PFRMAT SS
TARGET T0180
AUTHOR 4069-6308-1312 
METHOD This file is the result of combining several RDB files, specifically
METHOD T0180.t2k.dssp-ebghstl.rdb  (weight 1.53986)
METHOD T0180.t2k.stride-ebghtl.rdb  (weight 1.24869)
METHOD T0180.t2k.str.rdb  (weight 1.53983)
METHOD T0180.t2k.alpha.rdb  (weight 0.659012)
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 T0180.t2k.dssp-ebghstl.rdb
METHOD ============================================
METHOD TARGET T0180
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 T0180.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 1
METHOD
METHOD ============================================
METHOD Comments from T0180.t2k.stride-ebghtl.rdb
METHOD ============================================
METHOD TARGET T0180
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 T0180.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 1
METHOD
METHOD ============================================
METHOD Comments from T0180.t2k.str.rdb
METHOD ============================================
METHOD TARGET T0180
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 T0180.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 1
METHOD
METHOD ============================================
METHOD Comments from T0180.t2k.alpha.rdb
METHOD ============================================
METHOD TARGET T0180
METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-alpha-seeded.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   15
METHOD	    7	   15
METHOD	    9	   15
METHOD	   13	   11 (1 ABCDEFGHIST )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0180.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 1
METHOD
METHOD ============================================
MODEL 1
M C 0.89
V C 0.74
G C 0.75
R C 0.71
R C 0.78
P C 0.79
G C 0.84
G C 0.84
G C 0.76
L C 0.64
K C 0.66
D C 0.70
T C 0.74
K C 0.72
P C 0.57
V E 0.75
V E 0.85
V E 0.84
R E 0.82
L E 0.65
Y C 0.67
P C 0.57
D H 0.49
E H 0.66
I H 0.70
E H 0.69
A H 0.68
L H 0.64
K H 0.61
S H 0.48
R C 0.56
V C 0.72
P C 0.77
A C 0.65
N C 0.65
T C 0.55
S H 0.47
M H 0.72
S H 0.80
A H 0.85
Y H 0.87
I H 0.88
R H 0.90
R H 0.88
I H 0.88
I H 0.84
L H 0.80
N H 0.67
H H 0.55
L C 0.48
E C 0.60
D C 0.76
D C 0.92
END