Skip to main content

Table 3 Training and test dataset statistics

From: GODoc: high-throughput protein function prediction using novel k-nearest-neighbor and voting algorithms

Dataset Ontology # of seqs # of GOs Median # of GOs
CAFA2-Swiss BPO 40,728 15,838 25
CCO 40,571 1892 9
MFO 26,056 5480 8
CAFA3-Swiss BPO 50,813 19,682 29
CCO 49,328 2426 10
MFO 35,086 6366 8
CAFA2-Benchmark BPO 860 6540 29
CCO 1259 833 11
MFO 421 1501 8