PFRMAT SS
TARGET T0048
AUTHOR 1751-3146-3362
METHOD Using neural net fssp-12345-IDaa1-9-6-11-9-3-8-7-ehl-seeded4-trained.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    9	    6
METHOD	   11	    9
METHOD	    3	    8
METHOD	    7	    3 (1 EHL )
METHOD The input amino acid frequencies were determined from
METHOD alignment t48.t98_6.a2m.gz
METHOD with weighted counts, using HenikoffWeight(1 bits/column, 0.5)
METHOD The weighting was determined by the posterior distribution
METHOD after regularizing with recode3.20comp.
METHOD Counts were regularized to probabilities using
METHOD /projects/compbio/lib/recode3.20comp
METHOD Total sequence weight for alignment was 5.47553
METHOD
MODEL 1
M C 0.82
T C 0.77
A C 0.62
L C 0.55
T C 0.52
Q C 0.51
A C 0.66
H C 0.64
C C 0.60
E H 0.50
A H 0.43
C H 0.40
R C 0.41
A C 0.51
D C 0.52
A H 0.50
P H 0.52
H C 0.47
V C 0.77
S C 0.84
D H 0.72
E H 0.94
E H 0.90
L H 0.93
P H 0.97
V H 0.97
L H 0.95
L H 0.83
R C 0.59
Q H 0.50
I C 0.66
P C 0.81
D C 0.75
W C 0.79
N C 0.67
I C 0.47
E E 0.46
V E 0.40
R C 0.50
D C 0.79
G C 0.89
I C 0.71
M C 0.52
Q C 0.57
L C 0.49
E C 0.50
K C 0.43
V E 0.45
Y E 0.45
L E 0.41
F C 0.36
K C 0.43
N C 0.58
F H 0.87
K H 0.96
H H 0.97
A H 0.97
L H 0.97
A H 0.96
F H 0.95
T H 0.98
N H 0.98
A H 0.98
V H 0.99
G H 0.99
E H 0.99
I H 0.99
S H 0.99
E H 0.98
A H 0.97
E H 0.90
G H 0.54
H C 0.73
H C 0.85
P C 0.59
G H 0.56
L H 0.60
L H 0.52
T C 0.43
E C 0.50
W C 0.75
G C 0.68
K E 0.79
V E 0.92
T E 0.95
V E 0.94
T E 0.91
W E 0.81
W E 0.59
S C 0.55
H C 0.73
S C 0.60
I C 0.67
K C 0.89
G C 0.80
L C 0.73
H C 0.68
R C 0.52
N H 0.49
D H 0.77
F H 0.90
I H 0.90
M H 0.93
A H 0.95
A H 0.95
R H 0.88
T H 0.96
D H 0.98
E H 0.98
V H 0.97
A H 0.95
K H 0.93
T H 0.89
A H 0.74
E C 0.49
G C 0.69
R C 0.79
K C 0.80
END