PFRMAT SS
TARGET T0448
AUTHOR SAM-T06-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0448.t04.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0448.t04.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0448.t04.str2.rdb  (weight 1.54758)
METHOD T0448.t04.alpha.rdb  (weight 0.659012)
METHOD T0448.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0448.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0448.t2k.str2.rdb  (weight 1.54758)
METHOD T0448.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 T0448.t04.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 2322
METHOD
METHOD ============================================
METHOD Comments from T0448.t04.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 2322
METHOD
METHOD ============================================
METHOD Comments from T0448.t04.str2.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 2322
METHOD
METHOD ============================================
METHOD Comments from T0448.t04.alpha.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 2322
METHOD
METHOD ============================================
METHOD Comments from T0448.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 124
METHOD
METHOD ============================================
METHOD Comments from T0448.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 124
METHOD
METHOD ============================================
METHOD Comments from T0448.t2k.str2.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 124
METHOD
METHOD ============================================
METHOD Comments from T0448.t2k.alpha.rdb
METHOD ============================================
METHOD TARGET T0448
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 T0448.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 124
METHOD
METHOD ============================================
MODEL 1
M C 0.85
I C 0.59
A C 0.51
M C 0.44
I C 0.36
V H 0.37
K H 0.41
G H 0.42
G H 0.54
L H 0.62
A H 0.65
M H 0.69
A H 0.66
I H 0.61
S H 0.54
N C 0.53
G C 0.64
H C 0.67
V C 0.75
S C 0.80
F C 0.81
K C 0.60
R E 0.79
P E 0.91
A E 0.92
W E 0.91
L E 0.78
G C 0.52
D C 0.73
S C 0.65
I C 0.52
T C 0.54
A C 0.62
N C 0.72
N C 0.75
G C 0.78
L C 0.76
A C 0.77
T C 0.76
V C 0.76
H C 0.70
Y C 0.65
H H 0.66
D H 0.88
I H 0.91
L H 0.92
A H 0.91
A H 0.89
D H 0.82
W H 0.68
D C 0.63
V C 0.86
E C 0.62
R E 0.70
S E 0.87
D E 0.86
N E 0.81
L E 0.60
G E 0.47
I C 0.63
S C 0.72
G C 0.65
S C 0.50
T H 0.49
I H 0.68
G H 0.68
S H 0.68
R H 0.69
Y H 0.71
D H 0.70
A H 0.69
M H 0.66
A H 0.64
V H 0.56
R H 0.60
Y H 0.64
Q H 0.65
A H 0.63
I H 0.58
P C 0.55
E C 0.72
D C 0.84
A C 0.88
D C 0.82
F E 0.92
I E 0.93
A E 0.93
V E 0.93
F E 0.85
G E 0.50
G C 0.65
V C 0.62
N C 0.59
D C 0.54
Y C 0.56
G C 0.60
R C 0.66
D C 0.72
Q C 0.73
P C 0.70
L C 0.66
G C 0.73
Q C 0.73
Y C 0.73
G C 0.80
D C 0.82
C C 0.76
D C 0.84
M H 0.88
T H 0.89
T H 0.92
F H 0.92
Y H 0.95
G H 0.95
A H 0.95
L H 0.96
M H 0.96
M H 0.96
L H 0.96
L H 0.96
T H 0.96
G H 0.94
L H 0.92
Q H 0.87
T H 0.72
N C 0.57
W C 0.86
P C 0.88
T C 0.77
V E 0.53
P E 0.84
K E 0.92
L E 0.91
F E 0.89
I E 0.77
S C 0.52
A C 0.69
I C 0.72
H C 0.73
I C 0.75
G C 0.71
S C 0.56
D C 0.54
F C 0.57
G C 0.67
G C 0.71
S C 0.67
F C 0.64
S C 0.60
A C 0.54
V H 0.48
T H 0.53
N H 0.55
G H 0.58
L H 0.63
G H 0.69
Y H 0.78
R H 0.82
Q H 0.89
S H 0.91
D H 0.92
Y H 0.94
E H 0.95
A H 0.95
A H 0.96
I H 0.96
A H 0.96
Q H 0.96
M H 0.95
T H 0.94
A H 0.90
D H 0.80
Y C 0.60
G C 0.93
V C 0.90
P C 0.70
H E 0.70
L E 0.74
S E 0.59
L C 0.46
Y C 0.47
R H 0.55
D H 0.59
A H 0.51
G C 0.48
M C 0.48
T C 0.56
F C 0.51
A C 0.55
I C 0.56
P H 0.51
A H 0.49
Q H 0.51
A H 0.62
A H 0.61
I H 0.54
Y C 0.56
S C 0.73
V C 0.77
D C 0.82
T C 0.82
L C 0.74
H C 0.79
P C 0.84
N C 0.86
N H 0.87
A H 0.92
G H 0.93
H H 0.95
R H 0.96
V H 0.96
I H 0.95
A H 0.96
R H 0.95
K H 0.95
L H 0.95
Q H 0.95
S H 0.95
F H 0.94
L H 0.93
D H 0.89
S H 0.79
H H 0.65
F H 0.48
L C 0.52
E C 0.59
H C 0.65
H C 0.69
H C 0.72
H C 0.74
H C 0.81
H C 0.91
END