PFRMAT SS
TARGET T0098
AUTHOR 3670-4530-6947
METHOD Using neural net overrep-2500-IDaa13-5-10-7-10-5-10-11-ehl2-seeded9-stride-trained.net
METHOD This is a 4-layer network, with 
METHOD	window	units
METHOD	    5	   10
METHOD	    7	   10
METHOD	    5	   10
METHOD	   11	    3 (1 EHL2 )
METHOD The input amino acid frequencies were determined from
METHOD alignment T0098.t2k.a2m.gz
METHOD with weighted counts, using EntropyWeight(1.4 bits/column, 10)
METHOD The weighting was determined by the posterior distribution
METHOD after regularizing with /projects/compbio/lib/recode3.20comp.
METHOD Counts were regularized to probabilities using
METHOD /projects/compbio/lib/recode3.20comp
METHOD Total sequence weight for alignment was 3.50994
METHOD
MODEL 1
D C 0.819
N C 0.810
K C 0.776
P C 0.689
K C 0.574
N C 0.530
L C 0.453
D H 0.469
A H 0.634
S H 0.729
I H 0.910
T H 0.951
S H 0.965
I H 0.966
I H 0.977
H H 0.975
E H 0.949
I H 0.873
G C 0.906
V C 0.770
P C 0.627
A H 0.456
H H 0.612
I H 0.870
K H 0.956
G H 0.980
Y H 0.991
L H 0.996
Y H 0.997
L H 0.999
R H 0.999
E H 0.999
A H 0.998
I H 0.996
A H 0.992
M H 0.985
V H 0.949
Y H 0.933
H H 0.923
D H 0.879
I H 0.879
E H 0.860
L H 0.836
L H 0.854
G H 0.911
S H 0.915
I H 0.928
T H 0.919
K H 0.935
V H 0.913
L H 0.903
Y H 0.834
P H 0.952
D H 0.955
I H 0.955
A H 0.957
K H 0.954
K H 0.921
Y H 0.825
N C 0.918
T C 0.913
T C 0.897
A H 0.797
S H 0.948
R H 0.983
V H 0.990
E H 0.995
R H 0.994
A H 0.993
I H 0.985
R H 0.973
H H 0.955
A H 0.947
I H 0.900
E H 0.848
V H 0.733
A H 0.646
W H 0.687
S H 0.615
R C 0.563
G C 0.927
N C 0.833
L H 0.686
E H 0.756
S H 0.821
I H 0.879
S H 0.901
S H 0.895
L H 0.833
F H 0.796
G C 0.742
Y C 0.632
T C 0.471
V C 0.518
S C 0.559
V C 0.515
S C 0.543
K C 0.560
A C 0.750
K C 0.880
P C 0.877
T C 0.829
N C 0.621
S H 0.592
E H 0.784
F H 0.804
I H 0.814
A H 0.785
M H 0.849
V H 0.832
A H 0.835
D H 0.774
K H 0.633
L H 0.682
R H 0.517
L H 0.494
E H 0.383
H C 0.460
K C 0.581
A C 0.763
S C 0.965
END