PFRMAT SS
TARGET T0408
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0408.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0408.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0408.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 T0408.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0408
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 T0408.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 332
METHOD
METHOD ============================================
METHOD Comments from T0408.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0408
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 T0408.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 332
METHOD
METHOD ============================================
METHOD Comments from T0408.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0408
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 T0408.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 332
METHOD
METHOD ============================================
MODEL 1
M C 0.96
K C 0.76
N C 0.67
E C 0.50
V C 0.48
F H 0.48
F H 0.59
G H 0.85
E H 0.92
G H 0.94
M H 0.94
K H 0.94
V H 0.94
V H 0.93
K H 0.89
E H 0.81
K H 0.77
Y C 0.69
P H 0.84
D H 0.87
L H 0.95
Y H 0.97
D H 0.97
I H 0.97
I H 0.97
V H 0.96
K H 0.93
L H 0.88
N H 0.78
D H 0.70
T H 0.70
V H 0.61
F H 0.47
T C 0.67
G C 0.79
K C 0.86
T C 0.84
L C 0.86
D C 0.91
Y H 0.92
K H 0.95
T H 0.97
Q H 0.97
K H 0.97
L H 0.98
I H 0.98
A H 0.98
I H 0.98
G H 0.98
I H 0.98
V H 0.98
A H 0.97
S H 0.91
R H 0.63
C C 0.81
D C 0.89
E H 0.86
V H 0.92
A H 0.95
I H 0.97
E H 0.97
K H 0.97
Q H 0.97
M H 0.97
K H 0.97
S H 0.97
A H 0.97
M H 0.97
K H 0.97
E H 0.89
L C 0.65
G C 0.98
I C 0.98
T C 0.97
K H 0.93
E H 0.96
E H 0.97
I H 0.98
A H 0.98
D H 0.97
V H 0.97
L H 0.98
R H 0.98
V H 0.98
V H 0.98
L H 0.97
L H 0.97
T H 0.90
S H 0.76
G H 0.63
M H 0.77
P H 0.97
A H 0.97
F H 0.97
T H 0.97
K H 0.97
A H 0.97
M H 0.97
K H 0.96
I H 0.95
L H 0.92
E H 0.79
K H 0.59
L C 0.94
END