PFRMAT SS
TARGET T0437
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-ebghtl-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   15
METHOD	    7	   15
METHOD	    9	   15
METHOD	   13	    6 (1 EBGHTL )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0437.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 51
METHOD
MODEL 1
M C 0.751
K C 0.533
D C 0.437
V C 0.343
V C 0.441
D H 0.421
K H 0.442
C H 0.448
S T 0.389
T T 0.490
K T 0.503
G C 0.417
C C 0.407
A E 0.472
I E 0.539
D E 0.725
I E 0.726
G E 0.794
T E 0.921
V E 0.934
I E 0.928
D E 0.679
N T 0.765
D T 0.899
N T 0.895
C E 0.659
T E 0.936
S E 0.968
K E 0.986
F E 0.983
S E 0.979
R E 0.961
F E 0.909
F E 0.552
A C 0.461
T C 0.603
R H 0.962
E H 0.972
E H 0.981
A H 0.990
E H 0.996
S H 0.994
F H 0.994
M H 0.995
T H 0.993
K H 0.981
L H 0.977
K H 0.997
E H 0.995
L H 0.997
A H 0.989
A H 0.981
A H 0.940
A H 0.785
S T 0.364
S T 0.546
A T 0.560
D T 0.614
E T 0.480
G C 0.441
A C 0.331
S E 0.562
V E 0.747
A E 0.816
Y E 0.854
K E 0.905
I E 0.926
K E 0.939
D E 0.904
L E 0.642
E T 0.776
G T 0.893
Q T 0.599
V E 0.835
E E 0.962
L E 0.979
D E 0.983
A E 0.979
A E 0.982
F E 0.969
T E 0.959
F E 0.856
S E 0.763
C C 0.494
Q C 0.430
A H 0.517
E H 0.911
M H 0.969
I H 0.985
I H 0.992
F H 0.992
E H 0.992
L H 0.976
S H 0.900
L H 0.845
R H 0.751
S H 0.536
L C 0.508
A C 0.930
END