PFRMAT SS
TARGET T0404
AUTHOR SAM-T06-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0404.t04.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0404.t04.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0404.t04.str2.rdb  (weight 1.54758)
METHOD T0404.t04.alpha.rdb  (weight 0.659012)
METHOD T0404.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0404.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0404.t2k.str2.rdb  (weight 1.54758)
METHOD T0404.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 T0404.t04.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 82.5734
METHOD
METHOD ============================================
METHOD Comments from T0404.t04.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 82.5734
METHOD
METHOD ============================================
METHOD Comments from T0404.t04.str2.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 82.5734
METHOD
METHOD ============================================
METHOD Comments from T0404.t04.alpha.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 82.5734
METHOD
METHOD ============================================
METHOD Comments from T0404.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 47
METHOD
METHOD ============================================
METHOD Comments from T0404.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 47
METHOD
METHOD ============================================
METHOD Comments from T0404.t2k.str2.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 47
METHOD
METHOD ============================================
METHOD Comments from T0404.t2k.alpha.rdb
METHOD ============================================
METHOD TARGET T0404
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 T0404.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 47
METHOD
METHOD ============================================
MODEL 1
M C 0.90
S C 0.78
K C 0.71
R C 0.59
A C 0.52
N E 0.55
K E 0.75
L E 0.82
V E 0.85
I E 0.87
V E 0.82
T E 0.53
E C 0.61
K H 0.61
V H 0.73
L H 0.74
L H 0.85
K H 0.85
K H 0.92
V H 0.95
A H 0.96
K H 0.96
I H 0.96
I H 0.96
E H 0.95
E H 0.92
A C 0.53
G C 0.93
A C 0.89
T C 0.81
G E 0.55
Y E 0.82
T E 0.89
V E 0.86
V E 0.70
D C 0.53
T C 0.65
G C 0.79
G C 0.80
K C 0.70
G C 0.74
S C 0.75
R C 0.78
N C 0.76
V C 0.56
R C 0.48
S C 0.61
T C 0.75
G C 0.76
K C 0.67
P C 0.61
N C 0.59
T C 0.60
S C 0.56
D C 0.49
T C 0.47
D C 0.42
S C 0.45
N C 0.49
V C 0.48
K E 0.67
F E 0.83
E E 0.89
V E 0.92
L E 0.90
T E 0.85
E E 0.62
N C 0.81
R H 0.61
E H 0.86
M H 0.89
A H 0.90
E H 0.92
K H 0.91
I H 0.92
A H 0.93
D H 0.92
Q H 0.90
V H 0.86
A H 0.81
I H 0.75
K H 0.74
F H 0.67
F H 0.50
T C 0.54
D C 0.77
Y C 0.75
A C 0.50
G E 0.85
I E 0.92
I E 0.92
Y E 0.92
I E 0.82
C E 0.59
E C 0.53
A E 0.57
E E 0.74
V E 0.80
L E 0.68
Y C 0.55
G C 0.58
R C 0.58
T C 0.45
F C 0.55
C C 0.67
G C 0.84
P C 0.84
D C 0.87
G C 0.88
C C 0.90
END