Major Essential Revisions 1. The formula definition of Macro precision/recall doesn't seem correct. The dummy variable "j" in the summation shouldn't appear on the left of the equation.

Minor Essential Revisions 1. The interchangeably used terms "GO category" and "GO term" are confusing to the reader. It would be better to pick one and keep consistent.

1. A few typos: (i) paragraph 2 of "Introduction" asses --> assess (same for another occurrence in the last paragraph of this section). (ii) The 3rd sentence of "Data" section / "GO annotation": "we" should be capitalized.

2. The format of date is not consistent in the subsection of "Literature" (section: "Data") e.g. ("10-23-13", "2013-11-13")

Discretionary Revisions:

1. If I understand properly, "micro" metrics are from protein's perspective, i.e., calculate precision/recall for each protein and then average them; while "macro" average are from GO term's perspective. It's not clear to me why the authors chose the term "micro" versus "macro" here.

2. When comparing the performance of methods under NA and NP protocols, the authors used different sizes of test sets (i.e. NA evaluates on a smaller and more specific GO term sets), in which sense, F-max values from NA and NP are not directly comparable. NA is, by the settings in this manuscript, essentially a harder problem and is expected to have lower F-max. Level of interest An article of importance in its field Quality of written English Needs some language corrections before being published Statistical review No, the manuscript does not need to be seen by a statistician. Declaration of competing interests I declare that I have no competing interests.

Authors' response to reviews: (http://www.gigasciencejournal.com/imedia/2030968554168896_comment.pdf)