PFRMAT SS
TARGET T0634
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0634.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0634.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0634.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 T0634.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0634
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 T0634.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 1163
METHOD
METHOD ============================================
METHOD Comments from T0634.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0634
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 T0634.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 1163
METHOD
METHOD ============================================
METHOD Comments from T0634.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0634
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 T0634.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 1163
METHOD
METHOD ============================================
MODEL 1
M C 0.97
S C 0.90
L C 0.86
K E 0.55
K E 0.92
I E 0.97
L E 0.97
I E 0.91
I C 0.51
D C 0.92
Q C 0.86
Q H 0.82
D H 0.91
F H 0.95
S H 0.97
R H 0.97
I H 0.97
E H 0.97
L H 0.97
K H 0.96
N H 0.95
F H 0.92
L H 0.86
D H 0.67
S C 0.71
E C 0.98
Y C 0.77
L E 0.80
V E 0.94
I E 0.94
E E 0.91
S E 0.65
K C 0.83
N C 0.94
E H 0.69
K H 0.96
E H 0.97
A H 0.97
L H 0.98
E H 0.97
Q H 0.97
I H 0.97
D H 0.94
H H 0.77
H H 0.52
H C 0.95
P C 0.96
D C 0.89
L E 0.94
V E 0.98
I E 0.98
L E 0.95
D E 0.66
M C 0.59
D C 0.66
I C 0.84
I C 0.86
G C 0.91
E C 0.91
N C 0.90
S H 0.82
P H 0.97
N H 0.97
L H 0.97
C H 0.97
L H 0.97
K H 0.96
L H 0.94
K H 0.85
R H 0.63
S C 0.83
K C 0.74
G C 0.76
L C 0.61
K C 0.82
N C 0.87
V C 0.81
P C 0.61
L E 0.96
I E 0.97
L E 0.97
L E 0.91
F E 0.68
S C 0.61
S C 0.78
E C 0.79
H C 0.64
K H 0.85
E H 0.91
A H 0.92
I H 0.94
V H 0.92
N H 0.89
G H 0.87
L H 0.85
H H 0.74
S C 0.48
G C 0.87
A C 0.83
D C 0.79
D C 0.48
Y E 0.55
L E 0.62
T C 0.53
K C 0.83
P C 0.86
F C 0.89
N C 0.93
R H 0.93
N H 0.97
D H 0.97
L H 0.98
L H 0.98
S H 0.98
R H 0.98
I H 0.98
E H 0.98
I H 0.98
H H 0.97
L H 0.97
R H 0.94
T H 0.91
Q H 0.89
N H 0.83
Y H 0.83
Y H 0.86
S H 0.88
D H 0.88
L H 0.85
R H 0.83
K H 0.75
N H 0.52
E C 0.58
G C 0.65
H C 0.60
H C 0.65
H C 0.70
H C 0.73
H C 0.81
H C 0.98
END