Leveraging syntactic and semantic graph kernels to extract pharmacokinetic drug drug interactions from biomedical literature

Table 2 Performance for PK DDI extraction on the in vitro dataset

Methods	P	R	F ₁
DEP	43.43 %	63.24 %	51.50 %
PAS^a	73.03 %	62.07 %	67.68 %
DEP_SC^a	70.32 %	61.93 %	65.86 %
PAS_SC^a,b	69.23 %	66.48 %	67.83 %
DEP_ReSC^a	70.76 %	67.98%	69.34 %
PAS_ReSC^a,b	74.83 %	62.50 %	68.11 %

Totally, six different methods were implemented. The abbreviation DEP stands for the dependency-based graph kernel, PAS stands for the graph kernel based on predicate-argument-structure, SC stands for semantic class information, and ReSC stands for refined semantic class information. DEP_SC means that semantic class information is incorporated into the dependency-based graph kernel. Precision (P), Recall (R) and F-measure (F ₁) were reported for each method. The highest performance under each evaluation criterion is bolded.
^a means the performance difference between the underlying method and DEP is statistically significant
^b means the performance difference between the underlying method and PAS is statistically significant. (p-value < 0.05)

ISSN: 1752-0509