From: Literature mining of protein-residue associations with graph rules learned through distant supervision
Method
Precision (%)
Recall (%)
F-Measure (%)
Abstract level co-occurence
57.10
100
72.69
Sentence level co-occurence
63.50
84.77
72.61
Subgraph matching
85.09
69.54
76.54
(Modifed annotations)
90.38
71.57
79.89