I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI)
Vo
l.
8
,
No
.
4
,
Dec
em
b
er
201
9
,
p
p
.
3
75
~
38
1
I
SS
N:
2
2
5
2
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
8
.i
4
.
p
p
3
75
-
38
1
375
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
es
co
r
e
.
co
m
F
ea
ture
s
e
l
ect
i
o
n f
o
r hum
a
n
m
em
bra
ne prote
i
n t
y
pe cl
a
s
s
i
f
i
ca
t
i
o
n u
s
i
ng
fi
l
t
er m
etho
ds
G
len
da
Ana
k
K
a
y
a
,
No
r
As
hi
k
in M
o
ha
m
a
d K
a
m
a
l
F
a
c
u
lt
y
o
f
Co
m
p
u
ter an
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
,
S
h
a
h
A
la
m
,
S
e
lan
g
o
r
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
2
2
,
2
0
1
9
R
ev
i
s
ed
O
ct
2
,
2
0
1
9
A
cc
ep
ted
O
ct
1
6
,
2
0
1
9
A
s
th
e
n
u
m
b
e
r
o
f
p
ro
tein
se
q
u
e
n
c
e
s
in
th
e
d
a
tab
a
se
is
in
c
re
a
sin
g
,
e
ff
e
c
ti
v
e
a
n
d
e
ff
icie
n
t
tec
h
n
iq
u
e
s
a
re
n
e
e
d
e
d
to
m
a
k
e
th
e
se
d
a
ta
m
e
a
n
in
g
f
u
l.
T
h
e
se
p
ro
tein
se
q
u
e
n
c
e
s
c
o
n
tai
n
re
d
u
n
d
a
n
t
a
n
d
irrele
v
a
n
t
f
e
a
tu
re
s
th
a
t
c
a
u
se
lo
w
e
r
c
la
ss
i
f
ica
ti
o
n
a
c
c
u
ra
c
y
a
n
d
in
c
re
a
se
th
e
ru
n
n
in
g
ti
m
e
o
f
th
e
c
o
m
p
u
tatio
n
a
l
a
lg
o
ri
th
m
.
In
th
is
p
a
p
e
r,
w
e
se
lec
t
th
e
b
e
st
f
e
a
t
u
re
s
u
sin
g
M
in
im
u
m
Re
d
u
n
d
a
n
c
y
M
a
x
i
m
u
m
R
e
lev
a
n
c
e
(
m
RM
R)
a
n
d
Co
rre
latio
n
-
b
a
se
d
f
e
a
tu
re
se
lec
ti
o
n
(CF
S
)
m
e
th
o
d
s.
T
w
o
d
a
tas
e
ts
o
f
h
u
m
a
n
m
e
m
b
ra
n
e
p
ro
tei
n
a
re
u
se
d
,
S
1
a
n
d
S
2
.
A
f
t
e
r
th
e
f
e
a
tu
re
s
h
a
v
e
b
e
e
n
se
lec
t
e
d
b
y
m
RM
R
a
n
d
CF
S
,
K
-
Ne
a
re
st
Ne
ig
h
b
o
r
(KN
N)
a
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
(S
V
M
)
c
las
si
f
iers
a
re
u
se
d
to
c
las
sify
th
e
se
m
e
m
b
ra
n
e
p
ro
tein
s.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
se
tec
h
n
i
q
u
e
s
is
m
e
a
su
re
d
u
sin
g
a
c
c
u
ra
c
y
,
sp
e
c
if
icit
y
a
n
d
s
e
n
siti
v
it
y
.
a
n
d
F
-
m
e
a
su
re
.
T
h
e
p
ro
p
o
se
d
a
l
g
o
rit
h
m
m
a
n
a
g
e
d
to
a
c
h
iev
e
7
6
%
a
c
c
u
ra
c
y
f
o
r
S
1
a
n
d
7
3
%
a
c
c
u
ra
c
y
f
o
r
S
2
.
F
in
a
ll
y
,
o
u
r
p
r
o
p
o
se
d
m
e
th
o
d
s
p
re
se
n
t
c
o
m
p
e
ti
ti
v
e
re
su
lt
s
w
h
e
n
c
o
m
p
a
re
d
w
it
h
t
h
e
p
re
v
io
u
s
w
o
rk
s
o
n
m
e
m
b
ra
n
e
p
ro
tei
n
c
las
sif
ica
ti
o
n
K
ey
w
o
r
d
s
:
C
FS
Featu
r
e
s
elec
t
io
n
KNN
Me
m
b
r
an
e
p
r
o
tein
m
R
MR
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
No
r
A
s
h
i
k
in
Mo
h
a
m
ad
Ka
m
al
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
lt
y
o
f
C
o
m
p
u
ter
an
d
Ma
t
h
e
m
a
tical
Scie
n
ce
s
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
Sh
a
h
A
la
m
,
Selan
g
o
r
.
E
m
ail:
n
o
r
_
ash
i
k
i
n
@
t
m
s
k
.
u
it
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
th
r
ee
m
a
in
c
lass
e
s
o
f
p
r
o
tein
ar
e
g
lo
b
u
lar
,
f
ib
r
o
u
s
a
n
d
m
e
m
b
r
a
n
e.
Me
m
b
r
a
n
es
ar
e
a
u
n
i
v
er
s
al
f
ea
t
u
r
e
o
f
all
ce
ll
t
y
p
es
w
h
ic
h
s
ep
ar
ates
th
e
ce
l
ls
an
d
t
h
e
en
v
ir
o
n
m
e
n
t
o
u
ts
id
e
th
e
ce
ll.
I
t
p
r
o
tects
th
e
ce
ll
n
u
cle
u
s
a
n
d
s
u
r
v
i
v
al
s
y
s
te
m
s
t
h
at
w
o
r
k
i
n
t
h
e
c
y
to
p
las
m
.
T
h
e
m
e
m
b
r
a
n
e
p
r
o
tein
is
an
i
m
p
o
r
tan
t
clas
s
o
f
p
r
o
tein
t
h
at
f
u
n
ct
io
n
s
a
s
r
ec
ep
to
r
s
,
en
er
g
y
tr
a
n
s
d
u
ce
r
s
an
d
c
h
an
n
el
s
i
n
a
ce
ll
m
e
m
b
r
an
e
[
1
]
.
Mo
s
t
d
r
u
g
s
ai
m
at
m
e
m
b
r
an
e
p
r
o
tein
s
s
in
ce
th
e
th
er
ap
eu
t
ic
ef
f
ec
ts
o
f
m
o
s
t
m
ed
ici
n
es
ar
e
ac
h
ie
v
ed
th
r
o
u
g
h
in
ter
ac
tio
n
w
i
th
t
h
e
m
e
m
b
r
an
e
p
r
o
tein
.
T
h
is
m
a
k
es
t
h
e
m
a
d
esira
b
le
tar
g
et
f
o
r
d
r
u
g
r
esear
ch
an
d
d
esig
n
.
T
h
e
m
e
m
b
r
an
e
p
r
o
tein
d
ata
h
a
v
e
b
ee
n
r
ap
id
l
y
i
n
cr
ea
s
i
n
g
.
Un
f
o
r
t
u
n
ate
l
y
,
p
r
io
r
to
r
estri
cted
tech
n
iq
u
es
f
o
r
ex
p
r
ess
i
n
g
m
e
m
b
r
a
n
e
p
r
o
te
in
in
b
ig
a
m
o
u
n
ts
,
th
e
s
t
r
u
ctu
r
e
an
d
f
u
n
c
tio
n
o
f
m
e
m
b
r
an
e
p
r
o
tein
s
is
n
o
t
w
ell
u
n
d
er
s
to
o
d
[2
-
4
]
.
I
t
tak
es
ti
m
e
a
n
d
is
ex
p
en
s
i
v
e
t
o
d
eter
m
i
n
e
th
e
t
y
p
es
o
f
t
h
e
u
n
k
n
o
w
n
m
e
m
b
r
an
e
p
r
o
tein
b
y
u
s
i
n
g
t
h
e
tr
ad
itio
n
al
m
et
h
o
d
.
A
n
e
f
f
ic
ien
t
co
m
p
u
tatio
n
a
l
m
et
h
o
d
is
r
ea
ll
y
n
ee
d
ed
f
o
r
m
e
m
b
r
a
n
e
p
r
o
tein
t
y
p
e
cla
s
s
i
f
icatio
n
a
n
d
it
i
s
a
b
i
g
co
n
tr
ib
u
tio
n
to
u
n
d
er
s
tan
d
t
h
e
m
e
m
b
r
an
e
p
r
o
tein
t
y
p
es
an
d
th
eir
f
u
n
ctio
n
s
.
C
las
s
i
f
icatio
n
is
t
h
e
d
ata
m
in
i
n
g
f
u
n
ctio
n
th
at
h
elp
s
to
tar
g
e
t
th
e
ca
teg
o
r
ies
o
r
class
es
an
d
p
r
ed
ict
th
e
class
o
f
t
h
e
d
ataset.
T
h
e
class
i
f
icatio
n
o
f
m
e
m
b
r
an
e
p
r
o
t
ein
s
eq
u
en
ce
s
i
n
v
o
lv
e
s
t
h
r
ee
p
h
ases
w
h
ich
ar
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
f
ea
t
u
r
e
s
el
ec
tio
n
,
an
d
class
i
f
icatio
n
.
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
is
th
e
tr
a
n
s
f
o
r
m
atio
n
o
f
d
ata
in
to
a
s
et
o
f
f
ea
tu
r
es.
