PFRMAT SS
TARGET T0471
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0471.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0471.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0471.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 T0471.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0471
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 T0471.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 24
METHOD
METHOD ============================================
METHOD Comments from T0471.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0471
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 T0471.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 24
METHOD
METHOD ============================================
METHOD Comments from T0471.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0471
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 T0471.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 24
METHOD
METHOD ============================================
MODEL 1
M C 0.95
W C 0.73
N C 0.63
D H 0.66
L H 0.74
A H 0.75
V H 0.77
Y H 0.76
I H 0.74
I H 0.74
R H 0.71
C H 0.61
S C 0.49
G C 0.83
P C 0.90
G C 0.89
T C 0.70
R E 0.71
V E 0.94
V E 0.96
E E 0.97
V E 0.91
G E 0.76
A C 0.61
G C 0.81
R C 0.80
F C 0.75
L H 0.83
Y H 0.90
V H 0.96
S H 0.97
D H 0.97
Y H 0.97
I H 0.97
R H 0.95
K H 0.87
H C 0.52
S C 0.97
K C 0.93
V E 0.60
D E 0.92
L E 0.96
V E 0.96
L E 0.93
T E 0.78
D C 0.51
I C 0.60
K C 0.80
P C 0.84
S C 0.87
H C 0.87
G C 0.76
G C 0.54
I E 0.75
V E 0.80
R E 0.76
D E 0.53
D C 0.62
I C 0.70
T C 0.77
S C 0.91
P C 0.86
R C 0.80
M H 0.64
E H 0.68
I H 0.78
Y H 0.71
R H 0.50
G C 0.69
A C 0.75
A C 0.63
L E 0.85
I E 0.90
Y E 0.90
S E 0.78
I C 0.53
R C 0.86
P C 0.94
P C 0.83
A H 0.74
E H 0.78
I H 0.77
H H 0.74
S H 0.84
S H 0.92
L H 0.96
M H 0.97
R H 0.96
V H 0.97
A H 0.96
D H 0.90
A H 0.81
V C 0.52
G C 0.97
A C 0.94
R C 0.77
L E 0.93
I E 0.97
I E 0.97
K E 0.90
P E 0.53
L C 0.82
T C 0.86
G C 0.86
E C 0.75
D C 0.66
I C 0.66
V C 0.62
T C 0.65
E C 0.67
R C 0.59
K E 0.56
M E 0.66
K E 0.67
L E 0.58
V C 0.56
N C 0.77
Y C 0.77
G C 0.55
R E 0.74
T E 0.88
Y E 0.94
F E 0.94
Y E 0.92
E E 0.86
Y E 0.75
I E 0.60
A E 0.50
E C 0.56
V C 0.67
R C 0.69
S C 0.83
R C 0.98
END