Table 2.

Results for sequence models, sorted by Matthews Correlation Coefficient (MCC).

Family	Dataset Size	Recall	Precision	F1	MCC
C4	15,332	1.00	0.98	0.99	0.98
H3	4524	0.98	0.99	0.98	0.97
C2H2	3715	0.97	0.99	0.98	0.95
C3H1	9158	0.98	0.96	0.97	0.94
E1H2	2574	0.95	0.97	0.96	0.92
D1H2	2406	0.94	0.95	0.94	0.90
C2H1	1926	0.93	0.95	0.94	0.88
C3	2591	0.95	0.89	0.92	0.84
D1H1	804	0.80	0.93	0.86	0.74
E1H1	812	0.81	0.83	0.82	0.61
Mean		0.93	0.94	0.94	0.87