PFRMAT SS
TARGET T0392
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0392.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0392.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0392.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 T0392.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0392
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 T0392.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 317
METHOD
METHOD ============================================
METHOD Comments from T0392.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0392
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 T0392.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 317
METHOD
METHOD ============================================
METHOD Comments from T0392.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0392
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 T0392.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 317
METHOD
METHOD ============================================
MODEL 1
M C 0.93
H C 0.76
H C 0.69
H C 0.66
H C 0.62
H C 0.59
H C 0.60
S C 0.69
S C 0.75
G C 0.84
V C 0.84
D C 0.75
L C 0.74
G C 0.65
T C 0.68
E C 0.76
N C 0.75
L C 0.76
Y C 0.78
F C 0.82
Q C 0.83
S C 0.82
M C 0.81
P C 0.64
R E 0.82
S E 0.94
I E 0.96
R E 0.96
F E 0.92
T E 0.76
A C 0.67
E C 0.90
E C 0.90
G C 0.87
D C 0.71
L E 0.56
G E 0.85
F E 0.92
T E 0.95
L E 0.92
R E 0.72
G C 0.80
N C 0.92
A C 0.84
P C 0.55
V E 0.78
Q E 0.95
V E 0.94
H E 0.92
F E 0.88
L E 0.68
D C 0.82
P C 0.96
Y C 0.96
C C 0.92
S H 0.78
A H 0.85
S H 0.85
V H 0.79
A C 0.63
G C 0.94
A C 0.95
R C 0.89
E C 0.82
G C 0.89
D C 0.66
Y E 0.88
I E 0.97
V E 0.97
S E 0.95
I E 0.88
Q C 0.86
L C 0.92
V E 0.53
D E 0.59
C C 0.47
K C 0.69
W C 0.76
L C 0.78
T C 0.83
L H 0.94
S H 0.97
E H 0.97
V H 0.98
M H 0.98
K H 0.97
L H 0.97
L H 0.96
K H 0.87
S H 0.57
F C 0.80
G C 0.93
E C 0.91
D C 0.67
E E 0.67
I E 0.88
E E 0.96
M E 0.97
K E 0.97
V E 0.92
V E 0.70
S C 0.68
L C 0.84
L C 0.82
D C 0.80
E C 0.80
V C 0.69
T C 0.72
F C 0.94
END