Datasets and code for evaluation of protein-protein interaction network protein function prediction algorithms

These datasets and code were used to evaluate seven network-based protein function prediction algorithms (majority voting, hishigaki method, markov random fields, random walk, random walk with restart, personalized page rank, and deepNF) on six plant protein-protein interaction networks (Arabidopsis thaliana, Oryza sativa japonica, Zea mays, Solanum tuberosum, Glycine max, and Medicago truncatula).