T
h
e
p
o
p
u
lar
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
et
h
o
d
f
o
r
t
h
e
p
r
o
tein
s
eq
u
e
n
ce
s
ar
e
a
m
in
o
ac
id
co
m
p
o
s
i
tio
n
(
AAC)
,
p
s
e
u
d
o
a
m
i
n
o
ac
id
co
m
p
o
s
i
tio
n
(
P
s
eAA
C
)
,
f
u
n
ctio
n
al
d
o
m
ai
n
,
p
o
s
i
t
io
n
-
sp
ec
if
ic
s
co
r
i
n
g
m
atr
ices
(
P
SS
M)
an
d
p
h
y
s
ico
ch
e
m
ical
p
r
o
p
er
ties
o
f
a
m
i
n
o
ac
id
s
.
T
h
e
cr
u
cial
p
r
o
b
le
m
in
th
e
b
io
lo
g
ical
d
ata
is
h
i
g
h
d
i
m
en
s
io
n
a
l
f
ea
t
u
r
es
[
5
]
.
T
h
u
s
,
it
is
i
m
p
o
r
tan
t
t
o
s
elec
t
s
u
b
s
e
t
o
f
t
h
e
f
ea
t
u
r
es
av
ailab
le
f
o
r
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
A
I
Vo
l.
8
,
No
.
4
,
Dec
em
b
er
201
9
:
3
75
–
38
1
376
ap
p
licatio
n
o
f
lear
n
in
g
al
g
o
r
ith
m
.
Feat
u
r
e
s
elec
tio
n
m
et
h
o
d
s
ch
o
o
s
e
a
s
u
b
s
et
o
f
f
ea
tu
r
e
s
th
at
ca
n
co
r
r
ec
tl
y
ca
teg
o
r
ize
m
e
m
b
r
an
e
p
r
o
tein
to
th
e
tar
g
et
clas
s
[
6
]
.
Featu
r
es
s
e
lectio
n
ca
n
b
e
s
p
lit
in
to
th
r
ee
tech
n
iq
u
e
s
w
h
ic
h
ar
e
f
ilter
m
et
h
o
d
,
w
r
ap
p
er
m
et
h
o
d
,
an
d
an
e
m
b
ed
d
e
d
m
e
th
o
d
.
I
n
th
is
s
tu
d
y
,
t
h
e
m
et
h
o
d
th
at
w
ill
b
e
u
s
ed
is
t
h
e
f
i
lter
f
ea
t
u
r
e
s
elec
tio
n
m
et
h
o
d
.
T
h
e
f
ilter
m
et
h
o
d
s
elec
ts
f
ea
t
u
r
es
i
n
d
ep
en
d
en
t
o
f
th
e
clas
s
if
ier
s
.
I
t
ca
lcu
late
s
t
h
e
f
ea
t
u
r
e
s
co
r
e
r
ep
r
esen
tin
g
t
h
e
r
elev
a
n
ce
o
f
t
h
e
p
ar
ticu
lar
f
ea
tu
r
e
[
7
]
.
T
h
e
a
d
v
an
ta
g
es
o
f
u
s
in
g
th
e
f
ilter
m
et
h
o
d
ar
e
th
e
s
i
m
p
le
an
d
f
a
s
t
m
et
h
o
d
[
7
-
9]
.
T
h
is
f
il
ter
m
et
h
o
d
also
ca
n
b
e
ea
s
il
y
s
ca
led
a
n
d
ap
p
lied
to
a
v
er
y
h
i
g
h
-
d
i
m
e
n
s
i
o
n
al
d
ataset
[7
-
8
]
.
Mu
ch
o
f
t
h
e
e
x
i
s
ti
n
g
r
esear
ch
f
o
cu
s
e
s
o
n
l
y
o
n
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
et
h
o
d
s
t
h
at
o
p
er
ate
o
n
t
h
e
m
e
m
b
r
a
n
e
p
r
o
tein
d
ataset
[
3
,
1
0
-
1
3
]
.
In
[
1
4
]
ap
p
lied
a
ty
p
e
o
f
f
ea
t
u
r
e
th
at
is
d
er
iv
ed
f
r
o
m
th
e
w
av
ele
t
f
ea
t
u
r
e
an
al
y
s
is
o
f
t
h
e
p
r
o
tein
s
eq
u
e
n
ce
an
d
ca
s
ca
d
ed
n
e
u
r
al
n
et
w
o
r
k
clas
s
i
f
ier
.
T
h
e
clas
s
i
f
icatio
n
ac
c
u
r
ac
y
o
b
tain
ed
w
a
s
8
1
.
3
%.
In
[
1
5
]
r
ep
r
esen
ted
p
r
o
tein
f
ea
tu
r
e
s
b
y
u
s
i
n
g
Dip
ep
tid
e
d
ec
o
m
p
o
s
itio
n
m
et
h
o
d
.
T
h
e
KNN
class
i
f
ier
w
a
s
i
m
p
le
m
e
n
ted
i
n
o
r
d
er
to
class
i
f
y
t
h
e
m
e
m
b
r
an
e
p
r
o
tein
w
it
h
8
2
%
ac
c
u
r
ac
y
.
In
[
3
]
p
r
o
p
o
s
ed
th
r
ee
m
et
h
o
d
s
,
r
ea
l
w
ei
g
h
te
d
co
m
b
in
a
tio
n
(
R
W
C
)
,
Nea
r
est
n
ei
g
h
b
o
r
alg
o
r
ith
m
(
N
NA
)
a
n
d
in
te
g
r
ated
m
et
h
o
d
.
I
n
te
g
r
ated
m
e
th
o
d
cl
ass
i
f
ied
h
u
m
a
n
m
e
m
b
r
an
e
p
r
o
tein
t
y
p
es
u
s
in
g
p
r
o
tein
s
eq
u
en
ce
h
o
m
o
lo
g
y
an
d
s
i
m
ilar
ch
ar
ac
ter
is
tics
b
et
w
ee
n
i
n
ter
ac
tiv
e
p
r
o
tein
s
.
T
h
e
r
es
u
lts
r
ev
ea
led
t
h
at
t
h
e
p
r
o
ce
d
u
r
e
g
av
e
a
m
a
x
i
m
u
m
class
i
f
icatio
n
ac
cu
r
ac
y
o
f
8
7
.
6
5
%.
In
[
1
3
]
p
r
ed
icted
m
e
m
b
r
an
e
p
r
o
tein
s
u
s
i
n
g
th
r
e
e
f
ea
t
u
r
e
s
elec
tio
n
s
ch
e
m
es,
n
a
m
el
y
p
s
eu
d
o
a
m
i
n
o
ac
id
co
m
p
o
s
itio
n
(
P
s
e
AA
C
)
,
a
m
i
n
o
ac
id
co
m
p
o
s
itio
n
(
AA
C
)
an
d
s
p
lit
a
m
in
o
ac
id
co
m
p
o
s
itio
n
(
S
AAC).
T
h
e
ex
p
er
i
m
e
n
tal
f
i
n
d
in
g
s
h
o
wed
th
at
SAAC
f
ea
tu
r
e
s
p
ac
e
i
n
co
m
b
in
at
io
n
w
it
h
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
p
r
o
v
i
d
in
g
th
e
b
est
p
r
ed
ictiv
e
r
es
u
lt
s
.
In
[
1
1
]
d
ev
elo
p
ed
th
e
m
u
lt
i
class
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
M
C
SVM)
tec
h
n
iq
u
e
u
s
i
n
g
t
h
e
t
w
o
-
s
te
p
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
.
I
n
t
h
e
f
ir
s
t
s
tep
,
t
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
w
as
u
s
ed
i
n
d
iv
id
u
all
y
.
I
n
th
e
s
ec
o
n
d
s
te
p
,
th
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
et
h
o
d
s
w
er
e
co
m
b
in
ed
to
p
r
o
d
u
ce
o
p
ti
m
al
f
ea
tu
r
e
s
e
ts
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
o
b
tain
ed
m
a
x
i
m
u
m
ac
c
u
r
ac
y
o
f
8
6
.
1
1
%.
In
[
1
2
]
ap
p
lied
th
e
p
s
e
u
d
o
a
m
i
n
o
ac
i
d
co
m
p
o
s
itio
n
a
n
d
s
eq
u
e
n
ce
h
o
m
o
lo
g
y
f
o
r
m
e
m
b
r
a
n
e
p
r
o
tein
t
y
p
e
p
r
ed
ictio
n
.
T
h
ey
d
e
v
elo
p
ed
a
s
y
s
te
m
n
a
m
ed
MemP
r
ed
w
h
ic
h
ac
h
iev
e
m
ax
i
m
u
m
ac
c
u
r
ac
y
o
f
8
8
.
1
7
%.
T
o
f
ill th
e
g
ap
,
t
h
i
s
p
ap
er
w
ill
f
o
cu
s
o
n
f
ea
t
u
r
e
s
elec
tio
n
f
o
r
m
e
m
b
r
a
n
e
p
r
o
tein
clas
s
if
icatio
n
u
s
i
n
g
Min
i
m
u
m
R
ed
u
n
d
an
c
y
Ma
x
i
m
u
m
R
ele
v
a
n
ce
(
m
R
MR
)
an
d
C
o
r
r
elatio
n
-
b
ased
Featu
r
e
Selectio
n
(
C
FS
)
m
et
h
o
d
s
.
W
e
in
v
es
tig
a
te
h
er
e,
w
h
et
h
er
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
ca
n
b
e
u
s
ed
to
i
m
p
r
o
v
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
m
e
m
b
r
an
e
p
r
o
tein
t
y
p
e
class
i
f
icatio
n
.
T
h
is
p
ap
er
is
o
r
g
an
ized
a
s
f
o
llo
w
s
.
Sec
tio
n
2
d
is
cu
s
s
es
th
e
s
u
g
g
es
ted
m
et
h
o
d
o
lo
g
y
u
s
ed
i
n
t
h
is
r
esear
ch
.
Sectio
n
3
d
is
cu
s
s
e
s
t
h
e
o
u
tco
m
e
s
an
d
e
v
alu
a
tio
n
.
