PFRMAT SS
TARGET T0482
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0482.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0482.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0482.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 T0482.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0482
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 T0482.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 13
METHOD
METHOD ============================================
METHOD Comments from T0482.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0482
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 T0482.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 13
METHOD
METHOD ============================================
METHOD Comments from T0482.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0482
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 T0482.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 13
METHOD
METHOD ============================================
MODEL 1
M C 0.97
F C 0.85
E C 0.85
P C 0.83
G C 0.69
H E 0.68
L E 0.76
H E 0.77
L E 0.61
V C 0.46
S C 0.60
L C 0.77
P C 0.84
G C 0.88
L C 0.84
D C 0.86
Q C 0.85
Q C 0.82
D C 0.72
I E 0.62
N E 0.77
I E 0.90
H E 0.92
I E 0.93
R E 0.92
Y E 0.87
E E 0.79
V E 0.70
R E 0.58
Q C 0.60
N C 0.85
A C 0.80
E C 0.79
S C 0.77
G C 0.86
A C 0.60
Y E 0.89
V E 0.93
H E 0.96
F E 0.95
D E 0.94
M E 0.95
D E 0.95
G E 0.94
E E 0.92
I E 0.82
D C 0.85
G C 0.91
K C 0.61
P C 0.50
F C 0.59
S C 0.58
D C 0.52
S C 0.53
F E 0.52
E E 0.53
L C 0.72
P C 0.78
R H 0.63
D H 0.72
T H 0.79
A H 0.78
F H 0.82
N H 0.81
F H 0.88
A H 0.94
S H 0.94
D H 0.95
A H 0.97
T H 0.97
R H 0.97
V H 0.97
A H 0.97
Q H 0.96
K H 0.90
H H 0.60
G C 0.92
L C 0.94
H C 0.93
P C 0.78
K C 0.75
F C 0.66
G C 0.62
A C 0.53
I C 0.47
T H 0.51
R H 0.56
V H 0.68
H H 0.68
K H 0.76
E H 0.76
Y H 0.82
D H 0.87
A H 0.88
M H 0.88
F H 0.92
E H 0.94
D H 0.91
I H 0.95
R H 0.96
A H 0.93
K H 0.90
L H 0.60
H C 0.91
A C 0.95
H C 0.95
P C 0.93
G C 0.94
E C 0.86
P C 0.55
V C 0.52
D C 0.80
L H 0.76
E H 0.81
R H 0.87
I H 0.66
I H 0.45
R C 0.45
H C 0.75
E C 0.98
END