECS-Research-Lab

Standing on the shoulders of giants.

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Szelogowski"
  given-names: "Daniel"
  orcid: "https://orcid.org/0000-0002-0350-5771"
title: "ProteiNN-Structure-Predictor"
version: 1.0.0
doi: 10.1101/2023.04.26.538026
date-released: 2023-04-26
license: Apache-2.0
url: "https://github.com/danielathome19/ProteiNN-Structure-Predictor"

GitHub Events

Total
  • Watch event: 2
  • Push event: 7
Last Year
  • Watch event: 2
  • Push event: 7

Committers

Last synced: about 2 years ago

All Time
  • Total Commits: 34
  • Total Committers: 1
  • Avg Commits per committer: 34.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 34
  • Committers: 1
  • Avg Commits per committer: 34.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Daniel James Szelogowski d****i@g****m 34

Issues and Pull Requests

Last synced: about 2 years ago

All Time
  • Total issues: 0
  • Total pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • danielathome19 (1)
Top Labels
Issue Labels
Pull Request Labels