PFRMAT SS
TARGET T0187
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-alpha-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   15
METHOD	    7	   15
METHOD	    9	   15
METHOD	   13	   11 (1 ABCDEFGHIST )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0187.t2k-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(-1 bits/column, 1)
METHOD Counts were regularized to probabilities using
METHOD /projects/compbio/lib/recode3.20comp
METHOD Total sequence weight for alignment was 29
METHOD
MODEL 1
L E 0.272
K C 0.299
K B 0.356
P E 0.511
A E 0.702
A E 0.732
L E 0.566
I A 0.392
F D 0.304
G D 0.252
G S 0.213
E B 0.247
T E 0.356
V E 0.529
V E 0.686
H E 0.646
V E 0.403
K S 0.168
G B 0.169
N S 0.234
G D 0.325
I H 0.138
G S 0.234
G D 0.266
R H 0.204
N H 0.363
Q H 0.657
E H 0.815
L H 0.899
A H 0.918
L H 0.917
S H 0.947
A H 0.900
A H 0.858
I H 0.856
A H 0.675
L H 0.483
E H 0.456
G S 0.547
I E 0.279
E G 0.302
G S 0.611
V E 0.489
I E 0.404
L E 0.523
C E 0.527
S E 0.454
A E 0.241
G S 0.304
T E 0.153
D D 0.200
G D 0.224
T E 0.165
D B 0.237
G D 0.337
P H 0.174
T B 0.297
D H 0.157
A A 0.180
A B 0.195
G S 0.259
G E 0.319
I E 0.428
V B 0.328
D B 0.475
G H 0.511
S H 0.698
T H 0.675
A H 0.875
K H 0.935
T H 0.927
L H 0.914
K H 0.822
A H 0.800
M B 0.534
G S 0.460
E B 0.356
D E 0.363
P H 0.571
Y H 0.851
Q H 0.895
Y H 0.822
L H 0.588
K H 0.590
N H 0.284
N B 0.251
D E 0.233
S H 0.555
Y H 0.853
N H 0.907
A H 0.904
L H 0.874
K H 0.823
K H 0.629
S B 0.240
G H 0.278
A S 0.285
L E 0.289
L E 0.343
I E 0.363
T S 0.179
G C 0.322
P H 0.215
T B 0.195
G S 0.440
T B 0.311
N B 0.260
V I 0.257
N H 0.281
D E 0.221
L E 0.492
I E 0.468
I E 0.596
G E 0.709
L E 0.708
I E 0.440
V E 0.279
END