PFRMAT SS
TARGET T0492
AUTHOR SAM-T02-server 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0492.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0492.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0492.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 T0492.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0492
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 T0492.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 342
METHOD
METHOD ============================================
METHOD Comments from T0492.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0492
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 T0492.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 342
METHOD
METHOD ============================================
METHOD Comments from T0492.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0492
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 T0492.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 342
METHOD
METHOD ============================================
MODEL 1
M C 0.98
F C 0.77
S C 0.73
L H 0.78
R H 0.75
D H 0.74
A C 0.82
K C 0.94
C C 0.91
G C 0.94
Q C 0.74
T E 0.79
V E 0.94
K E 0.97
V E 0.96
V E 0.96
K E 0.94
L E 0.83
H E 0.51
G C 0.85
T C 0.85
G H 0.60
A H 0.87
L H 0.94
K H 0.96
R H 0.96
R H 0.97
I H 0.97
M H 0.96
D H 0.91
M H 0.56
G C 0.94
I C 0.88
T C 0.88
R C 0.93
G C 0.95
C C 0.59
E E 0.89
I E 0.96
Y E 0.97
I E 0.97
R E 0.97
K E 0.95
V E 0.81
A C 0.54
P C 0.83
L C 0.90
G C 0.93
D C 0.88
P C 0.65
I E 0.88
Q E 0.97
I E 0.97
N E 0.97
V E 0.95
R C 0.74
G C 0.88
Y E 0.71
E E 0.90
L E 0.93
S E 0.92
L E 0.85
R E 0.48
K H 0.68
S H 0.70
A H 0.74
A H 0.68
E H 0.49
M C 0.42
I E 0.51
E E 0.62
V C 0.51
E C 0.97
END