Skip to main content

Table 1 Datasets used to train and test a MoRF predictor

From: Discovering MoRFs by trisecting intrinsically disordered protein sequence into terminals and middle regions

Data sets No. of Sequences Total residues No. of MoRF residues No. of non-MoRF residues
training set TRAIN 421 245,984 5396 240,588
test sets TEST 419 258,829 5153 253,676
NEW 45 37,533 626 36,907
TEST464 464 296,362 5779 290, 583
TEST266 266 154,399 3305 151,094
validation set EXP53 53 25,186 2432 22,754