A Deep Learning Model for Protein Function Prediction.
SDNGO is a deep learning model for predicting protein functions using protein sequences, protein domains, and protein-protein interaction (PPI) networks.
This repository contains script which were used to build and train the SDN2GO model.
Validation.py - This script is used to build and train the model and evaluate the performance of the model.
Weight_nodom_model.py - This script is used to build and train the model without domain features.
my_Utils.py - This script contains some utility functions.
The ‘data’ folder contains the data files that the script depends on
If you use SDN2GO for your research, or incorporate our learning algorithms in your work, please cite:
Cai Y, Wang J, Deng L. SDN2GO: An Integrated Deep Learning Model for Protein Function Prediction. Frontiers in Bioengineering and Biotechnology. 2020 Apr 29;8:391.