PFRMAT SS
TARGET T0056
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 t56.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 9.50002
METHOD
METHOD Since the submitters provided a secondary structure assignment,
METHOD predicting it is rather silly, but I include the prediction for
METHOD completeness.  The prediction is not bad, though there seems to
METHOD a tendency to predict helix a little past the ends of the
MEHTOD reported helices.
MODEL 1
M C 0.90
K C 0.76
V C 0.85
P C 0.94
P C 0.87
H C 0.69
S C 0.56
I H 0.80
E H 0.94
A H 0.97
E H 0.98
Q H 0.97
S H 0.96
V H 0.95
L H 0.92
G H 0.87
G H 0.84
L H 0.78
M H 0.58
L C 0.60
D C 0.76
N C 0.55
E H 0.84
R H 0.86
W H 0.96
D H 0.98
D H 0.98
V H 0.98
A H 0.98
E H 0.96
R H 0.90
V H 0.66
V C 0.52
A C 0.53
D C 0.54
D H 0.48
F C 0.53
Y C 0.50
T H 0.60
R H 0.75
P H 0.80
H H 0.95
R H 0.98
H H 0.99
I H 0.99
F H 0.99
T H 0.99
E H 0.99
M H 0.98
A H 0.98
R H 0.95
L H 0.91
Q H 0.75
E C 0.61
S C 0.78
G C 0.93
S C 0.95
P C 0.82
I C 0.71
D C 0.61
L H 0.60
I H 0.85
T H 0.80
L H 0.93
A H 0.97
E H 0.97
S H 0.96
L H 0.89
E H 0.64
R H 0.50
Q C 0.84
G C 0.90
Q C 0.66
L C 0.52
D C 0.49
S C 0.42
V C 0.53
G C 0.85
G C 0.79
F H 0.58
A H 0.76
Y H 0.79
L H 0.93
A H 0.96
E H 0.95
L H 0.92
S H 0.86
K H 0.63
N C 0.57
T C 0.66
P C 0.84
S C 0.57
A H 0.73
A H 0.85
N H 0.78
I H 0.96
S H 0.98
A H 0.99
Y H 0.99
A H 0.99
D H 0.98
I H 0.97
V H 0.97
R H 0.96
E H 0.96
R H 0.97
A H 0.98
V H 0.96
V H 0.97
R H 0.97
E H 0.95
M H 0.92
I H 0.85
S H 0.63
END