Christopher S. Funk

TL;DR: Today's best protein function prediction algorithms substantially outperform widely used first-generation methods, with large gains on all types of targets, and there is considerable need for improvement of currently available tools.

TL;DR: The second critical assessment of functional annotation (CAFA), a timed challenge to assess computational methods that automatically assign protein function, was conducted by as mentioned in this paper. But the results of the CAFA2 assessment are limited.

TL;DR: The second critical assessment of functional annotation (CAFA) conducted, a timed challenge to assess computational methods that automatically assign protein function, revealed that the definition of top-performing algorithms is ontology specific, that different performance metrics can be used to probe the nature of accurate predictions, and the relative diversity of predictions in the biological process and human phenotype ontologies.

TL;DR: The second Critical Assessment of Functional Annotation (CAFA) challenge as mentioned in this paper was the first attempt to assess computational methods that automatically assign protein function. And the results of CAFA2 showed that computational function prediction is improving.

TL;DR: The finding that some systems were able to train high-performing models based on this corpus is additional evidence, beyond high inter-annotator agreement, that the quality of the CRAFT corpus is high.