Skip to content
DeepGO with GOPlus axioms
Python Shell
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.gitignore cleanup Apr 11, 2019
LICENSE Create LICENSE Apr 17, 2019
README.md
alphas.py filters and evaluation Jul 9, 2019
aminoacids.py train params Mar 6, 2019
analyze_filters.py filters and evaluation Jul 9, 2019
cafa3_data.py cleanup Apr 11, 2019
data_stats.py cleanup Apr 11, 2019
deepgoplus.py filters and evaluation Jul 9, 2019
deepgoplus_data.py filters and evaluation Jul 9, 2019
diamond_data.py cleanup Apr 11, 2019
evaluate_deepgo.py cleanup Apr 11, 2019
evaluate_deepgoplus.py . Jul 30, 2019
evaluate_diamondblast.py cleanup Apr 11, 2019
evaluate_diamondscore.py cleanup Apr 11, 2019
evaluate_filters.py filters and evaluation Jul 9, 2019
evaluate_interpros.py filters and evaluation Jul 9, 2019
evaluate_naive.py . Mar 31, 2019
filters.py filters and evaluation Jul 9, 2019
ic_plot.py filters and evaluation Jul 9, 2019
params_table.py cleanup Apr 11, 2019
pfam.py filters and evaluation Jul 9, 2019
plot.py filters and evaluation Jul 9, 2019
predict.py filters and evaluation Jul 9, 2019
predict.sh predict.sh Apr 17, 2019
requirements.txt interactions Jan 10, 2019
run_deepgoplus.sh cleanup Apr 11, 2019
run_diamond.sh train params Mar 6, 2019
uni2pandas.py cleanup Apr 11, 2019
utils.py filters and evaluation Jul 9, 2019

README.md

DeepGOPlus: Improved protein function prediction from sequence

DeepGOPlus is a novel method for predicting protein functions from protein sequences using deep neural networks combined with sequence similarity based predictions.

This repository contains script which were used to build and train the DeepGOPlus model together with the scripts for evaluating the model's performance.

Dependencies

The code was developed and tested using python 3.6. To install python dependencies run: pip install -r requirements.txt

Data

  • http://deepgoplus.bio2vec.net/data/ - Here you can find the data used to train and evaluate our method.
  • data.tar.gz - Data required to run predict.sh script
  • data-cafa.tar.gz - CAFA3 challenge dataset
  • data-2016.tar.gz - Dataset which is used to compare DeepGOPlus with GOLabeler and DeepText2GO

Scripts

The scripts require GeneOntology in OBO Format.

  • uni2pandas.py - This script is used to convert data from UniProt database format to pandas dataframe.
  • deepgoplus_data.py - This script is used to generate training and testing datasets.
  • deepgoplus.py - This script is used to train the model
  • evaluate_*.py - The scripts are used to compute Fmax, Smin and AUPR

Running

The online version of DeepGOPlus is available at http://deepgoplus.bio2vec.net/

Citation

If you use DeepGOPlus for your research, or incorporate our learning algorithms in your work, please cite: Maxat Kulmanov, Robert Hoehndorf; DeepGOPlus: Improved protein function prediction from sequence, Bioarxiv, https://www.biorxiv.org/content/10.1101/615260v1

You can’t perform that action at this time.