Identification of novel arthropod vector G protein-coupled receptors

Parasites & Vectors

Table 3 Number of test set sequences found / missed by species

Species (Total sequences)	Number of sequences found / Missed*
	GPCRHMM	Pfam	Predcouple	Ensemble*
Ae. aegypti (134)	73 / 61	111 / 23	101 / 33	122 / 12
An. gambiae (137)	105 / 32	115 / 22	113 / 24	122 / 15
Ap. mellifera (56)	45 / 11	54 / 2	54 / 2	56 / 0
Dr. melanogaster (195)	176 / 19	156 / 39	180 / 15	185 / 10
Ho. sapiens (892)	759 / 133	712 / 180	778 / 114	807 / 85
Pe. humanus (103)	72 / 31	89 / 14	86 / 17	95 / 8
Vectors (374)	250 / 124	315 / 39	300 / 74	339 / 35
Total (1517)	1230 / 287	1237 / 280	1312 / 205	1387 / 130

* The number of test set sequences each classifier identified (found) and was unable to identify (missed) as GPCRs are given by species, vectors, and total. GPCRHMM, Pfam, and Predcouple were run using default settings. For Ensemble*, sequences with a positive likelihood score were considered to predicted GPCRs. The best results are in bold.

ISSN: 1756-3305