PFRMAT SS
TARGET T96C
AUTHOR 3670-4530-6947
METHOD Using neural net overrep-2500-IDaa13-5-10-7-10-5-10-11-ehl2-seeded9-stride-trained.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   10
METHOD	    7	   10
METHOD	    5	   10
METHOD	   11	    3 (1 EHL2 )
METHOD The input amino acid frequencies were determined from
METHOD alignment c-term/T96C.t2k.a2m.gz
METHOD with weighted counts, using EntropyWeight(1.4 bits/column, 10)
METHOD The weighting was determined by the posterior distribution
METHOD after regularizing with /projects/compbio/lib/recode3.20comp.
METHOD Counts were regularized to probabilities using
METHOD /projects/compbio/lib/recode3.20comp
METHOD Total sequence weight for alignment was 3.23325
METHOD
MODEL 1
P C 0.78
D H 0.56
K H 0.75
A H 0.79
Q H 0.91
E H 0.93
V H 0.95
L H 0.96
A H 0.96
T H 0.96
A H 0.96
N H 0.95
E H 0.92
V H 0.89
A H 0.89
D H 0.82
H H 0.75
A C 0.54
D H 0.55
A H 0.60
F H 0.66
A H 0.71
E H 0.81
L H 0.74
D H 0.62
Y H 0.69
N H 0.75
I H 0.68
F H 0.72
R H 0.67
G H 0.57
L H 0.56
A H 0.48
F E 0.44
A C 0.35
S C 0.57
G C 0.81
N C 0.93
P H 0.50
I H 0.68
Y H 0.82
G H 0.76
L H 0.69
I H 0.47
L H 0.59
N H 0.62
G H 0.53
M C 0.72
K H 0.48
G H 0.61
L H 0.73
Y H 0.82
T H 0.84
R H 0.80
I H 0.77
G H 0.65
R H 0.62
H H 0.52
Y H 0.46
F C 0.60
A C 0.78
N C 0.82
P H 0.78
E H 0.84
A H 0.87
R H 0.88
S H 0.92
L H 0.96
A H 0.96
L H 0.98
G H 0.99
F H 0.99
Y H 0.99
H H 1.00
K H 1.00
L H 1.00
S H 1.00
A H 0.99
L H 0.98
C H 0.96
S H 0.90
E H 0.82
G C 0.80
A C 0.64
H H 0.58
D H 0.62
Q H 0.76
V H 0.86
Y H 0.89
E H 0.88
T H 0.88
V H 0.87
R H 0.86
R H 0.84
Y H 0.59
G C 0.84
H C 0.85
E C 0.73
S C 0.59
G H 0.89
E H 0.96
I H 0.98
W H 0.99
H H 0.99
R H 0.99
M H 0.98
Q H 0.96
K H 0.90
N H 0.71
L C 0.91
P C 0.87
G C 0.77
D C 0.68
L C 0.44
A E 0.42
I C 0.39
Q C 0.51
G C 0.75
R C 0.93
END