NCBO Ontology Recommender 2.0: an enhanced approach for biomedical ontology recommendation

Table 11 Experiment 3 results

Input	Size	Input domain	Ontology Recommender 1.0			Ontology Recommender 2.0
Input	Size	Input domain	Result	Size	Coverage (%)	Result	Size	Coverage (%)
1	23	Adverse reactions	SNOMEDCT	324,129	52.1	MEDDRA	68,261	91.3
2	8	Autism spectrum disorder	ASDPTO	284	100.0	ASDPTO	284	100.0
3	14	Bioinformatics operations	SWO	4,068	100.0	EDAM	3,240	100.0
4	30	Biomedical investigations	NCIT	118,941	63.3	OBI	3,055	100.0
5	26	Cell types	SYN	14,462	76.9	CL	6,532	88.4
6	14	Clinical research	NCIT	118,941	78.6	OCRE	389	100.0
7	13	Dermatology	DERMLEX	6,106	92.3	DERMLEX	6,106	92.3
8	14	Environmental features	ENVO	2,307	100.0	ENVO	2,307	100.0
9	18	Enzyme sources	NCIT	118,941	55.6	BTO	5,902	72.2
10	19	Fish anatomy	NIFSTD	124,337	68.4	TAOcpr	3,428	79.0
11	44	Human diseases	RH-MESH	305,349	52.3	DOID	11,280	95.5
12	13	Mathematical models in life sciences	MAMO	100	100.0	MAMO	100	100.0
13	25	Primary care	NCIT	118,941	80.0	SNOMEDCT	324,129	88.0
14	23	Signs and symptoms	NCIT	118,941	65.2	SYMP	936	91.3
15	25	Units of Measurement	TEO	687	92.0	TEO	687	92.0

The size of each ontology (number of classes) and the coverage provided are also shown. The best results for each input (lowest ontology size and highest coverage), are highlighted in bold
The table shows the input size (number of keywords) and domain, as well as the first ontology suggested by Ontology Recommender 1.0 and Ontology Recommender 2.0

ISSN: 2041-1480