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.
pip install -r requirements.txt
pip install deepgoplus
deepgoplus --data-root <path_to_data_folder> --in-file <input_fasta_filename>
The scripts require GeneOntology in OBO Format.
The online version of DeepGOPlus is available at http://deepgoplus.bio2vec.net/
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, Bioinformatics, https://doi.org/10.1093/bioinformatics/btz595
Current dependencies can be found in the requirements.txt file. The used Python version is 3.7.9. Current version of Tensorflow will require Cuda 10.1 and Cudnn 7.6.5
The following scripts must be run to update the model using the latest versions of the Gene Ontology (GO) and the SwissProt Database.