PFRMAT SS
TARGET T0139
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 T0139.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 3
METHOD
MODEL 1
T B 0.201
G D 0.184
I B 0.182
S B 0.142
R H 0.254
E H 0.402
T H 0.442
S H 0.515
S H 0.688
D H 0.784
V H 0.800
A H 0.824
L H 0.829
A H 0.784
S H 0.788
H H 0.806
I H 0.854
L H 0.761
T H 0.758
A H 0.702
L H 0.299
R H 0.331
E B 0.186
K B 0.325
Q B 0.370
A B 0.343
P B 0.277
E E 0.349
L E 0.351
S E 0.413
L E 0.242
S E 0.236
S H 0.205
Q H 0.194
D E 0.299
L H 0.293
E H 0.485
L H 0.328
V H 0.274
T B 0.310
K H 0.495
E H 0.295
D E 0.519
P H 0.552
K H 0.786
A H 0.774
L H 0.753
A H 0.625
V H 0.570
A H 0.461
L H 0.360
N H 0.269
W H 0.194
D E 0.247
I H 0.395
K H 0.511
K H 0.368
T H 0.450
E H 0.701
T H 0.718
V H 0.792
Q H 0.853
E H 0.865
A H 0.806
C H 0.778
E H 0.811
R H 0.819
E H 0.820
L H 0.820
A H 0.834
L H 0.782
R H 0.772
L H 0.765
Q H 0.731
Q H 0.692
T H 0.608
Q H 0.591
S H 0.579
L H 0.522
H H 0.416
S H 0.382
L H 0.351
R H 0.229
END