The PFP.zip file contains 1. 5 well-formated GO terms dataset for EI, 2. STRING data 3. GO term annotation. The last two could be merged by the 'generate_data.py' script in https://github.com/GauravPa
This dataset includes the data for training the protein function prediction models at github.com/stamakro/GCN-for-Structure-and-Function. For each protein, a pickle file is provided, containing its se