PFRMAT SS
TARGET T0106
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 T0106.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 35.5883
METHOD
MODEL 1
A C 0.83
A C 0.72
C C 0.73
E C 0.75
P C 0.71
V C 0.61
R C 0.58
I C 0.54
P C 0.56
L C 0.45
C C 0.49
K C 0.59
S C 0.70
L C 0.84
P C 0.90
W C 0.80
E C 0.72
M C 0.59
T C 0.48
K C 0.53
M C 0.80
P C 0.85
N C 0.82
H C 0.75
L C 0.80
H C 0.90
H C 0.75
S C 0.69
T C 0.60
Q H 0.98
A H 0.99
N H 0.99
A H 0.99
I H 0.99
L H 1.00
A H 0.99
M H 0.99
E H 0.98
Q H 0.98
F H 0.93
E H 0.89
G H 0.87
L H 0.79
L H 0.76
G H 0.71
T H 0.55
H C 0.55
C H 0.60
S H 0.74
P H 0.93
D H 0.96
L H 0.98
L H 0.98
F H 0.98
F H 0.98
L H 0.97
C H 0.96
A H 0.91
M H 0.72
Y C 0.50
A C 0.87
P C 0.77
I C 0.81
C C 0.69
T C 0.78
I C 0.83
D C 0.83
F C 0.81
Q C 0.81
H C 0.94
E C 0.89
P C 0.84
I C 0.87
K C 0.81
P C 0.48
C H 0.62
K H 0.72
S H 0.80
V H 0.89
C H 0.90
E H 0.96
R H 0.94
A H 0.92
R H 0.91
Q H 0.91
G H 0.86
C H 0.72
E H 0.67
P H 0.71
I H 0.87
L H 0.93
I H 0.92
K H 0.90
Y H 0.85
R C 0.97
H C 0.95
S C 0.83
W C 0.89
P C 0.77
E C 0.60
S C 0.51
L C 0.58
A C 0.62
C C 0.47
D C 0.47
E C 0.56
L C 0.91
P C 0.77
V C 0.81
Y C 0.91
D C 0.95
R C 0.96
G C 0.94
V C 0.68
C E 0.56
I E 0.68
S E 0.56
P C 0.57
E C 0.70
A C 0.69
I C 0.60
V C 0.61
T C 0.67
A C 0.76
D C 0.77
G C 0.83
A C 0.89
D C 0.94
END