Automated Training for Algorithms That Learn from Genomic Data

Table 2

Cardinalities of the negative interim training sets for the 17 apicomplexan species gathered by ApicoAP-CS.

Apicomplexan Species	OrthoMCL^a	BLAST^b	Confirmed^c	All Combined^d	Conflicts Removed^e	Non-SP Filtered^f
B. bovis	144	136	8	161	159	33
B. microti	142	130	0	159	156	23
C. hominis	135	130	0	157	154	28
C. muris	143	137	0	163	160	34
C. parvum	130	129	10	164	161	33
E. tenella	400	175	8	443	438	169
N. caninum	254	220	15	288	283	81
P. berghei	222	212	28	260	256	101
P. chabaudi	238	223	2	258	253	108
P. cynomolgi	259	224	0	273	269	93
P. falciparum	284	173	156	443	439	138
P. knowlesi	236	227	6	258	254	91
P. vivax	261	227	13	281	277	103
P. yoelii	242	216	16	270	266	89
T. annulata	151	133	4	169	167	42
T. parva	186	128	4	204	202	71
T. gondii	194	198	131	333	327	92

 ^aCardinality of the set gathered by ortholog search using OrthoMCL.
^bCardinality of the set gathered by ortholog search using the BLAST-based algorithm.
^cCardinality of the set containing experimentally confirmed positive/negative proteins.
^dCardinality of the set that is the union of the sets presented in columns 2, 3, and 4.
^eCardinality of the union set when conflicts with the negative/positive set are removed.
^fCardinality of the final training set after proteins without signal peptides have been removed.