PFRMAT SS
TARGET T0557
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0557.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0557.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0557.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 T0557.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0557
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 T0557.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 155
METHOD
METHOD ============================================
METHOD Comments from T0557.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0557
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 T0557.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 155
METHOD
METHOD ============================================
METHOD Comments from T0557.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0557
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 T0557.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 155
METHOD
METHOD ============================================
MODEL 1
M C 0.89
R C 0.67
S H 0.56
A H 0.89
T H 0.94
D H 0.95
L H 0.96
L H 0.97
D H 0.96
E H 0.96
L H 0.94
N H 0.88
A H 0.65
V C 0.67
D C 0.89
E C 0.84
S C 0.72
A C 0.59
R E 0.47
I E 0.64
E E 0.69
A E 0.67
K E 0.61
R C 0.40
A C 0.73
S C 0.88
D C 0.90
M C 0.91
G C 0.86
K H 0.53
S H 0.59
V H 0.83
M H 0.77
E H 0.81
T H 0.79
V H 0.81
I H 0.80
A H 0.78
F H 0.67
A H 0.54
N C 0.68
E C 0.87
P C 0.86
G C 0.88
L C 0.85
D C 0.88
G C 0.83
G C 0.60
Y E 0.86
L E 0.96
L E 0.97
L E 0.96
G E 0.91
V E 0.86
D E 0.71
W C 0.64
A C 0.86
I C 0.91
N C 0.88
D E 0.57
K E 0.81
G E 0.78
D E 0.66
T E 0.55
V C 0.53
Y C 0.64
R C 0.76
P C 0.80
V C 0.83
G C 0.82
L C 0.50
P H 0.56
D H 0.64
P H 0.88
D H 0.93
K H 0.95
V H 0.95
Q H 0.95
R H 0.94
D H 0.91
L H 0.87
A H 0.77
S H 0.66
Q H 0.67
C H 0.69
A H 0.68
S H 0.59
M C 0.53
L C 0.70
N C 0.86
V C 0.84
A C 0.82
L C 0.76
R C 0.77
P C 0.71
E C 0.55
M E 0.73
Q E 0.91
L E 0.94
E E 0.95
Q E 0.86
V E 0.65
G C 0.93
G C 0.95
K C 0.56
T E 0.90
L E 0.97
L E 0.98
V E 0.98
V E 0.97
Y E 0.90
V E 0.58
P C 0.81
E C 0.88
A C 0.89
D C 0.91
V C 0.65
T C 0.67
H C 0.71
K C 0.85
P C 0.76
I E 0.81
Y E 0.90
K E 0.83
K E 0.62
A C 0.72
T C 0.85
G C 0.84
L C 0.80
P C 0.77
G C 0.78
G C 0.64
A E 0.70
Y E 0.90
R E 0.91
R E 0.84
I E 0.51
G C 0.85
S C 0.91
S C 0.87
D C 0.78
Q C 0.63
R C 0.56
C C 0.80
V C 0.98
END