PFRMAT SS
TARGET T0403
AUTHOR SAM-T06-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0403.t04.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0403.t04.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0403.t04.str2.rdb  (weight 1.54758)
METHOD T0403.t04.alpha.rdb  (weight 0.659012)
METHOD T0403.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0403.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0403.t2k.str2.rdb  (weight 1.54758)
METHOD T0403.t2k.alpha.rdb  (weight 0.659012)
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 T0403.t04.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0403
METHOD Using neural net t04-2621-IDGaaH13-3-13-7-13-9-13-11-ebghstl-dssp-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    3	   13
METHOD	    7	   13
METHOD	    9	   13
METHOD	   11	    7 (1 EBGHSTL )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0403.t04-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(1.3 bits/column, 1)
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 1046
METHOD
METHOD ============================================
METHOD Comments from T0403.t04.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0403
METHOD Using neural net t04-2621-IDGaaH13-3-13-7-13-9-13-11-ebghtl-stride-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    3	   13
METHOD	    7	   13
METHOD	    9	   13
METHOD	   11	    6 (1 EBGHTL )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0403.t04-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(1.3 bits/column, 1)
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 1046
METHOD
METHOD ============================================
METHOD Comments from T0403.t04.str2.rdb
METHOD ============================================
METHOD TARGET T0403
METHOD Using neural net t04-2621-IDGaaH13-3-13-7-13-9-13-11-str2-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    3	   13
METHOD	    7	   13
METHOD	    9	   13
METHOD	   11	   13 (1 str2 )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0403.t04-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(1.3 bits/column, 1)
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 1046
METHOD
METHOD ============================================
METHOD Comments from T0403.t04.alpha.rdb
METHOD ============================================
METHOD TARGET T0403
METHOD Using neural net t04-2621-IDGaaH13-3-13-7-13-9-13-11-alpha-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    3	   13
METHOD	    7	   13
METHOD	    9	   13
METHOD	   11	   11 (1 ABCDEFGHIST )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0403.t04-thin90.a2m.gz
METHOD with weighted counts, using HenikoffWeight(1.3 bits/column, 1)
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 1046
METHOD
METHOD ============================================
METHOD Comments from T0403.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0403
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 T0403.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 1006
METHOD
METHOD ============================================
METHOD Comments from T0403.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0403
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 T0403.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 1006
METHOD
METHOD ============================================
METHOD Comments from T0403.t2k.str2.rdb
METHOD ============================================
METHOD TARGET T0403
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-str2-from-empty.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 str2 )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0403.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 1006
