PFRMAT SS
TARGET T0497
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0497.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0497.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0497.t2k.str.rdb  (weight 1.53983)
METHOD These files were combined by translating their predictions into EHL
METHOD predictions with tables generated by compare-real, and then combining
METHOD those predictions with weights proportional to their mutual information
METHOD with the EHL alphabet.  The comments from the individual files follow.
METHOD
METHOD Comments from T0497.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0497
METHOD Using neural net t2k-5740-IDaaHr-5-15-7-15-9-15-13-ebghstl-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   15
METHOD	    7	   15
METHOD	    9	   15
METHOD	   13	    7 (1 EBGHSTL )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0497.t2k-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(-1 bits/column, 1)
METHOD Counts were regularized to probabilities using
METHOD /projects/compbio/lib/recode3.20comp
METHOD Total sequence weight for alignment was 152
METHOD
METHOD ============================================
METHOD Comments from T0497.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0497
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-ebghtl-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   15
METHOD	    7	   15
METHOD	    9	   15
METHOD	   13	    6 (1 EBGHTL )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0497.t2k-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(-1 bits/column, 1)
METHOD Counts were regularized to probabilities using
METHOD /projects/compbio/lib/recode3.20comp
METHOD Total sequence weight for alignment was 152
METHOD
METHOD ============================================
METHOD Comments from T0497.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0497
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-str-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   15
METHOD	    7	   15
METHOD	    9	   15
METHOD	   13	   13 (1 str )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0497.t2k-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(-1 bits/column, 1)
METHOD Counts were regularized to probabilities using
METHOD /projects/compbio/lib/recode3.20comp
METHOD Total sequence weight for alignment was 152
METHOD
METHOD ============================================
MODEL 1
M C 0.97
A C 0.90
D C 0.91
P H 0.68
K H 0.81
E H 0.90
L H 0.93
Q H 0.96
D H 0.97
K H 0.97
F H 0.97
W H 0.98
K H 0.97
A H 0.96
L H 0.90
K H 0.55
S C 0.71
D C 0.88
R C 0.92
T E 0.76
V E 0.95
M E 0.97
L E 0.96
G E 0.90
L E 0.79
D E 0.64
G C 0.77
V C 0.92
E C 0.94
D C 0.91
G C 0.80
H C 0.51
A C 0.59
R C 0.57
P C 0.66
M C 0.65
T C 0.55
A C 0.57
Q C 0.54
I C 0.56
E C 0.58
G C 0.64
D C 0.76
S C 0.87
G C 0.90
G C 0.71
P E 0.68
I E 0.92
W E 0.95
F E 0.95
F E 0.85
T C 0.52
S C 0.86
K C 0.90
D C 0.86
N C 0.72
A H 0.57
L H 0.77
I H 0.86
A H 0.88
M H 0.89
L H 0.89
G H 0.77
Q H 0.50
G C 0.92
R C 0.94
R C 0.84
V E 0.58
I E 0.90
G E 0.97
A E 0.97
F E 0.96
S E 0.92
S E 0.57
K C 0.91
G C 0.91
H C 0.86
D C 0.78
L E 0.76
F E 0.95
A E 0.97
S E 0.98
I E 0.97
S E 0.94
G E 0.91
S E 0.93
L E 0.94
R E 0.96
E E 0.94
D E 0.72
T C 0.61
D C 0.92
P H 0.88
A H 0.93
V H 0.96
V H 0.96
D H 0.94
R H 0.86
L H 0.74
W H 0.68
N H 0.59
P H 0.89
Y H 0.90
V H 0.91
A H 0.90
A H 0.81
W H 0.74
Y C 0.71
E C 0.81
G C 0.89
G C 0.90
K C 0.90
D C 0.89
D C 0.91
P C 0.92
K C 0.90
L E 0.63
A E 0.92
L E 0.97
L E 0.98
R E 0.97
L E 0.92
D E 0.61
A C 0.57
D C 0.54
H H 0.43
A E 0.70
Q E 0.91
I E 0.95
W E 0.90
L E 0.67
N C 0.79
G C 0.92
S C 0.87
S C 0.69
L H 0.60
L H 0.76
A H 0.76
G H 0.78
I H 0.81
K H 0.84
V H 0.85
L H 0.82
L H 0.63
G C 0.74
V C 0.97
END