PFRMAT SS
TARGET T0475
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0475.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0475.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0475.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 T0475.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0475
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 T0475.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 76
METHOD
METHOD ============================================
METHOD Comments from T0475.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0475
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 T0475.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 76
METHOD
METHOD ============================================
METHOD Comments from T0475.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0475
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 T0475.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 76
METHOD
METHOD ============================================
MODEL 1
L C 0.93
N C 0.88
S C 0.72
E C 0.65
I H 0.85
E H 0.93
L H 0.96
P H 0.97
V H 0.97
Q H 0.97
K H 0.97
Q H 0.97
L H 0.97
E H 0.95
A H 0.93
Y H 0.86
N H 0.67
A C 0.50
R C 0.70
D C 0.78
I H 0.95
D H 0.97
A H 0.97
F H 0.97
M H 0.96
A H 0.91
W H 0.73
W H 0.52
A C 0.54
D C 0.64
D C 0.65
C E 0.58
Q E 0.81
Y E 0.85
Y E 0.81
A E 0.60
F C 0.77
P C 0.89
A C 0.90
T C 0.82
L C 0.56
L E 0.68
A E 0.70
G E 0.47
N C 0.54
A H 0.93
A H 0.96
E H 0.96
I H 0.96
R H 0.97
V H 0.96
R H 0.95
H H 0.92
I H 0.89
E H 0.79
R H 0.66
F C 0.58
K C 0.74
E C 0.86
P C 0.88
D C 0.81
L C 0.70
Y C 0.46
G E 0.74
E E 0.86
L E 0.83
L E 0.83
T E 0.80
R E 0.85
V E 0.88
I E 0.81
V E 0.48
G C 0.85
N C 0.76
V E 0.84
V E 0.92
I E 0.92
D E 0.89
H E 0.85
E E 0.85
T E 0.87
V E 0.88
T E 0.84
R E 0.71
N C 0.60
F C 0.86
P C 0.93
E C 0.93
G C 0.74
K E 0.63
G E 0.79
E E 0.79
V E 0.84
D E 0.89
V E 0.96
A E 0.97
C E 0.97
I E 0.97
Y E 0.97
E E 0.97
V E 0.89
E E 0.57
N C 0.95
G C 0.91
R E 0.66
I E 0.91
A E 0.92
K E 0.92
A E 0.88
W E 0.82
F E 0.76
K E 0.70
I E 0.46
G C 0.81
E C 0.91
P C 0.85
R C 0.73
I C 0.50
V E 0.49
S C 0.62
Q C 0.80
K C 0.98
END