Time series-based hybrid ensemble learning model with multivariate multidimensional feature coding for DNA methylation prediction

Table 2 Experimental data distribution

Dataset	Species	Type	Training(70%)	Validation(15%)	Testing(15%)	Total
1	H.sapiens	5hmC	2915	624	624	4163
2	M.musculus	5hmC	5152	1103	1103	7358
3	C.equisetifolia	4mC	2772	593	593	3958
4	F.vesca	4mC	22116	4739	4739	31594
5	S.cerevisiae	4mC	2772	593	593	3958
6	Tolypocladium	4mC	21456	4598	4598	30,652
7	D.melanogaster	6 mA	15668	3357	3357	22382
8	R.chinensis	6 mA	838	180	180	1198
9	Xoc BLS256	6 mA	24102	5164	5164	34430
10	C.elegans	6 mA	11146	2388	2388	15922
11	T.thermophile	6 mA	11146	2388	2388	15922
12	A.thaliana	6 mA	44622	9562	9562	63746
13	H.sapiens	6 mA	25670	5500	5500	36670
14	C.equisetifolia	6 mA	8492	1820	1820	12132
15	F.vesca	6 mA	4344	930	930	6204
16	S.cerevisiae	6 mA	5300	1136	1136	7572
17	Tolypocladium	6 mA	4730	1014	1014	6758
Total			213241	45689	45689	304619

ISSN: 1471-2164