Skip to main content

Table 1 Average performance of grammars for individual ASMs

From: Searching for universal model of amyloid signaling motifs using probabilistic context-free grammars

motif trn val: PDBfrag tst: PDBfull tst: NLReff tst: DisProt
Family Size AP YI Recall@ Recall@ Recall@ AP
     FPR0.01 FPR0.01 FPR0.001  
BASS1 210 0.93/0.95 0.98/0.98 0.99 0.99 0.97 1.00
BASS2 329 0.92/0.94 0.96/0.97 0.98 0.99 0.97 1.00
BASS3 145 0.92/0.93 0.98/0.97 0.97 0.98 0.92 0.99
BASS4 127 0.77/0.93 0.96/0.97 1.00 1.00 0.96 1.00
BASS5 50 0.83/0.86 0.99/0.99 0.85 0.90 0.81 0.97
BASS6 111 0.89/0.89 0.97/0.98 0.91 0.97 0.89 0.97
BASS7 17 0.85/– 0.95/– 0.97 0.92 0.97 0.98
BASS8 14 0.79/– 0.93/– 1.00 1.00 0.96 1.00
BASS9 38 0.42/0.63 0.87/0.91 0.79 0.90 0.79 0.96
BASS10 7 0.57/– 0.99/– 1.00 1.00 1.00 1.00
  1. AP and YI are given for both training without contacts/with contacts. The test set performance is shown only for the mode with the best validation AP. Notations: trn, val, tst are training, validation and testing positive sets, AP is the average precision and YI is Youden’s Index