PFRMAT SS
TARGET T0418
AUTHOR SAM-T06-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0418.t04.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0418.t04.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0418.t04.str2.rdb  (weight 1.54758)
METHOD T0418.t04.alpha.rdb  (weight 0.659012)
METHOD T0418.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0418.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0418.t2k.str2.rdb  (weight 1.54758)
METHOD T0418.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 T0418.t04.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2117
METHOD
METHOD ============================================
METHOD Comments from T0418.t04.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2117
METHOD
METHOD ============================================
METHOD Comments from T0418.t04.str2.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2117
METHOD
METHOD ============================================
METHOD Comments from T0418.t04.alpha.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2117
METHOD
METHOD ============================================
METHOD Comments from T0418.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2182
METHOD
METHOD ============================================
METHOD Comments from T0418.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2182
METHOD
METHOD ============================================
METHOD Comments from T0418.t2k.str2.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2182
METHOD
METHOD ============================================
METHOD Comments from T0418.t2k.alpha.rdb
METHOD ============================================
METHOD TARGET T0418
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 T0418.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 2182
METHOD
METHOD ============================================
MODEL 1
M C 0.89
K C 0.75
Y C 0.51
T E 0.76
V E 0.89
Y E 0.92
L E 0.92
F E 0.88
D E 0.60
F C 0.71
D C 0.84
Y C 0.75
T C 0.55
L E 0.54
A C 0.47
D C 0.69
S C 0.69
S H 0.78
R H 0.92
G H 0.93
I H 0.94
V H 0.95
T H 0.95
C H 0.96
F H 0.96
R H 0.96
S H 0.96
V H 0.96
L H 0.95
E H 0.93
R H 0.87
H C 0.51
G C 0.92
Y C 0.91
T C 0.87
G C 0.83
I C 0.83
T H 0.54
D H 0.87
D H 0.89
M H 0.90
I H 0.90
K H 0.88
R H 0.83
T H 0.70
I H 0.50
G C 0.62
K C 0.60
T H 0.49
L H 0.78
E H 0.87
E H 0.89
S H 0.90
F H 0.89
S H 0.87
I H 0.83
L H 0.71
T H 0.55
G C 0.51
I C 0.62
T C 0.68
D C 0.67
A H 0.64
D H 0.71
Q H 0.72
L H 0.79
E H 0.86
S H 0.89
F H 0.89
R H 0.92
Q H 0.93
E H 0.93
Y H 0.93
S H 0.94
K H 0.94
E H 0.94
A H 0.93
D H 0.91
I H 0.88
Y H 0.79
M H 0.62
N C 0.50
A C 0.59
N C 0.71
T C 0.79
I C 0.79
L C 0.77
F C 0.85
P C 0.68
D C 0.70
T H 0.86
L H 0.95
P H 0.96
T H 0.96
L H 0.96
T H 0.96
H H 0.96
L H 0.95
K H 0.94
K H 0.86
Q C 0.69
G C 0.95
I C 0.91
R C 0.51
I E 0.91
G E 0.93
I E 0.93
I E 0.88
S C 0.49
T C 0.88
K C 0.88
Y C 0.70
R H 0.81
F H 0.89
R H 0.91
I H 0.95
L H 0.96
S H 0.96
F H 0.96
L H 0.96
R H 0.94
N H 0.86
H C 0.57
M C 0.90
P C 0.80
D C 0.55
D H 0.49
W C 0.52
F C 0.65
D C 0.54
I E 0.90
I E 0.92
I E 0.89
G E 0.58
G C 0.70
E C 0.59
D H 0.48
V C 0.51
T C 0.66
H C 0.74
H C 0.83
K C 0.82
P C 0.83
D C 0.83
P H 0.69
E H 0.88
G H 0.94
L H 0.96
L H 0.96
L H 0.96
A H 0.96
I H 0.96
D H 0.94
R H 0.90
L H 0.49
K C 0.93
A C 0.92
C C 0.92
P H 0.61
E H 0.62
E H 0.50
V E 0.79
L E 0.89
Y E 0.91
I E 0.82
G E 0.51
D C 0.81
S C 0.90
T H 0.65
V H 0.78
D H 0.86
A H 0.95
G H 0.95
T H 0.96
A H 0.95
A H 0.94
A H 0.90
A C 0.58
G C 0.94
V C 0.90
S C 0.51
F E 0.92
T E 0.92
G E 0.92
V E 0.87
T E 0.58
S C 0.81
G C 0.85
M C 0.83
T C 0.82
T C 0.77
A H 0.67
Q H 0.78
E H 0.85
F H 0.86
Q H 0.83
A H 0.73
Y H 0.48
P C 0.81
Y C 0.84
D C 0.70
R E 0.79
I E 0.87
I E 0.76
S C 0.69
T C 0.88
L H 0.79
G H 0.90
Q H 0.91
L H 0.94
I H 0.94
S H 0.92
V H 0.91
P H 0.88
E H 0.82
D H 0.70
K H 0.52
S C 0.75
G C 0.90
C C 0.89
P C 0.87
L C 0.91
END