F
in
all
y
,
Sectio
n
4
co
n
cl
u
d
es t
h
e
s
tu
d
y
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
m
et
h
o
d
o
lo
g
y
o
f
t
h
i
s
s
t
u
d
y
h
a
s
f
o
u
r
p
h
a
s
es
n
a
m
el
y
p
r
o
tein
f
ea
t
u
r
e
ex
tr
ac
t
io
n
,
f
ea
t
u
r
e
s
elec
tio
n
,
class
i
f
icatio
n
an
d
p
er
f
o
r
m
a
n
ce
ev
alu
at
io
n
as s
h
o
w
n
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
R
esear
ch
m
et
h
o
d
o
lo
g
y
T
h
e
f
ir
s
t
s
tep
ai
m
s
to
cr
ea
te
a
f
ea
tu
r
e
m
atr
i
x
f
o
r
ea
ch
p
r
o
tein
s
eq
u
e
n
ce
.
I
n
t
h
i
s
p
h
ase
,
w
e
u
s
ed
P
s
eu
d
o
a
m
i
n
o
ac
id
co
m
p
o
s
iti
o
n
(
P
s
eAA
C
)
ap
p
r
o
ac
h
to
ex
t
r
ac
t
an
d
co
n
v
er
t
th
e
f
ea
tu
r
es
f
o
r
ea
ch
m
e
m
b
r
a
n
e
p
r
o
tein
s
eq
u
en
ce
i
n
to
n
u
m
er
i
ca
l
v
al
u
es.
S
u
b
s
eq
u
e
n
tl
y
,
th
e
p
r
o
p
o
s
ed
Min
i
m
u
m
R
ed
u
n
d
a
n
c
y
a
n
d
Ma
x
i
m
u
m
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
F
ea
tu
r
e
s
elec
tio
n
fo
r
h
u
ma
n
mem
b
r
a
n
e
p
r
o
tein
typ
e
cla
s
s
ifica
tio
n
.
.
.
(
N
o
r
A
s
h
ikin
Mo
h
a
ma
d
K
a
ma
l
)
377
R
elev
a
n
ce
(
m
R
M
R
)
an
d
C
o
r
r
elatio
n
-
b
as
ed
f
ea
t
u
r
e
s
elec
tio
n
(
C
FS
)
m
et
h
o
d
s
w
ill
s
elec
t
t
h
e
b
est
f
ea
t
u
r
es
f
r
o
m
th
ese
ex
tr
ac
ted
f
ea
tu
r
es.
T
h
e
s
elec
ted
f
ea
tu
r
es
ar
e
in
s
er
ted
in
to
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
an
d
k
-
Nea
r
est
Nei
g
h
b
o
u
r
(
k
NN)
class
i
f
ier
s
to
p
r
ed
ict
th
e
clas
s
o
f
th
e
s
e
f
ea
t
u
r
es.
T
h
e
r
esu
lt
s
o
f
class
i
f
icat
io
n
ar
e
ev
alu
a
ted
u
s
i
n
g
ac
cu
r
ac
y
,
s
p
ec
if
icit
y
,
s
e
n
s
i
tiv
it
y
a
n
d
F
-
m
ea
s
u
r
e.
T
h
e
d
etail
o
f
ea
ch
p
h
ase
i
s
d
escr
ib
ed
in
th
e
f
o
llo
w
i
n
g
s
u
b
s
ec
tio
n
s
.
2
.
1
.
Da
t
a
c
o
llect
io
n
T
h
is
p
r
o
j
ec
t
u
s
ed
tw
o
d
ataset
o
f
m
e
m
b
r
a
n
e
p
r
o
tein
th
at
is
d
o
w
n
lo
ad
f
r
o
m
th
e
Un
iP
r
o
t
[
1
6
]
d
atab
ase
th
at
w
a
s
r
elea
s
ed
i
n
Octo
b
er
2
0
1
2
.
Six
k
i
n
d
s
o
f
m
e
m
b
r
an
e
p
r
o
tein
ar
e
in
ea
c
h
d
atase
t.
T
h
e
f
ir
s
t
d
ata
s
et,
S1
in
cl
u
d
es
2
8
7
6
p
r
o
tein
s
eq
u
en
ce
s
w
it
h
1
,
4
1
4
m
u
l
tip
ass
,
1
4
0
lip
id
-
an
ch
o
r
ed
,
5
4
5
p
er
i
p
h
er
al,
5
4
6
s
in
g
le
p
ass
t
y
p
e
-
I
,
1
6
1
ar
e
s
in
g
le
p
as
s
t
y
p
e
-
I
I
an
d
7
0
GP
I
an
ch
o
r
m
e
m
b
r
a
n
e
p
r
o
tein
s
eq
u
e
n
ce
s
.
T
h
e
s
ec
o
n
d
d
ataset,
S2
co
n
s
is
ts
o
f
2
0
7
3
m
e
m
b
r
an
e
p
r
o
tein
s
eq
u
en
ce
s
w
it
h
8
7
9
m
u
ltip
ass
,
8
4
lip
id
-
a
n
ch
o
r
ed
,
4
7
0
p
er
ip
h
er
al,
4
3
s
in
g
le
-
p
ass
t
y
p
e
-
I
,
1
4
4
s
i
n
g
le
-
p
ass
t
y
p
e
-
I
I
a
n
d
6
0
GP
I
-
an
c
h
o
r
m
e
m
b
r
a
n
e
p
r
o
tein
s
eq
u
en
ce
s
.
T
h
e
s
a
m
e
d
ataset
h
as b
ee
n
u
s
ed
b
y
r
esear
ch
er
s
[
1
1
,
1
2
,
1
7
]
.
2
.
2
.
F
e
a
t
ure
e
x
t
ra
ct
io
n
T
h
e
P
s
eu
d
o
Am
i
n
o
A
c
id
C
o
m
p
o
s
i
tio
n
(
P
s
eAA
C
)
i
s
u
s
e
d
to
o
b
tain
t
h
e
f
ea
t
u
r
es
o
f
m
e
m
b
r
a
n
e
p
r
o
tein
s
.
P
s
eAA
C
is
t
h
e
e
x
te
n
s
io
n
o
f
th
e
a
m
in
o
A
cid
(
AA
)
c
o
m
p
o
s
i
tio
n
t
h
at
in
tr
o
d
u
ce
d
b
y
[
1
8
-
1
9
]
.
P
s
eAA
C
in
co
r
p
o
r
ates
s
eq
u
en
ce
o
r
d
er
an
d
s
tr
u
ct
u
r
e
in
f
o
r
m
a
tio
n
o
f
p
r
o
tein
s
[
1
8
-
2
0
]
.
I
t
r
ep
r
esen
ts
t
h
e
p
r
o
tein
s
eq
u
en
ce
as sh
o
w
n
i
n
(
1
)
.
=
1
,
2
,
…
,
ʌ
(
1)
w
h
er
e,
ʌ
=
20
+
ʎ
(
2)
I
n
th
e
(
2
)
,
th
e
f
ir
s
t
2
0
ele
m
e
n
ts
,
t
h
at
i
s
,
P
1
to
P
20
in
ab
o
v
e
ar
e
g
i
v
en
b
y
AA
co
m
p
o
s
itio
n
(
f
r
eq
u
e
n
c
y
o
f
o
cc
u
r
r
en
ce
o
f
2
0
a
m
i
n
o
ac
i
d
s
)
.
ʎ
(
la
m
b
d
a)
is
th
e
n
u
m
b
er
o
f
tier
s
u
s
ed
i
n
t
h
e
P
s
eAA
,
ʎ
=
1
,
…,
m
.
T
h
e
n
r
ep
r
esen
ts
t
h
e
n
u
m
b
er
o
f
p
h
y
s
io
c
h
e
m
ical
p
r
o
p
er
ties
.
T
h
e
f
ea
t
u
r
es
o
f
m
e
m
b
r
a
n
e
p
r
o
tein
s
eq
u
e
n
ce
is
b
ein
g
e
x
tr
ac
ted
b
y
u
s
i
n
g
P
s
eu
d
o
Am
i
n
o
A
cid
C
o
m
p
o
s
it
io
n
(
P
s
eAA
C
)
tec
h
n
iq
u
e
th
a
t
is
a
v
ailab
le
v
i
a
h
ttp
://
www
.
c
s
b
io
.
s
j
tu
.
ed
u
.
cn
/b
io
in
f
/P
s
e
AA
C
/
w
eb
s
ite.
T
h
e
p
ar
a
m
eter
s
etti
n
g
s
ar
e
T
y
p
e
2
P
s
eAA
C
,
s
i
x
t
y
p
e
s
o
f
p
h
y
s
ico
ch
e
m
ical
p
r
o
p
er
tie
s
w
h
i
c
h
ar
e
h
y
d
r
o
p
h
o
b
icit
y
,
h
y
d
r
o
p
h
ilici
t
y
,
m
a
s
s
,
p
K1
(
a
lp
h
a
-
C
OOH)
,
p
K2
(
NH3
)
an
d
p
I
(
at
2
5
℃
)
.
T
h
e
w
e
ig
h
t
f
ac
to
r
is
0
.
5
0
an
d
la
m
b
d
a
is
2
5
[
2
0
]
.
B
y
u
s
in
g
(
2
)
,
th
e
to
tal
n
u
m
b
er
o
f
f
ea
t
u
r
es u
s
ed
in
t
h
is
w
o
r
k
i
s
1
7
0
.
2
.
3
.
F
e
a
t
ure
s
elec
t
io
n
W
e
em
p
lo
y
ed
t
w
o
f
ea
t
u
r
e
s
e
lectio
n
tec
h
n
iq
u
es
f
o
r
th
i
s
s
t
u
d
y
w
h
ic
h
ar
e
Min
i
m
u
m
R
e
d
u
n
d
an
c
y
Ma
x
i
m
u
m
R
ele
v
a
n
ce
(
m
R
M
R
)
[
3
1
]
,
an
d
C
o
r
r
elatio
n
-
b
a
s
ed
f
ea
t
u
r
e
s
elec
tio
n
(
C
FS
)
[
2
1
]
.
