Skip to main content

Table 1 Number of protein sequences for plastids and non-plastid class used in phase-I (identification) training/testing

From: Identification and characterization of plastid-type proteins from sequence-attributed features using machine learning

Type Available < 30% cutoff
(within class)
< 30% cutoff (across class) 10% independent test set Training set
Plastids 17514 3535 3160 316 2844
Non-plastids 17514 3191 3160 316 2844
Total 35,028 6726 6320 632 5688