PFRMAT SS
TARGET T0091
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 T0091.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 21.3505
METHOD
MODEL 1
M C 0.671
F C 0.807
G C 0.786
K C 0.735
G C 0.778
G C 0.831
L H 0.958
G H 0.977
G H 0.984
L H 0.975
M H 0.982
K H 0.980
Q H 0.985
A H 0.983
Q H 0.986
Q H 0.991
M H 0.987
Q H 0.989
E H 0.993
K H 0.992
M H 0.994
Q H 0.994
K H 0.993
M H 0.992
Q H 0.988
E H 0.987
E H 0.970
I H 0.910
A H 0.846
Q H 0.594
L C 0.440
E E 0.532
V E 0.702
T E 0.734
G E 0.749
E E 0.640
S C 0.674
G C 0.886
A C 0.852
G C 0.505
L E 0.874
V E 0.968
K E 0.994
I E 0.997
T E 0.995
I E 0.969
N E 0.662
G C 0.774
A C 0.774
H E 0.512
N E 0.660
C E 0.793
R E 0.781
R E 0.752
I E 0.696
D E 0.730
I E 0.497
D C 0.907
P H 0.753
S H 0.873
L H 0.896
M H 0.756
E H 0.645
D H 0.504
D C 0.644
K H 0.973
E H 0.983
M H 0.982
L H 0.991
E H 0.994
D H 0.994
L H 0.993
I H 0.989
A H 0.987
A H 0.983
A H 0.971
F H 0.965
N H 0.967
D H 0.972
A H 0.978
V H 0.981
R H 0.984
R H 0.988
A H 0.989
E H 0.991
E H 0.993
L H 0.990
Q H 0.986
K H 0.983
E H 0.977
K H 0.965
M H 0.953
A H 0.950
S H 0.941
V H 0.923
T H 0.903
A H 0.886
G H 0.784
M C 0.666
P C 0.908
L C 0.906
P C 0.950
P C 0.921
G C 0.880
M C 0.833
K C 0.846
F C 0.805
P C 0.865
F C 0.972
END