B
elo
w
ar
e
th
e
d
escr
ip
tio
n
s
o
f
th
e
s
e
t
w
o
alg
o
r
ith
m
s
.
2
.
3
.
1
.
M
ini
m
u
m
re
du
nd
a
ncy
m
a
x
i
m
u
m
re
lev
a
nce
(
m
RM
R)
Th
e
m
R
MR
i
s
o
n
e
o
f
th
e
co
m
m
o
n
f
ilter
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
s
[
2
3
]
.
I
t
is
a
tech
n
iq
u
e
t
h
at
tr
y
i
n
g
to
b
alan
ce
th
e
m
in
i
m
u
m
o
f
r
e
d
u
n
d
an
c
y
a
n
d
m
a
x
i
m
ize
th
e
r
elev
an
ce
o
f
f
ea
t
u
r
es
[
2
4
]
.
T
h
e
m
R
MR
tech
n
iq
u
e
co
u
ld
clas
s
i
f
y
t
h
e
f
ea
t
u
r
es
ac
co
r
d
in
g
to
t
h
eir
s
i
g
n
if
ican
c
e
an
d
r
ed
u
n
d
an
c
y
a
m
o
n
g
s
t
th
e
f
ea
tu
r
e
s
[
2
5
]
.
(
3
)
s
h
o
w
s
th
e
f
o
r
m
u
la
f
o
r
m
u
tu
al
in
f
o
r
m
at
io
n
;
I
t
h
a
t
is
u
s
ed
to
ev
al
u
ate
t
h
e
"
s
im
ilar
it
y
"
lev
el
.
T
h
e
f
u
n
c
tio
n
P
(
x
)
an
d
P
(
y
)
ar
e
th
e
m
ar
g
i
n
al
p
r
o
b
ab
ilit
y
d
en
s
i
t
y
f
u
n
ctio
n
.
(
,
)
=
∑
P(
,
)
,
∈
l
og
(
,
)
(
)
(
)
(
3
)
T
h
e
id
ea
o
f
m
i
n
i
m
u
m
r
ed
u
n
d
a
n
c
y
is
to
id
e
n
ti
f
y
f
ea
tu
r
es
th
a
t
d
if
f
er
f
r
o
m
o
n
e
a
n
o
th
er
[
1
2
]
.
Min
i
m
u
m
r
ed
u
n
d
an
c
y
w
i
ll
i
m
p
r
o
v
e
t
h
e
p
r
o
ce
s
s
in
g
ti
m
e
o
f
th
e
en
tire
d
ataset
[
3
0
]
.
T
h
e
m
in
i
m
u
m
r
ed
u
n
d
an
c
y
i
s
ca
lcu
lated
b
y
u
s
i
n
g
(
4
)
.
(
)
,
=
1
|
|
2
∑
(
,
)
,
∈
(
4
)
I
n
4
,
th
e
I
(
x
i
,x
j
)
r
ep
r
esen
t
s
t
h
e
m
u
tu
al
in
f
o
r
m
a
tio
n
a
n
d
R
r
ep
r
esen
t
th
e
n
o
tatio
n
al
s
i
m
p
lici
t
y
s
co
r
e
b
et
w
ee
n
t
h
e
x
i
an
d
x
j
in
S
.
T
h
e
le
v
el
o
f
d
i
s
cr
i
m
i
n
atio
n
f
ea
t
u
r
es
i
s
m
ea
s
u
r
ed
b
y
ca
lc
u
lat
in
g
t
h
e
m
u
tu
a
l
i
n
f
o
r
m
atio
n
,
I
(
C
,
x
i
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
A
I
Vo
l.
8
,
No
.
4
,
Dec
em
b
er
201
9
:
3
75
–
38
1
378
o
f
class
i
f
icatio
n
v
ar
iab
le
C
w
ith
th
e
i
n
d
ep
en
d
en
t
v
ar
iab
le
x
i
[
2
4
]
.
T
h
e
m
ax
i
m
u
m
r
ele
v
a
n
ce
is
ca
lcu
lated
b
y
u
s
i
n
g
(
5
)
.
(
)
,
=
1
|
|
∑
(
,
)
∈
(
5)
I
n
th
e
(
5
)
,
D
r
ep
r
esen
ts
th
e
m
ea
n
v
al
u
e
o
f
t
h
e
m
u
t
u
al
i
n
f
o
r
m
atio
n
b
et
w
ee
n
tar
g
et
v
ar
iab
l
e
C
w
ith
t
h
e
f
ea
tu
r
e
s
in
S
.
|
S|
r
ep
r
esen
t
t
h
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
i
n
S
.
T
h
e
m
R
MR
s
tr
ate
g
y
i
s
to
o
p
ti
m
iz
e
th
e
r
eq
u
ir
e
m
en
t
s
in
(
4
)
an
d
(
5
)
co
n
cu
r
r
en
tl
y
b
y
in
te
g
r
atin
g
t
h
e
m
to
p
r
o
d
u
ce
a
s
in
g
le
o
p
ti
m
izatio
n
p
r
o
b
le
m
[
2
6
]
.
T
h
ese
t
w
o
m
e
th
o
d
s
ac
t
u
all
y
t
o
eith
er
u
s
e
t
h
e
d
if
f
er
en
ce
o
r
t
h
e
r
atio
o
f
th
e
m
R
MR
cr
iter
ia
.
T
h
e
f
o
llo
w
in
g
ar
e
th
e
cr
iter
ia
o
f
t
h
e
m
R
MR
:
ma
x
(
−
)
,
(
6
)
ma
x
(
/
)
.
(
7
)
I
n
th
e
(
6
)
an
d
(
7
)
,
D
is
th
e
r
ed
u
n
d
a
n
c
y
a
n
d
R
is
t
h
e
r
elev
a
n
c
e.
(
6
)
is
ca
lled
th
e
Mu
tu
a
l
I
n
f
o
r
m
atio
n
D
if
f
er
en
c
e
(
MI
D)
cr
iter
io
n
w
h
ile
(
7
)
is
ca
lled
th
e
Mu
t
u
al
I
n
f
o
r
m
a
tio
n
Q
u
o
tien
t (
MI
Q)
cr
iter
io
n
.
2
.
3
.
2
.
Co
rr
ela
t
io
n
f
e
a
t
ur
e
s
elec
t
io
n (
CF
S)
C
o
r
r
elatio
n
-
b
ased
f
ea
tu
r
e
s
ele
ctio
n
is
an
al
g
o
r
ith
m
w
h
ic
h
r
an
k
s
a
s
u
b
s
e
t
b
ased
o
n
h
eu
r
i
s
tic
b
ased
ev
alu
a
tio
n
f
u
n
ctio
n
.
I
t
is
b
ase
d
o
n
th
e
h
y
p
o
t
h
esi
s
t
h
at
a
s
u
b
s
et
o
f
g
o
o
d
f
ea
t
u
r
es
co
n
tai
n
s
f
ea
tu
r
es
t
h
at
h
a
v
e
a
h
ig
h
co
r
r
elatio
n
to
clas
s
an
d
n
o
t
w
i
th
o
t
h
er
f
ea
tu
r
e
s
.
Hi
g
h
c
o
r
r
elatio
n
w
i
th
o
th
er
f
ea
t
u
r
es
i
n
d
icate
s
t
h
e
f
ea
t
u
r
e
r
ed
u
n
d
an
c
y
.
L
o
w
co
r
r
elatio
n
w
it
h
clas
s
in
d
icate
s
th
e
f
ea
tu
r
e
ar
e
n
o
r
r
elev
an
t.
T
h
er
ef
o
r
e,
C
FS
r
e
m
o
v
es
th
e
r
ed
u
n
d
a
n
t a
n
d
u
n
r
elate
d
f
e
atu
r
es.
A
cc
o
r
d
in
g
to
[
2
1
]
,
th
e
f
ea
t
u
r
e
s
u
b
s
et
s
ea
r
ch
f
o
r
m
u
la
i
s
s
h
o
w
n
i
n
(
8
)
.
=
̅
̅
̅
̅
̅
√
+
(
−
1
)
̅
̅
̅
̅
̅
(
8
)
w
h
er
e
is
th
e
h
e
u
r
is
tic
s
co
r
e
f
o
r
a
f
ea
tu
r
e
s
u
b
s
et
S
w
it
h
k
f
ea
t
u
r
es,
̅
̅
̅
̅
is
th
e
av
er
a
g
e
co
r
r
elatio
n
b
et
w
ee
n
f
u
n
ctio
n
a
n
d
clas
s
,
an
d
̅
̅
̅
̅
is
th
e
a
v
er
ag
e
co
r
r
elatio
n
b
et
w
ee
n
f
ea
t
u
r
es.
A
g
r
ea
ter
s
co
r
e
s
h
o
w
s
g
r
ea
ter
co
r
r
elatio
n
b
et
w
ee
n
t
h
e
f
ea
tu
r
e
s
u
b
s
et
s
to
th
e
tar
g
et
cla
s
s
a
n
d
less
et
in
ter
-
co
r
r
elatio
n
b
et
wee
n
th
e
f
ea
t
u
r
es.
a.
Cla
s
s
if
ica
t
io
n
T
h
e
class
i
f
icatio
n
tec
h
n
iq
u
es
u
s
ed
in
t
h
is
s
t
u
d
y
ar
e
K
-
N
ea
r
est
Nei
g
h
b
o
u
r
(
KNN)
a
n
d
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
.
B
elo
w
ar
e
th
e
d
escr
ip
tio
n
s
o
f
t
h
ese
t
w
o
clas
s
i
f
ier
s
.
2
.
4
.
1
.
