PFRMAT SS
TARGET T0110
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 T0110.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 21.99
METHOD
MODEL 1
M C 0.475
A C 0.542
R C 0.569
E H 0.642
F H 0.830
K H 0.902
R H 0.944
S H 0.980
D H 0.988
R H 0.993
V H 0.991
A H 0.993
Q H 0.995
E H 0.993
I H 0.995
Q H 0.995
K H 0.997
E H 0.996
I H 0.993
A H 0.993
V H 0.986
I H 0.977
L H 0.960
Q H 0.954
R H 0.909
E H 0.742
V C 0.661
K C 0.808
D C 0.953
P C 0.796
R C 0.816
I C 0.853
G C 0.806
M E 0.642
V E 0.906
T E 0.951
V E 0.940
S E 0.866
D E 0.925
V E 0.971
E E 0.968
V E 0.932
S E 0.706
S C 0.810
D C 0.852
L C 0.518
S E 0.630
Y E 0.890
A E 0.946
K E 0.959
I E 0.990
F E 0.994
V E 0.990
T E 0.960
F E 0.764
L C 0.729
F C 0.923
D C 0.834
H C 0.810
D C 0.732
E H 0.527
M H 0.769
A H 0.805
I H 0.930
E H 0.967
Q H 0.977
G H 0.988
M H 0.987
K H 0.989
G H 0.986
L H 0.981
E H 0.982
K H 0.981
A H 0.983
S H 0.979
P H 0.873
Y H 0.963
I H 0.981
R H 0.989
S H 0.990
L H 0.978
L H 0.960
G H 0.929
K H 0.867
A H 0.685
M C 0.474
R C 0.528
L E 0.528
R E 0.614
I E 0.625
V C 0.602
P C 0.570
E E 0.625
I E 0.834
R E 0.894
F E 0.885
I E 0.805
Y E 0.596
D C 0.628
Q C 0.661
S C 0.568
L C 0.518
V H 0.514
E H 0.642
G H 0.781
M H 0.835
R H 0.865
M H 0.987
S H 0.990
N H 0.993
L H 0.988
V H 0.982
T H 0.975
N H 0.950
V H 0.895
V H 0.816
R H 0.862
E H 0.722
D H 0.674
E H 0.633
K H 0.632
K C 0.471
H C 0.568
V C 0.642
E C 0.750
E C 0.825
S C 0.910
N C 0.972
END