From sequence to enzyme mechanism using multi-label machine learning

BMC Bioinformatics

Table 1 Datasets statistics

Dataset	Instances	Attributes	Class labels
Mechanism set with CSA	248	134	82
Mechanism set with Maximum sequence identity	248	82	82
Mechanism set with Minimum Euclidean distance (InterPro)	248	82	82
Mechanism set with InterPro + CSA	248	456	82
Mechanism set with Max seq. Id. + min Eucl. Dist. (InterPro)	248	162	82
Mechanism set with all InterPro sub-signature matches	248	743	82
Mechanism set with InterPro signatures	248	322	82
Negative set with InterPro attributes	290	917	290
Mechanism set + Swiss-Prot non-EC with InterPro attributes	35,171	4418	82
Swiss-Prot non-EC set with InterPro attributes	68,667 (226,213)	4,825	0

The table presents the number of instances (proteins), attributes (signatures or sequence identity values) and class values (mechanisms) for the datasets used in this work; for the swissprot-non-EC set we present the instances that need prediction (the ones sharing a signature with the mechanism set), while the total number of instances is shown between parentheses.

ISSN: 1471-2105