PFRMAT SS
TARGET T0064
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 t66_7.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 106.045
METHOD
MODEL 1
M C 0.91
I C 0.56
G H 0.87
Q H 0.96
R H 0.93
I H 0.98
K H 0.99
Q H 0.99
Y H 0.99
R H 0.98
K H 0.96
E H 0.89
K C 0.54
G C 0.66
Y H 0.51
S C 0.46
L H 0.95
S H 0.99
E H 0.98
L H 0.99
A H 0.99
E H 0.98
K H 0.94
A H 0.70
G C 0.51
V C 0.44
A H 0.57
K H 0.78
S H 0.82
Y H 0.74
L H 0.80
S H 0.86
S H 0.88
I H 0.86
E H 0.75
R C 0.53
N C 0.80
L C 0.75
Q C 0.77
T C 0.77
N C 0.84
P C 0.92
S C 0.61
I H 0.91
Q H 0.97
F H 0.93
L H 0.99
E H 0.99
K H 0.99
V H 0.99
S H 0.99
A H 0.97
V H 0.92
L H 0.69
D C 0.53
V C 0.46
S C 0.61
V H 0.80
H H 0.85
T H 0.86
L H 0.73
L C 0.49
D C 0.78
E C 0.80
K C 0.83
H C 0.61
E C 0.48
T C 0.44
E C 0.41
Y C 0.46
D C 0.73
G C 0.88
Q C 0.81
L C 0.83
D C 0.91
S C 0.61
E H 0.53
W H 0.55
E H 0.55
K C 0.46
L C 0.41
V E 0.39
R E 0.42
D E 0.41
A C 0.44
M C 0.57
T C 0.56
S C 0.62
G C 0.75
V C 0.84
S C 0.84
K C 0.49
K H 0.83
Q H 0.84
F H 0.90
R H 0.91
E H 0.89
F H 0.81
L H 0.51
D C 0.76
Y C 0.54
Q H 0.80
K H 0.88
W H 0.84
R H 0.74
K H 0.73
S H 0.67
Q H 0.67
K H 0.69
E H 0.57
E C 0.47
END