K
-
nea
re
s
t
neig
hb
o
r
(
K
NN)
K
-
Nea
r
est
Neig
h
b
o
u
r
(
KNN)
alg
o
r
ith
m
i
s
a
m
e
th
o
d
th
a
t
u
s
e
s
s
u
p
er
v
is
ed
al
g
o
r
ith
m
.
KNN
b
elo
n
g
s
to
in
s
ta
n
ce
-
b
ased
l
ea
r
n
in
g
g
r
o
u
p
.
T
h
is
al
g
o
r
ith
m
is
d
o
n
e
b
y
s
e
ar
ch
in
g
th
e
k
-
g
r
o
u
p
i
n
t
h
e
tr
ai
n
in
g
d
ata
s
i
m
i
lar
o
r
clo
s
est to
th
e
o
b
j
ec
t in
tes
tin
g
d
ata.
I
n
th
is
p
ap
er
,
th
e
v
al
u
e
o
f
k
is
s
et
to
1
,
an
d
th
e
E
u
c
lid
ea
n
d
is
ta
n
ce
f
o
r
m
u
l
a
in
(
9
)
is
u
s
ed
to
d
ef
i
n
e
th
e
d
is
t
an
ce
b
et
w
ee
n
t
w
o
o
b
j
ec
ts
x
an
d
y
[
2
8
]
.
,
=
√
∑
(
−
)
2
=
1
(
9
)
2
.
4
.
2
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chi
ne
(
SVM
)
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e,
p
r
esen
ted
b
y
[
2
9
]
is
a
tec
h
n
i
q
u
e
th
at
p
r
o
d
u
ce
g
o
o
d
p
r
ed
ictio
n
s
f
o
r
class
i
f
icatio
n
a
n
d
r
eg
r
es
s
io
n
.
T
h
is
alg
o
r
it
h
m
w
o
r
k
s
b
y
s
ea
r
ch
in
g
f
o
r
s
ep
ar
atio
n
b
et
w
ee
n
h
y
p
er
p
la
n
es d
e
n
o
ted
b
y
ca
te
g
o
r
ies
o
f
d
ata
.
T
h
e
o
b
j
ec
tiv
e
is
to
m
ea
s
u
r
e
t
h
e
m
ar
g
i
n
o
f
t
h
e
s
ep
ar
atio
n
o
f
t
h
e
d
ata.
T
h
e
b
est
s
ep
ar
ato
r
f
u
n
ctio
n
is
a
f
u
n
ctio
n
th
a
t is a
b
le
to
s
ep
ar
ate
th
e
d
ata
w
it
h
t
h
e
lar
g
est
m
ar
g
in
v
al
u
e,
e
x
ac
tl
y
b
et
w
ee
n
b
o
th
d
ata
class
es.
Her
e,
a
lin
ea
r
f
u
n
ctio
n
w
as c
h
o
s
e
n
as t
h
e
s
ep
ar
ato
r
f
u
n
ct
io
n
.
2
.
5
.
P
er
f
o
rm
a
nce
e
v
a
lua
t
io
n
I
n
th
is
p
ap
er
,
5
-
f
o
ld
cr
o
s
s
-
v
al
i
d
atio
n
m
eth
o
d
is
s
elec
ted
to
test
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
.
I
n
ad
d
itio
n
,
th
e
f
r
eq
u
en
tl
y
u
s
e
m
ea
s
u
r
e
m
e
n
t
f
o
r
class
if
ica
tio
n
w
h
ich
ar
e
s
e
n
s
it
iv
i
t
y
,
s
p
ec
i
f
icit
y
,
ac
cu
r
ac
y
an
d
F
-
m
ea
s
u
r
e
ar
e
also
u
s
ed
.
Se
n
s
iti
v
it
y
,
s
p
ec
i
f
ic
it
y
,
ac
cu
r
ac
y
an
d
F
-
m
ea
s
u
r
e
ar
e
d
ef
in
ed
as f
o
llo
w
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
F
ea
tu
r
e
s
elec
tio
n
fo
r
h
u
ma
n
mem
b
r
a
n
e
p
r
o
tein
typ
e
cla
s
s
ifica
tio
n
.
.
.
(
N
o
r
A
s
h
ikin
Mo
h
a
ma
d
K
a
ma
l
)
379
S
en
s
itivity
=
+
(
1
0
)
S
p
ec
ificity =
+
(
1
1
)
A
cc
u
r
a
cy
=
(
+
)
(
+
+
+
)
(
1
2
)
F
-
mea
s
u
r
e
=
2
∗
∗
+
(
1
3
)
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
p
u
r
p
o
s
e
o
f
th
e
ab
o
v
e
ex
p
er
i
m
en
ts
is
to
ac
q
u
ir
e
a
s
u
b
s
e
t
o
f
o
p
ti
m
u
m
f
ea
t
u
r
es.
T
h
e
ex
p
er
im
e
n
t
s
h
av
e
b
ee
n
ex
ec
u
ted
o
n
a
m
ac
h
in
e
w
it
h
1
.
6
GHz
C
P
U
an
d
8
GB
o
f
R
A
M.
W
e
i
m
p
le
m
e
n
t
th
e
al
g
o
r
ith
m
s
i
n
Ma
tlab
2
0
1
7
a.
T
ab
le
1
s
h
o
w
s
th
e
s
elec
ted
f
ea
t
u
r
es
f
o
r
C
FS
an
d
m
R
MR
alg
o
r
it
h
m
s
.
T
h
e
C
FS
alg
o
r
ith
m
s
elec
ted
4
5
f
ea
t
u
r
es
f
o
r
d
ata
s
et
S1
a
n
d
5
5
f
ea
t
u
r
es
f
o
r
d
at
aset
S2
.
W
h
ile
m
R
MR
s
elec
t
ed
1
2
7
f
ea
tu
r
es
f
o
r
d
ataset
S1
an
d
S2
t
o
ac
h
iev
e
it
s
m
a
x
i
m
u
m
ac
c
u
r
ac
y
.
T
ab
le
1
.
T
h
e
lis
t o
f
f
ea
t
u
r
es se
lecte
d
f
o
r
d
ataset
SI
an
d
S2
u
s
in
g
C
F
S a
n
d
m
R
M
R
M
e
t
h
o
d
S
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
D
a
t
a
se
t
S
1
w
i
t
h
C
F
S
F
S
me
t
h
o
d
(
4
5
f
e
a
t
u
r
e
s)
3
,
4
,
1
3
,
2
1
,
2
2
,
2
5
,
2
6
,
2
7
,
2
8
,
3
1
,
3
2
,
3
4
,
3
7
,
3
8
,
3
9
,
4
3
,
4
4
,
4
5
,
4
9
,
5
0
,
5
5
,
5
6
,
6
0
,
6
1
,
6
7
,
6
8
,
7
3
,
7
4
,
7
6
,
8
4
,
8
9
,
9
2
,
9
4
,
9
6
,
1
0
2
,
1
2
0
,
1
2
6
,
1
3
2
,
1
4
4
,
1
5
0
,
1
5
6
,
1
6
2
,
1
6
6
,
1
6
8
D
a
t
a
se
t
S
2
w
i
t
h
C
F
S
F
S
me
t
h
o
d
(
5
5
F
e
a
t
u
r
e
s)
4
,
1
3
,
1
9
,
2
2
,
2
3
,
2
5
,
2
6
,
2
7
,
2
8
,
3
1
,
3
2
,
3
3
,
3
7
,
3
8
,
3
9
,
4
3
,
4
4
,
4
5
,
4
9
,
5
0
,
5
5
,
5
6
,
6
0
,
6
1
,
6
2
,
6
7
,
6
8
,
7
3
,
7
4
,
7
9
,
8
2
,
8
4
,
8
5
,
8
8
,
9
1
,
9
4
,
9
6
,
9
8
,
1
0
2
,
1
0
8
,
1
1
3
,
1
1
4
,
1
2
0
,
1
2
4
,
1
2
6
,
1
3
0
,
1
3
2
,
1
3
8
,
1
4
4
,
1
5
0
,
1
5
4
,
1
5
6
,
1
6
2
,
1
6
8
,
1
6
9
D
a
t
a
se
t
S
1
w
i
t
h
mRM
R
F
S
me
t
h
o
d
(
1
2
7
f
e
a
t
s)
2
5
,
4
,
4
4
,
3
1
,
5
5
,
4
9
,
2
2
,
3
8
,
4
3
,
3
2
,
1
0
2
,
1
5
0
,
5
0
,
7
3
,
1
2
6
,
3
9
,
2
8
,
2
6
,
3
7
,
1
4
4
,
9
4
,
1
3
2
,
1
3
,
2
7
,
1
6
2
,
6
7
,
8
4
,
5
6
,
7
4
,
4
5
,
6
2
,
3
4
,
1
2
0
,
1
6
8
,
6
1
,
6
8
,
1
2
4
,
7
9
,
1
0
0
,
2
1
,
3
,
9
1
,
8
8
,
9
6
,
1
0
6
,
1
5
6
,
1
4
8
,
1
4
,
1
6
6
,
1
5
4
,
6
0
,
8
2
,
9
0
,
1
4
2
,
3
3
,
7
6
,
1
0
8
,
9
7
,
1
1
8
,
5
1
,
2
,
1
3
6
,
9
2
,
6
3
,
5
8
,
3
0
,
1
1
2
,
1
1
6
,
8
9
,
6
9
,
1
1
4
,
9
8
,
1
6
0
,
9
,
5
7
,
8
5
,
1
6
3
,
1
3
0
,
1
6
9
,
7
0
,
6
4
,
1
5
8
,
3
6
,
1
2
5
,
4
6
,
7
8
,
6
,
1
1
5
,
4
2
,
1
5
7
,
1
3
9
,
5
,
1
2
1
,
4
0
,
7
5
,
5
2
,
7
,
1
1
3
,
1
4
5
,
1
2
2
,
1
8
,
1
3
8
,
1
6
5
,
1
5
,
1
4
1
,
1
2
,
1
5
3
,
8
7
,
1
6
4
,
8
6
,
1
0
7
,
1
2
7
,
1
4
0
,
1
4
7
,
1
0
9
,
8
1
,
1
2
3
,
1
9
,
1
6
,
8
,
2
0
,
1
5
9
,
1
0
,
1
3
5
,
1
1
,
1
7
,
1
D
a
t
a
se
t
S
2
w
i
t
h
mRM
R
F
S
me
t
h
o
d
(
1
2
7
f
e
a
t
s)
2
5
,
4
,
3
1
,
4
3
,
4
9
,
3
2
,
3
7
,
5
6
,
1
5
0
,
4
4
,
5
0
,
1
4
4
,
2
2
,
1
3
,
8
4
,
5
5
,
3
8
,
1
2
6
,
1
3
2
,
6
7
,
3
9
,
1
0
2
,
2
7
,
7
3
,
6
2
,
2
6
,
1
5
6
,
1
2
0
,
4
5
,
6
1
,
9
4
,
8
8
,
7
8
,
3
,
2
8
,
1
6
8
,
1
6
2
,
1
1
4
,
1
0
8
,
9
6
,
9
1
,
7
4
,
1
4
2
,
6
0
,
6
8
,
1
4
8
,
9
7
,
2
1
,
1
9
,
1
3
8
,
3
3
,
5
7
,
9
2
,
3
0
,
1
5
4
,
1
1
8
,
1
6
9
,
8
2
,
6
3
,
1
6
6
,
2
,
7
9
,
6
4
,
1
4
,
2
3
,
9
8
,
1
2
4
,
9
0
,
1
1
2
,
5
1
,
1
0
0
,
6
9
,
1
0
6
,
5
8
,
1
1
6
,
3
4
,
1
3
6
,
1
3
0
,
1
5
7
,
1
6
7
,
7
6
,
1
3
9
,
3
6
,
1
6
0
,
1
6
3
,
9
,
8
5
,
1
5
3
,
5
,
4
2
,
1
6
5
,
4
6
,
1
0
3
,
8
0
,
7
0
,
4
1
,
1
2
1
,
1
4
5
,
1
5
9
,
8
9
,
1
5
1
,
1
5
8
,
6
,
1
4
1
,
1
8
,
2
4
,
7
5
,
1
2
3
,
1
1
0
,
1
2
7
,
1
2
,
1
1
5
,
1
3
5
,
5
3
,
1
5
,
1
6
4
,
9
9
,
1
1
,
2
0
,
1
0
,
5
9
,
7
,
1
,
1
4
7
,
8
,
1
6
,
1
7
T
ab
le
2
p
r
esen
ts
th
e
r
esu
lts
o
f
class
i
f
ica
tio
n
m
e
th
o
d
s
o
n
th
e
S1
m
e
m
b
r
a
n
e
p
r
o
tein
d
ataset.
