Table 7. The data for protein sequences identification.

Data name	Training or test	Positive or negative	Data size
Biofilm	Training Data Set	Positive Sequences	1,305
	Training Data Set	Negative Sequences	1,463
	Test Data Set	Positive Sequences	145
	Test Data Set	Negative Sequences	163
Integrins	Training Data Set	Positive Sequences	100
	Training Data Set	Negative Sequences	518
	Test Data Set	Positive Sequences	12
	Test Data Set	Negative Sequences	58