Community-Wide Evaluation of Computational Function Prediction

TL;DR

This paper discusses a community-wide challenge designed to evaluate the performance of computational methods in predicting protein functions, which is crucial due to the impracticality of experimental annotation for all genes.

Contribution

It introduces a large-scale, ongoing evaluation framework for assessing computational protein function prediction algorithms against experimental data.

Findings

Community challenge enables benchmarking of algorithms

Evaluation highlights strengths and weaknesses of current methods

Promotes development of more accurate computational tools

Abstract

A biological experiment is the most reliable way of assigning function to a protein. However, in the era of high-throughput sequencing, scientists are unable to carry out experiments to determine the function of every single gene product. Therefore, to gain insights into the activity of these molecules and guide experiments, we must rely on computational means to functionally annotate the majority of sequence data. To understand how well these algorithms perform, we have established a challenge involving a broad scientific community in which we evaluate different annotation methods according to their ability to predict the associations between previously unannotated protein sequences and Gene Ontology terms. Here we discuss the rationale, benefits and issues associated with evaluating computational methods in an ongoing community-wide challenge.