I
n
th
i
s
tab
le,
th
e
MRM
R
-
KNN
o
b
tain
s
7
6
%
ac
cu
r
ac
y
,
0
.
5
0
7
1
s
en
s
iti
v
it
y
,
0
.
7
4
6
7
s
p
ec
if
icit
y
a
n
d
0
.
6
0
3
7
F
-
m
ea
s
u
r
e
b
y
u
s
i
n
g
1
2
7
f
ea
tu
r
es,
w
h
ic
h
is
th
e
h
i
g
h
est
f
r
o
m
all
th
e
m
eth
o
d
s
.
Ho
w
e
v
er
,
SVM
class
i
f
ier
p
r
o
d
u
ce
s
7
6
%
a
cc
u
r
ac
y
b
y
u
s
i
n
g
all
th
e
1
7
0
f
ea
t
u
r
es
w
it
h
o
u
t
f
ea
t
u
r
e
s
e
le
ctio
n
.
T
h
er
ef
o
r
e,
b
et
w
ee
n
th
e
s
e
t
w
o
al
g
o
r
ith
m
s
,
m
R
MR
-
KNN
is
b
etter
s
in
ce
i
t
ca
n
p
r
o
d
u
ce
th
e
s
a
m
e
ac
c
u
r
ac
y
as
SVM
w
i
th
f
e
w
er
n
u
m
b
er
o
f
f
ea
t
u
r
es.
T
h
e
C
FS
-
S
VM
m
eth
o
d
p
r
o
d
u
ce
s
t
h
e
co
m
p
etiti
v
e
r
es
u
lt
w
h
i
c
h
i
s
7
5
% a
cc
u
r
ac
y
b
y
o
n
l
y
u
s
in
g
4
5
f
ea
tu
r
es.
O
v
er
all,
m
R
MR
-
KNN
m
et
h
o
d
is
s
u
ita
b
le
f
o
r
m
e
m
b
r
an
e
p
r
o
tein
cla
s
s
if
ica
tio
n
i
n
d
ataset
S1
.
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
o
f
S1
M
e
t
h
o
d
S
e
l
e
c
t
e
d
F
e
a
t
u
r
e
s
A
c
c
u
r
a
c
y
(
%)
S
e
n
si
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
F
-
M
e
a
su
r
e
K
N
N
-
7
4
%
0
.
4
6
8
3
0
.
5
6
6
7
0
.
5
1
2
3
mRM
R
-
K
N
N
1
2
7
7
6
%
0
.
5
0
7
1
0
.
7
4
6
7
0
.
6
0
3
7
C
F
S
-
K
N
N
45
7
2
%
0
.
4
9
7
0
.
5
7
8
0
.
5
3
4
S
V
M
-
7
6
%
0
.
5
3
1
7
0
.
5
5
8
3
0
.
5
4
4
7
mRM
R
-
S
V
M
1
2
7
7
6
%
0
.
5
5
5
0
.
5
6
5
0
.
5
5
6
C
F
S
-
S
V
M
45
7
5
%
0
.
4
5
5
0
.
5
0
5
0
.
4
7
8
6
T
ab
le
3
s
h
o
w
s
t
h
e
r
esu
lts
o
f
class
i
f
icatio
n
m
et
h
o
d
s
o
n
S2
m
e
m
b
r
a
n
e
p
r
o
tein
d
ataset.
I
n
th
is
tab
le
,
C
FS
-
S
VM
p
r
o
d
u
ce
s
t
h
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
w
h
ic
h
i
s
7
3
%,
0
.
5
0
3
3
s
en
s
iti
v
it
y
,
0
.
6
0
8
3
s
p
ec
if
i
cit
y
a
n
d
0
.
5
5
0
8
F
-
m
ea
s
u
r
e
b
y
u
s
i
n
g
o
n
l
y
5
5
f
e
atu
r
es
.
MRM
R
-
SVM
p
r
o
d
u
ce
d
co
m
p
etiti
v
e
r
esu
lt
s
w
ith
7
2
%
ac
cu
r
ac
y
,
0
.
5
7
1
s
en
s
iti
v
it
y
,
0
.
6
3
2
s
p
ec
if
icit
y
an
d
0
.
6
F
-
m
ea
s
u
r
e
b
y
u
s
in
g
1
2
7
f
ea
tu
r
es.
SVM
class
i
f
ier
p
r
o
d
u
ce
s
7
1
%
ac
cu
r
ac
y
,
0
.
5
5
5
s
en
s
iti
v
it
y
,
0
.
5
6
5
s
p
ec
if
icit
y
a
n
d
0
.
5
5
9
9
F
-
m
ea
s
u
r
e
b
y
u
s
i
n
g
all
1
7
0
f
ea
t
u
r
es.
KNN
cla
s
s
i
f
ier
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
A
I
Vo
l.
8
,
No
.
4
,
Dec
em
b
er
201
9
:
3
75
–
38
1
380
i
s
u
n
s
u
i
tab
le
b
ec
au
s
e
o
f
lo
w
p
er
f
o
r
m
an
ce
s
.
T
h
er
ef
o
r
e,
C
F
S
-
SVM
al
g
o
r
ith
m
i
s
s
u
itab
le
f
o
r
m
e
m
b
r
an
e
p
r
o
tei
n
class
i
f
icatio
n
in
d
atase
t S2
.
T
ab
le
3
.
P
er
f
o
r
m
a
n
ce
o
f
S2
M
e
t
h
o
d
S
e
l
e
c
t
e
d
F
e
a
t
u
r
e
s
A
c
c
u
r
a
c
y
(
%)
S
e
n
si
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
F
-
M
e
a
su
r
e
K
N
N
-
6
1
%
0
.
3
5
5
0
.
4
5
8
3
0
.
4
0
0
1
mRM
R
-
K
N
N
1
2
7
6
6
%
0
.
3
9
0
.
5
2
8
0
.
4
4
8
7
C
F
S
-
K
N
N
55
6
2
%
0
.
3
5
8
3
0
.
3
7
8
3
0
.
3
6
8
0
S
V
M
-
7
1
%
0
.
5
5
5
0
.
5
6
5
0
.
5
5
9
9
mRM
R
-
S
V
M
1
2
7
7
2
%
0
.
5
7
1
0
.
6
3
2
0
.
6
C
F
S
-
S
V
M
55
7
3
%
0
.
5
0
3
3
0
.
6
0
8
3
0
.
5
5
0
8
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
u
g
g
ested
m
o
d
el
w
a
s
co
m
p
ar
ed
w
it
h
p
r
io
r
m
o
d
els
o
n
th
e
t
w
o
d
ata
s
ets
in
T
ab
le
4
.
I
n
th
e
ca
s
e
o
f
d
ata
s
et
S1
,
R
W
C
[
7
]
,
MCS
VM
[
1
9
]
an
d
Me
m
p
r
ed
[
2
0
]
h
as
y
iel
d
ed
m
o
r
e
th
a
n
8
0
%
ac
cu
r
ac
y
.
NN
A
b
ased
m
et
h
o
d
[
7
]
h
as
o
b
tain
ed
7
0
.
4
%
ac
cu
r
ac
y
.
