Computational Challenges of Protein Function Prediction

January 29, 2013 | A worldwide effort encompassing 102 researchers and students from 30 research groups working over 2 years tackled the computational challenges of protein function prediction. The results were published this week in Nature Methods. The project analyzed and evaluated protein function prediction methods. “Fifty-four methods representing the state of the art for protein function prediction were evaluated on a target set of 866 proteins from 11 organisms,” the study authors write. “Two findings stand out: (i) today's best protein function prediction algorithms substantially outperform widely used first-generation methods, with large gains on all types of targets; and (ii) although the top methods perform well enough to guide experiments, there is considerable need for improvement of currently available tools.” Nature Methods