PreGO: A Protein Function Prediction Algorithm Based on an Infinite Mixture of Hidden Markov and Bayesian Network Models

摘要

Automatic protein function prediction is a non-trivial task in the era of omics. We propose a novel method to predict protein functions, called PreGO. PreGO is an algorithm based on an infinite mixture of hidden Markov models. Given an unannotated protein sequence, PreGO predicts the probability of existence of Gene Ontology terms. The PreGO algorithm was tested on a small dataset. We compared our algorithm with a baseline predictor. The proposed algorithm performed significantly better than the baseline. The PreGO algorithm could be a promising method for predicting GO terms given an amino acid sequence.