PFRMAT SS
TARGET T0061
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 t61.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 2.46379
METHOD
MODEL 1
A H 0.53
D H 0.62
A H 0.63
Q H 0.59
K H 0.52
A C 0.60
A C 0.58
D C 0.73
N C 0.71
K C 0.58
K C 0.69
P C 0.58
V C 0.52
N C 0.65
S C 0.71
W C 0.80
T C 0.88
C C 0.59
E H 0.67
D H 0.69
F H 0.60
L H 0.47
A C 0.47
V C 0.52
D C 0.66
E C 0.64
S C 0.72
F C 0.77
Q C 0.79
P C 0.60
T C 0.48
A H 0.41
V H 0.43
G C 0.46
F H 0.54
A H 0.88
E H 0.91
A H 0.89
L H 0.75
N C 0.53
N C 0.58
K C 0.56
D C 0.73
K C 0.84
P C 0.79
E C 0.62
D C 0.56
A E 0.44
V E 0.61
L E 0.65
D E 0.71
V E 0.65
Q E 0.56
G E 0.63
I E 0.66
A E 0.63
T E 0.56
V C 0.65
T C 0.82
P H 0.76
A H 0.92
I H 0.90
V H 0.93
Q H 0.93
A H 0.86
C H 0.60
T H 0.54
Q H 0.89
D H 0.95
K H 0.95
Q H 0.96
A H 0.97
N H 0.94
F H 0.93
K H 0.93
D H 0.90
K H 0.78
V H 0.56
K C 0.74
G C 0.64
E C 0.56
W C 0.45
D H 0.45
K H 0.44
I C 0.56
K C 0.70
K C 0.74
D C 0.82
M C 0.78
END