Exploring supervised and unsupervised methods to detect topics in biomedical text

BMC Bioinformatics

Table 2 OMIM topics and the number of documents that have been assigned to each topic.

Topics	Total Number	No_dup*	Topics	Total Number	No_dup*
CLONING	7719	2397	ANIMAL MODEL	879	261
MAPPING	7487	1760	CYTOGENETICS	770	222
MOLECULAR GENETICS	7139	2347	OTHER FEATUERS	349	90
CLINICAL FEATURES	6917	3044	HETEROGENEITY	298	62
GENE FUNCTION	6469	2960	HISTORY	131	42
GENE STRUCTURE	2444	165	EVOLUTION	126	16
INHERITANCE	1513	385	ALLELIC VARIANTS	122	80
DIAGNOSIS	1300	193	NOMENCLATURE	99	9
POPULATION GENETICS	1163	213	GENOTYPE	91	12
PATHOGENESIS	1062	216	GENE FAMILY	83	25
PHENOTYPE	1034	270	GENE THERAPY	51	21
BIOCHEMICAL FEATURES	993	314	GENETIC VARIABILITY	47	17
CLINICAL MANAGEMENT	974	284	Total:	49,260	15,405

* The number of references that have been assigned to only one topic, not others, within an OMIM entry.

ISSN: 1471-2105