O
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
o
b
tain
ed
7
6
%
ac
cu
r
ac
y
,
h
ig
h
er
th
a
n
NN
A
b
ased
m
et
h
o
d
.
T
h
e
r
ea
s
o
n
f
o
r
th
is
i
s
b
ec
au
s
e
NN
A
b
ased
m
eth
o
d
[
7
]
u
s
ed
th
e
s
i
m
ilar
p
r
o
tein
f
ea
t
u
r
e
ex
tr
ac
t
io
n
s
tr
ate
g
y
w
it
h
o
u
r
m
e
th
o
d
.
Ho
w
e
v
er
,
o
u
r
m
et
h
o
d
i
m
p
le
m
en
ted
th
e
f
ea
tu
r
e
s
elec
tio
n
p
h
ase
t
h
at
i
m
p
r
o
v
ed
th
e
NN
A
b
ased
m
eth
o
d
[
7
]
a
cc
u
r
ac
y
.
Me
m
p
r
ed
[
2
0
]
w
a
s
a
b
le
to
o
b
tain
8
8
%
ac
cu
r
ac
y
w
h
ic
h
is
t
h
e
h
i
g
h
est
ac
cu
r
ac
y
a
m
o
n
g
th
e
t
h
r
ee
m
eth
o
d
s
.
On
t
h
e
o
th
er
h
a
n
d
,
in
th
e
ca
s
e
o
f
d
atase
t
S2
,
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
h
a
s
y
ield
ed
7
3
%
ac
cu
r
ac
y
,
h
ig
h
er
th
a
n
R
W
C
[
7
]
a
n
d
NN
A
[
7
]
m
et
h
o
d
s
.
MC
SVM
[
1
9
]
an
d
Me
m
p
r
ed
[
2
0
]
o
b
tain
ed
8
6
.
1
1
%
an
d
8
2
%
ac
cu
r
ac
y
r
esp
ec
tiv
el
y
.
Fro
m
t
h
e
co
m
p
ar
is
o
n
,
it
s
h
o
w
s
t
h
at
f
ea
t
u
r
e
s
elec
tio
n
p
h
ase
u
n
ab
le
to
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
h
u
m
a
n
m
e
m
b
r
an
e
p
r
o
tein
cla
s
s
i
f
icatio
n
.
T
ab
le
4
.
C
o
m
p
ar
is
o
n
o
f
p
r
o
p
o
s
ed
m
o
d
el
w
i
th
p
r
ev
io
u
s
m
et
h
o
d
s
.
D
a
t
a
se
t
N
N
A
b
a
se
d
o
n
P
se
A
A
C
[
7
]
R
W
C
[
7
]
M
C
S
V
M
[
1
9
]
M
e
mp
r
e
d
[
2
0
]
P
r
o
p
o
se
d
M
e
t
h
o
d
SI
7
0
.
4
1
%
8
1
.
3
4
%
8
3
.
3
3
%
8
8
%
7
6
%
S2
6
1
.
7
0
%
7
1
.
4
0
%
8
6
.
1
1
%
8
2
%
7
3
%
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
esen
ts
t
h
e
f
ilter
f
ea
t
u
r
e
s
elec
tio
n
m
et
h
o
d
f
o
r
h
u
m
a
n
m
e
m
b
r
an
e
p
r
o
tein
cla
s
s
i
f
icatio
n
.
W
e
ap
p
lied
t
w
o
t
y
p
es
o
f
f
il
ter
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
,
m
R
MR
a
n
d
C
FS
.
T
w
o
class
i
f
ie
r
s
,
KNN
an
d
SVM
ar
e
u
s
ed
f
o
r
class
i
f
icat
io
n
.
C
o
m
p
ar
ed
w
i
th
th
e
p
r
e
v
io
u
s
m
e
t
h
o
d
s
o
n
t
h
e
s
a
m
e
d
ataset,
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
r
ed
u
ce
d
th
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
f
o
r
class
if
ica
tio
n
.
Ho
w
e
v
e
r
,
th
er
e
h
av
e
b
ee
n
n
o
i
m
p
o
r
tan
t
c
h
a
n
g
e
s
to
t
h
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
o
f
t
h
e
cl
ass
i
f
icatio
n
s
y
s
te
m
b
y
ad
d
in
g
th
i
s
f
ea
tu
r
e
s
elec
tio
n
p
h
ase.
T
h
er
e
ar
e
a
lo
t
o
f
en
h
a
n
ce
m
en
ts
t
h
at
ca
n
b
e
m
a
d
e
to
th
is
p
r
o
j
ec
t
in
th
e
f
u
tu
r
e
,
th
e
f
ea
t
u
r
e
s
elec
tio
n
tec
h
n
iq
u
es
co
u
ld
b
e
h
y
b
r
id
to
en
h
an
ce
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
f
ea
tu
r
e
s
elec
t
io
n
tech
n
iq
u
es.
I
n
ad
d
itio
n
,
th
e
f
ea
t
u
r
es
co
u
ld
b
e
o
p
ti
m
ized
b
y
u
s
i
n
g
m
e
tah
e
u
r
is
t
ic
alg
o
r
it
h
m
a
n
d
o
th
er
clas
s
if
icatio
n
tec
h
n
iq
u
es.
RE
F
E
R
E
NC
ES
[1
]
S
.
K.
G
o
lm
o
h
a
m
m
a
d
i,
L
.
Ku
rg
a
n
,
B.
Cro
w
ley
,
M
.
Re
f
o
r
m
a
t,
“
Clas
sif
ic
a
ti
o
n
o
f
c
e
ll
m
e
m
b
ra
n
e
p
ro
tein
s,”
I
n
Fro
n
ti
e
rs
i
n
th
e
C
o
n
v
e
rg
e
n
c
e
o
f
Bi
o
sc
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
ies
FB
I
T
2
0
0
7
,
p
p
.
1
5
3
-
1
5
8
,
2
0
0
7
.
[2
]
J.
H.
Kle
in
sc
h
m
id
t,
"
M
e
m
b
ra
n
e
P
r
o
tein
s
-
I
n
tro
d
u
c
ti
o
n
,
"
Ce
ll
u
l
a
r
a
n
d
M
o
lec
u
l
a
r
L
i
fe
S
c
ien
c
e
s
CM
L
S
,
v
o
l.
6
0
,
p
p
.
1
5
2
7
-
1
5
2
8
,
2
0
0
3
.
[3
]
G
.
Hu
a
n
g
,
Y.
Zh
a
n
g
,
L
.
Ch
e
n
,
N.
Zh
a
n
g
,
T
.
Hu
a
n
g
,
Y.D.
C
a
i,
“
P
re
d
icti
o
n
o
f
m
u
lt
i
-
t
y
p
e
m
e
m
b
r
a
n
e
p
ro
tein
s
i
n
h
u
m
a
n
b
y
a
n
in
teg
ra
ted
a
p
p
ro
a
c
h
.
”
,
P
lo
S
On
e
,
v
o
l
.
9
,
n
o
.
3
,
2
0
1
4
.
[4
]
J.
Qiu
,
X
.
S
u
n
,
J.
Hu
a
n
g
,
R.
L
i
a
n
g
,
“
P
re
d
icti
o
n
o
f
th
e
ty
p
e
s
o
f
m
e
m
b
ra
n
e
p
ro
tein
s
b
a
se
d
o
n
d
isc
re
te
w
a
v
e
let
tran
sf
o
r
m
a
n
d
su
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
s,”
T
h
e
Pro
tei
n
J
o
u
rn
a
l
,
v
o
l.
2
9
,
n
o
.
2
,
p
p
.
1
1
4
-
1
1
9
,
2
0
1
0
.
[5
]
M
.
J.
Iq
b
a
l,
I.
F
a
y
e
,
B.
B.
S
a
m
ir,
A
.
M
.
S
a
id
,
“
Eff
i
c
ien
t
fe
a
tu
re
se
l
e
c
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
o
f
p
ro
tein
se
q
u
e
n
c
e
d
a
ta
in
b
io
i
n
f
o
rm
a
ti
c
s”
,
T
h
e
S
c
ien
ti
f
ic
W
o
rld
J
o
u
r
n
a
l
,
2
0
1
4
.
[6
]
F
.
R.
Ka
m
a
la,
P
.
R
.
T
h
a
n
g
a
iah
,
“
A
n
im
p
ro
v
e
d
h
y
b
rid
f
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
f
o
r
h
u
g
e
d
im
e
n
sio
n
a
l
d
a
tas
e
ts,”
IAE
S
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Art
if
icia
l
In
telli
g
e
n
c
e
(
IJ
-
AI)
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
7
7
-
8
6
,
2
0
1
9
.
[7
]
K.
Ka
d
a
m
,
S
.
S
a
w
a
n
t,
U.
Ku
lk
a
rn
i
-
Ka
le,
V
.
K
.
Ja
y
a
r
a
m
a
n
,
“
P
r
e
d
ictio
n
o
f
p
r
o
tein
f
u
n
c
ti
o
n
b
a
s
e
d
o
n
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
s: an
o
v
e
rv
ie
w
,
”
Ge
n
o
mic
s III
M
e
th
o
d
s
,
T
e
c
h
n
iq
u
e
s a
n
d
Ap
p
li
c
a
ti
o
n
s
,
iC
o
n
c
e
p
t
P
re
ss
L
td
,
2
0
1
4
.
[8
]
B.
Ku
m
a
ri,
T
.
S
w
a
rn
k
a
r,
“
F
il
ter
v
e
rsu
s
w
ra
p
p
e
r
f
e
a
tu
re
su
b
se
t
s
e
lec
ti
o
n
i
n
larg
e
d
im
e
n
sio
n
a
li
ty
m
icro
a
rra
y
:
A
re
v
ie
w
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
a
n
d
In
f
o
rm
a
t
io
n
T
e
c
h
n
o
lo
g
ies
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
1
0
4
8
-
1
0
5
3
,
2
0
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
F
ea
tu
r
e
s
elec
tio
n
fo
r
h
u
ma
n
mem
b
r
a
n
e
p
r
o
tein
typ
e
cla
s
s
ifica
tio
n
.
