PFRMAT SS
TARGET T0097
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 T0097.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 9.69344
METHOD
MODEL 1
G C 0.953
C C 0.747
L H 0.568
P H 0.769
A H 0.862
Y H 0.952
D H 0.949
A H 0.967
L H 0.977
A H 0.969
G H 0.964
Q H 0.942
F H 0.906
I H 0.785
E H 0.508
A C 0.726
S C 0.904
S C 0.592
R H 0.983
E H 0.990
A H 0.996
R H 0.997
Q H 0.998
A H 0.999
I H 0.999
L H 0.999
K H 0.998
Q H 0.996
G H 0.987
Q H 0.981
D H 0.963
G H 0.898
L H 0.806
S H 0.676
G H 0.551
V C 0.734
K C 0.877
E H 0.688
T H 0.761
D H 0.836
K H 0.851
K H 0.922
W H 0.945
A H 0.967
S H 0.990
Q H 0.995
Y H 0.994
L H 0.996
K H 0.997
I H 0.996
M H 0.994
G H 0.990
K H 0.979
I H 0.932
L H 0.908
D H 0.826
Q H 0.771
G C 0.582
E H 0.677
D H 0.792
F H 0.882
P H 0.930
A H 0.966
S H 0.979
E H 0.983
L H 0.984
A H 0.987
R H 0.986
I H 0.984
S H 0.982
K H 0.975
L H 0.952
I H 0.900
E H 0.785
N C 0.702
K C 0.869
M C 0.870
S C 0.904
E H 0.558
G H 0.545
K H 0.594
K H 0.928
E H 0.948
E H 0.947
L H 0.925
Q H 0.922
R H 0.939
S H 0.916
L H 0.818
N C 0.744
I H 0.663
L H 0.782
T H 0.908
A H 0.927
F H 0.930
R H 0.947
K H 0.922
K H 0.893
G C 0.712
A H 0.626
E H 0.651
K H 0.522
E C 0.574
E C 0.777
L C 0.987
END