PFRMAT SS
TARGET T0550
AUTHOR SAM-T06-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0550.t04.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0550.t04.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0550.t04.str2.rdb  (weight 1.54758)
METHOD T0550.t04.alpha.rdb  (weight 0.659012)
METHOD T0550.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0550.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0550.t2k.str2.rdb  (weight 1.54758)
METHOD T0550.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 T0550.t04.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 604
METHOD
METHOD ============================================
METHOD Comments from T0550.t04.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 604
METHOD
METHOD ============================================
METHOD Comments from T0550.t04.str2.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 604
METHOD
METHOD ============================================
METHOD Comments from T0550.t04.alpha.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 604
METHOD
METHOD ============================================
METHOD Comments from T0550.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 41
METHOD
METHOD ============================================
METHOD Comments from T0550.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 41
METHOD
METHOD ============================================
METHOD Comments from T0550.t2k.str2.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 41
METHOD
METHOD ============================================
METHOD Comments from T0550.t2k.alpha.rdb
METHOD ============================================
METHOD TARGET T0550
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 T0550.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 41
METHOD
METHOD ============================================
MODEL 1
M C 0.67
K H 0.70
N H 0.85
I H 0.91
Y H 0.94
I H 0.95
Y H 0.96
L H 0.96
S H 0.96
L H 0.96
L H 0.96
A H 0.96
V H 0.96
I H 0.95
V H 0.93
L H 0.87
G H 0.70
T C 0.51
A C 0.72
C C 0.79
N C 0.79
N C 0.51
E H 0.67
W H 0.66
E H 0.72
D H 0.80
E H 0.78
Q H 0.73
Y H 0.66
E H 0.56
Q H 0.43
Y E 0.47
V E 0.60
S E 0.66
F E 0.65
K E 0.59
A C 0.50
P C 0.61
I C 0.67
A C 0.71
S C 0.71
G C 0.70
S C 0.60
D C 0.53
G E 0.54
V E 0.72
T E 0.78
T E 0.83
I E 0.86
Y E 0.88
V E 0.87
R E 0.86
Y E 0.82
K C 0.51
D C 0.84
N C 0.92
G C 0.88
K E 0.52
V E 0.86
T E 0.89
Y E 0.90
Q E 0.90
L E 0.89
P E 0.88
I E 0.91
I E 0.91
V E 0.88
S E 0.64
G C 0.57
S C 0.64
T C 0.68
V C 0.73
N C 0.80
S C 0.78
Q C 0.78
D C 0.70
R E 0.63
D E 0.84
I E 0.89
H E 0.90
I E 0.87
A E 0.81
V E 0.50
D C 0.83
K H 0.64
D H 0.67
T H 0.86
L H 0.91
K H 0.93
T H 0.93
L H 0.92
N H 0.88
I H 0.85
E H 0.80
R H 0.66
F C 0.50
S C 0.55
L C 0.56
Y C 0.69
R C 0.54
P C 0.48
E H 0.46
L C 0.46
W C 0.45
Y E 0.44
T E 0.52
E E 0.46
M C 0.65
E C 0.73
E C 0.54
D C 0.55
K C 0.53
Y E 0.50
E E 0.59
F C 0.55
P C 0.75
E C 0.77
T C 0.57
V E 0.69
H E 0.81
I E 0.66
P C 0.75
A C 0.88
G C 0.89
S C 0.68
C E 0.61
V E 0.71
E E 0.75
L E 0.80
L E 0.76
N E 0.71
I E 0.78
D E 0.81
F E 0.73
N C 0.55
L C 0.66
Q C 0.73
D C 0.72
I C 0.72
D C 0.78
M C 0.70
L C 0.70
E C 0.67
K C 0.63
W E 0.63
V E 0.74
L E 0.67
P E 0.66
L E 0.83
T E 0.88
I E 0.88
V E 0.72
D C 0.57
D C 0.82
G C 0.85
S C 0.83
Y C 0.77
A C 0.60
Y E 0.50
Q E 0.52
S C 0.49
H C 0.72
P C 0.69
R C 0.73
K C 0.69
N C 0.64
Y C 0.40
A E 0.59
K E 0.71
A E 0.76
L E 0.75
L E 0.72
K E 0.70
V E 0.66
V E 0.58
P E 0.57
F E 0.50
N C 0.61
N C 0.72
Y C 0.76
S C 0.70
G C 0.70
S C 0.56
Y E 0.47
T C 0.58
A C 0.60
S C 0.56
S E 0.47
M E 0.66
K E 0.79
V E 0.83
Y E 0.83
T E 0.81
Y E 0.66
I C 0.56
N C 0.73
G C 0.80
K C 0.83
P C 0.79
D C 0.75
T C 0.76
N C 0.73
A C 0.61
R E 0.54
T E 0.65
T E 0.71
D E 0.73
K E 0.80
R E 0.81
T E 0.81
G E 0.77
Y E 0.80
V E 0.82
V E 0.72
D C 0.51
N C 0.74
N C 0.74
S E 0.63
I E 0.81
F E 0.88
F E 0.85
Y E 0.80
A E 0.65
G E 0.53
L E 0.58
I E 0.55
N C 0.53
E H 0.46
D H 0.48
M H 0.55
D H 0.62
K H 0.56
D H 0.56
M H 0.47
R C 0.55
K C 0.65
K C 0.57
Y E 0.72
K E 0.84
I E 0.88
N E 0.89
V E 0.83
H E 0.63
F C 0.69
K C 0.84
E C 0.82
D C 0.79
G C 0.66
T E 0.63
L E 0.82
D E 0.86
M E 0.83
K E 0.80
Q E 0.71
D E 0.56
D C 0.61
P C 0.74
S C 0.78
N C 0.78
E C 0.76
M C 0.58
E C 0.48
F E 0.65
E E 0.66
L E 0.59
I C 0.59
G C 0.78
T C 0.81
P C 0.74
T C 0.58
Y E 0.62
S E 0.71
S E 0.75
T E 0.72
S E 0.70
V E 0.68
M E 0.53
D C 0.77
A C 0.81
T C 0.85
R C 0.83
P C 0.68
Y E 0.53
L E 0.74
E E 0.81
R E 0.82
R E 0.87
Y E 0.90
V E 0.90
Q E 0.90
I E 0.83
M E 0.68
F C 0.49
E E 0.49
Y E 0.49
D C 0.51
F C 0.56
Q C 0.65
D C 0.66
F C 0.61
T C 0.60
Y C 0.59
G C 0.77
G C 0.83
S C 0.87
G C 0.83
T C 0.68
E C 0.56
V C 0.50
I E 0.59
P E 0.67
I E 0.77
K E 0.78
Y E 0.84
R E 0.90
V E 0.90
A E 0.84
G E 0.82
S E 0.86
M E 0.86
T E 0.86
L E 0.83
L E 0.84
R E 0.69
N E 0.54
I C 0.48
N C 0.62
T C 0.65
Q C 0.64
I C 0.75
P C 0.86
D C 0.79
E H 0.71
D H 0.79
Q H 0.74
Q H 0.69
I H 0.56
E C 0.53
W C 0.89
END