PFRMAT SS
TARGET T0150
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 T0150.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 77
METHOD
MODEL 1
G H 0.431
S H 0.626
V H 0.788
D H 0.834
F H 0.881
A H 0.934
F H 0.959
E H 0.940
L H 0.917
R H 0.924
K H 0.934
A H 0.914
Q H 0.787
D H 0.723
T B 0.665
G S 0.629
K B 0.407
I E 0.538
V E 0.368
M H 0.137
G D 0.380
A H 0.546
R H 0.763
K H 0.873
S H 0.925
I H 0.932
Q H 0.953
Y H 0.964
A H 0.868
K H 0.752
M B 0.760
G S 0.738
G S 0.304
A E 0.461
K E 0.337
L E 0.718
I E 0.820
I E 0.656
V E 0.423
A E 0.247
R I 0.172
N S 0.436
A B 0.381
R B 0.457
P I 0.486
D H 0.592
I H 0.597
K H 0.692
E H 0.743
D H 0.678
I H 0.745
E H 0.867
Y H 0.897
Y H 0.857
A H 0.806
R H 0.722
L H 0.530
S B 0.677
G S 0.391
I B 0.569
P E 0.680
V E 0.532
Y E 0.649
E E 0.639
F E 0.367
E E 0.263
G H 0.159
T B 0.388
S H 0.427
V H 0.562
E H 0.481
L H 0.582
G H 0.637
T H 0.691
L H 0.518
L B 0.538
G S 0.600
R B 0.503
P A 0.254
H B 0.393
T E 0.396
V E 0.466
S E 0.656
A E 0.565
L E 0.570
A E 0.662
V A 0.421
V B 0.260
D B 0.360
P I 0.398
G S 0.256
E H 0.275
S H 0.548
R H 0.722
I H 0.763
L H 0.633
A H 0.579
L H 0.359
G B 0.217
G H 0.380
K H 0.396
E H 0.251
END