METHOD
METHOD ============================================
METHOD Comments from T0403.t2k.alpha.rdb
METHOD ============================================
METHOD TARGET T0403
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-alpha-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   15
METHOD	    7	   15
METHOD	    9	   15
METHOD	   13	   11 (1 ABCDEFGHIST )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0403.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 1006
METHOD
METHOD ============================================
MODEL 1
M C 0.73
G C 0.60
R C 0.57
D C 0.59
L C 0.57
Q E 0.57
V E 0.78
T E 0.88
L E 0.91
Y E 0.85
G E 0.84
T E 0.89
I E 0.87
K E 0.80
A E 0.71
G E 0.73
V E 0.82
E E 0.82
V E 0.79
S E 0.70
R C 0.50
V C 0.68
K C 0.71
D C 0.74
A C 0.76
G C 0.76
T C 0.77
Y C 0.76
K C 0.72
A C 0.68
Q C 0.73
G C 0.76
G C 0.67
K C 0.50
S E 0.64
K E 0.73
T E 0.72
A E 0.64
T E 0.51
Q C 0.53
I C 0.64
A C 0.67
D C 0.69
F C 0.70
G C 0.67
S C 0.58
K E 0.49
I E 0.50
G E 0.50
F E 0.68
K E 0.66
G E 0.67
Q E 0.67
E E 0.65
D E 0.55
L C 0.69
G C 0.82
N C 0.86
G C 0.77
M E 0.58
K E 0.85
A E 0.92
I E 0.92
W E 0.92
Q E 0.92
L E 0.89
E E 0.77
Q E 0.47
K C 0.57
A E 0.54
S C 0.53
I C 0.62
A C 0.77
G C 0.84
T C 0.86
N C 0.82
S C 0.80
G C 0.70
W C 0.53
G C 0.50
N C 0.47
R E 0.52
Q E 0.69
S E 0.76
F E 0.82
I E 0.78
G E 0.73
L E 0.62
K C 0.52
G C 0.78
G C 0.78
F C 0.59
G E 0.59
T E 0.84
V E 0.88
R E 0.87
A E 0.77
G E 0.55
N E 0.47
L C 0.49
N C 0.61
T C 0.74
V H 0.59
L H 0.67
K H 0.69
D H 0.63
S H 0.56
G C 0.43
D C 0.55
N C 0.60
V C 0.62
N C 0.76
A C 0.64
W C 0.66
E C 0.63
S C 0.63
G C 0.63
S C 0.64
N C 0.63
T C 0.62
E C 0.60
D C 0.61
V C 0.53
L C 0.54
G C 0.50
L C 0.51
G C 0.55
T C 0.60
I C 0.63
G C 0.67
R C 0.69
V C 0.64
E C 0.55
S C 0.53
R C 0.53
E C 0.69
I C 0.64
S E 0.73
V E 0.88
R E 0.89
Y E 0.85
D E 0.73
S C 0.55
P C 0.69
V C 0.69
F C 0.59
A C 0.74
G C 0.60
F E 0.74
S E 0.86
G E 0.89
S E 0.90
V E 0.90
Q E 0.90
Y E 0.88
V E 0.78
P E 0.55
R C 0.69
D C 0.73
N C 0.71
A C 0.73
N C 0.77
D C 0.75
V C 0.70
D C 0.70
K C 0.74
Y C 0.77
K C 0.78
H C 0.63
T E 0.70
K E 0.83
S E 0.88
S E 0.88
R E 0.89
E E 0.89
S E 0.87
Y E 0.81
H E 0.60
A C 0.61
G C 0.74
L C 0.56
K E 0.68
Y E 0.79
E E 0.83
N E 0.84
A E 0.85
G E 0.83
F E 0.80
F E 0.70
G E 0.60
Q E 0.44
Y C 0.54
A C 0.66
G C 0.62
S C 0.59
F C 0.57
A C 0.55
K C 0.51
Y C 0.54
A C 0.56
D C 0.56
L C 0.57
N C 0.60
T C 0.61
D C 0.63
A C 0.65
E C 0.66
R C 0.67
V C 0.67
A C 0.63
V C 0.58
N C 0.56
T C 0.59
A C 0.61
N C 0.58
A C 0.59
H C 0.62
P C 0.63
V C 0.53
K C 0.48
D C 0.41
Y E 0.49
Q E 0.69
V E 0.82
H E 0.85
R E 0.89
V E 0.88
V E 0.87
A E 0.88
G E 0.88
Y E 0.87
D E 0.82
A E 0.59
N C 0.67
D C 0.50
L E 0.82
Y E 0.89
V E 0.91
S E 0.91
V E 0.91
A E 0.91
G E 0.90
Q E 0.85
Y E 0.80
E E 0.66
A E 0.56
A C 0.47
K C 0.59
N C 0.70
N C 0.70
E C 0.68
V C 0.68
G C 0.68
S C 0.65
I C 0.62
K C 0.65
G C 0.69
K C 0.64
K C 0.59
H C 0.56
E C 0.49
Q C 0.50
T C 0.52
Q E 0.76
V E 0.88
A E 0.91
A E 0.90
T E 0.89
A E 0.88
A E 0.88
Y E 0.86
R E 0.78
F E 0.49
G C 0.81
N C 0.65
V C 0.51
T H 0.41
P H 0.36
R E 0.51
V E 0.64
S E 0.69
Y E 0.72
A E 0.74
H E 0.75
G E 0.74
F E 0.65
K E 0.50
A C 0.55
K C 0.63
V C 0.62
N C 0.67
G C 0.69
V C 0.69
K C 0.70
D C 0.74
A C 0.77
N C 0.77
Y C 0.74
Q C 0.66
Y C 0.50
D E 0.56
Q E 0.86
V E 0.91
I E 0.92
V E 0.90
G E 0.88
A E 0.87
D E 0.85
Y E 0.78
D E 0.72
F E 0.56
S C 0.72
K C 0.72
R C 0.63
T C 0.41
S E 0.55
A E 0.68
L E 0.71
V E 0.73
S E 0.76
A E 0.72
G E 0.67
W E 0.69
L E 0.60
K E 0.54
Q C 0.43
G C 0.74
K C 0.85
G C 0.85
A C 0.77
G C 0.78
K C 0.61
V E 0.54
E E 0.62
Q E 0.53
T C 0.55
A C 0.65
S C 0.69
M C 0.88
END