PFRMAT SS
TARGET T0554
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0554.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0554.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0554.t2k.str.rdb  (weight 1.53983)
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 T0554.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0554
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 T0554.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 295
METHOD
METHOD ============================================
METHOD Comments from T0554.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0554
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 T0554.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 295
METHOD
METHOD ============================================
METHOD Comments from T0554.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0554
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-str-seeded.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 str )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0554.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 295
METHOD
METHOD ============================================
MODEL 1
M C 0.96
P C 0.84
V E 0.64
E E 0.74
L E 0.69
R C 0.67
A C 0.88
N C 0.95
W C 0.95
S C 0.97
E H 0.91
E H 0.94
D H 0.96
L H 0.97
E H 0.97
T H 0.97
V H 0.97
I H 0.97
R H 0.98
A H 0.98
V H 0.98
Y H 0.97
R H 0.97
Q H 0.96
V H 0.94
L H 0.83
G C 0.51
N C 0.68
D C 0.72
Y C 0.62
V C 0.59
M C 0.56
A C 0.48
S C 0.48
E C 0.51
R C 0.53
L H 0.52
V H 0.66
S H 0.70
A H 0.91
E H 0.94
S H 0.95
L H 0.94
L H 0.92
R H 0.82
N C 0.60
G C 0.91
K C 0.86
I E 0.53
T C 0.53
V H 0.92
R H 0.96
E H 0.97
F H 0.97
V H 0.97
R H 0.97
A H 0.95
V H 0.90
A H 0.65
K H 0.51
S C 0.64
E H 0.92
L H 0.93
Y H 0.94
K H 0.94
E H 0.90
K H 0.84
F H 0.69
L C 0.47
Y C 0.58
G C 0.65
N C 0.70
F C 0.68
Q H 0.64
T H 0.86
R H 0.94
V H 0.96
I H 0.97
E H 0.97
L H 0.98
N H 0.98
Y H 0.97
K H 0.96
H H 0.94
L H 0.88
L H 0.59
G C 0.91
R C 0.93
A C 0.93
P C 0.90
Y C 0.93
D C 0.94
E H 0.95
S H 0.97
E H 0.97
V H 0.97
I H 0.97
F H 0.97
H H 0.97
L H 0.97
D H 0.97
L H 0.97
Y H 0.97
E H 0.95
N H 0.90
E H 0.70
G C 0.68
F H 0.51
D H 0.72
A H 0.78
D H 0.80
I H 0.81
D H 0.82
S H 0.83
Y H 0.79
I H 0.61
D C 0.63
S H 0.56
P H 0.96
E H 0.97
Y H 0.97
T H 0.96
N H 0.93
S H 0.85
F H 0.56
G C 0.82
D C 0.77
W C 0.68
V C 0.59
V C 0.63
P C 0.61
Y C 0.56
Y C 0.64
R C 0.83
G C 0.98
END