PFRMAT SS
TARGET T0059
AUTHOR 1751-3146-3362
METHOD Using neural net fssp-12345-IDaa1-9-6-11-9-3-8-7-ehl-seeded6-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 t59.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 7.37613
METHOD
MODEL 1
M C 0.86
S C 0.89
I C 0.72
G C 0.74
V C 0.90
P C 0.61
I H 0.81
K H 0.89
V H 0.82
L H 0.87
H H 0.89
E H 0.85
A H 0.62
E C 0.72
G C 0.92
H C 0.80
I E 0.69
V E 0.94
T E 0.99
C E 0.99
E E 0.99
T E 0.94
N E 0.58
T C 0.83
G C 0.90
E C 0.64
V E 0.61
Y E 0.69
R E 0.68
G E 0.56
K E 0.61
L E 0.61
I C 0.44
E C 0.57
A C 0.46
E H 0.44
D H 0.50
N H 0.39
M H 0.36
N E 0.44
C E 0.60
Q E 0.66
M E 0.49
S H 0.37
N H 0.37
I H 0.51
T H 0.52
V H 0.42
T C 0.44
Y C 0.69
R C 0.86
D C 0.89
G C 0.88
R C 0.67
V C 0.51
A C 0.52
Q C 0.50
L C 0.62
E C 0.75
Q E 0.51
V E 0.79
Y E 0.90
I E 0.89
R E 0.83
G E 0.56
S C 0.71
K E 0.71
I E 0.93
R E 0.98
F E 0.99
L E 0.98
I E 0.92
L E 0.61
P C 0.80
D C 0.85
END