.
.
(
N
o
r
A
s
h
ikin
Mo
h
a
ma
d
K
a
ma
l
)
381
[9
]
A
.
A
d
e
le
k
e
,
N.
A
.
S
a
m
su
d
in
,
Z.
A
.
Oth
m
a
n
,
S
.
.
K.
A
h
m
a
d
Kh
a
li
d
,
“
A
t
w
o
-
ste
p
f
e
a
tu
re
se
le
c
ti
o
n
m
e
t
h
o
d
f
o
r
q
u
ra
n
i
c
tex
t
c
las
sif
i
c
a
ti
o
n
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
1
6
,
n
o
.
2
,
p
p
.
7
3
0
-
7
3
6
,
2
0
1
9
.
[1
0
]
N.A
.
M
.
Ka
m
a
l,
A
.
A
.
Ba
k
a
r
,
S
.
Zain
u
d
in
,
“
Clas
sif
ica
ti
o
n
o
f
Hu
m
a
n
M
e
m
b
ra
n
e
P
ro
tein
T
y
p
e
s
u
sin
g
Op
ti
m
a
l
L
o
c
a
l
Disc
ri
m
in
a
n
t
Ba
se
s
F
e
a
tu
re
Ex
tra
c
ti
o
n
M
e
th
o
d
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
r
e
ti
c
a
l
a
n
d
A
p
p
li
e
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
9
6
,
n
o
.
3
,
p
p
.
7
6
7
-
7
7
1
,
2
0
1
8
.
[1
1
]
N.
Ra
j,
T
.
M
a
h
a
lek
sh
m
i,
“
Hu
m
a
n
m
e
m
b
ra
n
e
p
ro
tein
c
las
sif
ica
ti
o
n
u
si
n
g
M
u
l
ti
c
las
s
S
u
p
p
o
rt
Ve
c
to
r
M
a
c
h
in
e
(M
CS
VM),
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
ien
c
e
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
1
-
5
,
2
0
1
8
.
[1
2
]
H.
Ya
n
ju
n
,
H
.
G
u
o
h
u
a
,
“
A
h
o
m
o
lo
g
y
a
n
d
p
se
u
d
o
-
a
m
in
o
a
c
id
c
o
m
p
o
siti
o
n
b
a
se
d
m
u
lt
i
-
la
b
e
l
m
o
d
e
l
f
o
r
p
re
d
icti
n
g
h
u
m
a
n
m
e
m
b
ra
n
e
p
ro
tein
ty
p
e
s,”
Cu
rr
e
n
t
Pro
te
o
mic
s
,
v
o
l.
1
5
,
n
o
.
2
,
p
p
.
1
3
5
-
1
4
1
,
2
0
1
8
.
[1
3
]
M
.
A
rif
,
M
.
Ha
y
a
t,
Z.
Ja
n
,
“
iM
e
m
-
2
L
S
AA
C:
A
t
w
o
-
lev
e
l
m
o
d
e
l
fo
r
d
isc
rim
in
a
ti
o
n
o
f
m
e
m
b
ra
n
e
p
ro
tein
s
a
n
d
th
e
ir
ty
p
e
s
b
y
e
x
ten
d
in
g
th
e
n
o
ti
o
n
o
f
S
AA
C
in
to
C
h
o
u
’s
ps
e
u
d
o
a
m
in
o
a
c
id
c
o
m
p
o
siti
o
n
,
”
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
Bi
o
lo
g
y
,
v
o
l
.
4
4
2
,
p
p
.
1
1
-
2
1
,
2
0
1
8
.
[1
4
]
M
.
A
.
Re
z
a
e
i,
P
.
A
b
d
o
lm
a
lek
i,
S
.
Ja
h
a
n
d
id
e
h
,
Z.
Ka
ra
m
i,
E.
B.
A
sa
d
a
b
a
d
i,
M
.
A
.
S
h
e
ra
f
a
t,
H.
A
b
rish
a
m
i
-
M
o
g
h
a
d
d
a
m
,
M
.
F
a
d
a
ie,
a
n
d
M
.
F
o
ro
u
z
a
n
f
a
r,
“
P
re
d
ictio
n
o
f
m
e
m
b
ra
n
e
p
r
o
tein
ty
p
e
s
b
y
m
e
a
n
s
o
f
w
a
v
e
let
a
n
a
l
y
sis
a
n
d
c
a
sc
a
d
e
d
n
e
u
ra
l
n
e
tw
o
rk
s,”
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
Bi
o
lo
g
y
,
v
o
l.
2
5
4
,
n
o
.
4
,
p
p
.
8
1
7
-
8
2
0
,
Oc
t.
2
0
0
8
.
[1
5
]
L
.
Wan
g
,
Z.
Yu
a
n
,
X
.
Ch
e
n
,
Z.
Z
h
o
u
,
“
T
h
e
p
re
d
ictio
n
o
f
m
e
m
b
ra
n
e
p
ro
tei
n
ty
p
e
s
w
it
h
NP
E,
”
IEI
CE
El
e
c
tro
n
ic
s
Exp
re
ss
,
v
o
l.
7
,
n
o
.
6
,
p
p
.
3
9
7
-
4
0
2
,
2
0
1
0
.
[1
6
]
C.
Un
i
P
r
o
t
,
“
T
h
e
Un
iv
e
rsa
l
P
ro
tei
n
Re
so
u
rc
e
(Un
i
P
ro
t)
in
2
0
1
0
,
”
N
u
c
leic
Acid
s R
e
s 3
8
,
p
p
.
1
4
2
–
1
4
8
,
2
0
1
0
.
[1
7
]
F
.
A
li
,
M
.
Ha
y
a
t,
“
Clas
si
f
ica
ti
o
n
o
f
m
e
m
b
ra
n
e
p
ro
tein
ty
p
e
s
u
sin
g
v
o
ti
n
g
f
e
a
tu
re
in
terv
a
l
in
c
o
m
b
in
a
ti
o
n
w
it
h
Ch
o
u
’s
p
se
u
d
o
a
m
in
o
a
c
id
c
o
m
p
o
siti
o
n
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
re
ti
c
a
l
Bi
o
lo
g
y
,
v
o
l.
3
8
4
,
p
p
.
7
8
-
8
3
,
2
0
1
5
.
[1
8
]
K.C.
Ch
o
u
,
“
P
re
d
ictio
n
o
f
p
ro
tei
n
c
e
ll
u
lar
a
tt
rib
u
tes
u
si
n
g
p
se
u
d
o
-
a
m
in
o
a
c
id
c
o
m
p
o
siti
o
n
,
”
PR
OTE
I
NS
:
S
tr
u
c
tu
re
,
Fu
n
c
ti
o
n
,
a
n
d
Ge
n
e
t
ics
,
v
o
l.
4
3
,
p
p
.
2
4
6
-
2
5
5
,
2
0
0
1
a
.
[1
9
]
K.C.
Ch
o
u
,
“
Us
in
g
su
b
site c
o
u
p
li
n
g
to
p
re
d
ict
sig
n
a
l
p
e
p
ti
d
e
s,”
Pro
tein
E
n
g
in
e
e
rin
g
,
v
o
l.
1
4
,
p
p
.
7
5
-
7
9
.
2
0
0
1
b
.
[2
0
]
Q.
B.
G
a
o
,
X
.
F
.
Ye
,
J.
He
,
“
Clas
sify
in
g
G
-
P
ro
tein
-
Co
u
p
led
Re
c
e
p
t
o
rs
to
t
h
e
f
in
e
st
su
b
ty
p
e
lev
e
l,
”
Bi
o
c
h
e
mic
a
l
a
n
d
Bi
o
p
h
y
sic
a
l
Res
e
a
rc
h
C
o
mm
u
n
ica
ti
o
n
s
,
v
o
l
.
4
3
9
(
2
),
p
p
.
3
0
3
-
3
0
8
,
2
0
1
3
.
[2
1
]
M
.
Ha
ll
,
“
Co
rre
latio
n
-
b
a
se
d
f
e
a
t
u
re
su
b
se
t
se
lec
ti
o
n
f
o
r
m
a
c
h
in
e
lea
rn
in
g
,
”
P
h
.
D
d
isse
rtatio
n
,
Un
iv
.
W
a
ik
a
to
,
Ha
m
il
to
m
,
Ne
w
Zea
l
a
n
d
,
1
9
9
9
.
[2
2
]
H.C.
P
e
n
g
,
F
.
L
o
n
g
,
C.
Din
g
.
,
“
F
e
a
tu
re
se
lec
ti
o
n
b
a
se
d
in
m
u
tu
a
l
in
f
o
rm
a
ti
o
n
:criteria
o
f
m
a
x
-
d
e
p
e
n
d
e
n
c
y
m
a
x
-
re
lev
a
n
c
e
a
n
d
m
in
-
re
d
u
n
d
a
n
c
y
,
”
2
nd
IEE
E
T
r
a
n
sc
a
c
ti
o
n
s o
n
P
a
tt
e
rn
An
a
lys
is a
n
d
M
a
c
h
i
n
e
In
telli
g
e
n
c
e
,
v
o
l.
2
7
,
n
o
.
8
,
p
p
.
1
2
2
6
-
1
2
3
8
,
2
0
0
5
.
[2
3
]
I.
Jo
,
S
.
L
e
e
,
S
.
O
h
,
“
Im
p
ro
v
e
d
m
e
su
re
s
o
f
re
d
u
n
d
a
n
c
y
a
n
d
re
lev
a
n
c
e
f
o
r
m
RM
R
f
e
a
tu
re
se
lec
ti
o
n
,
”
Co
m
p
u
ter
s
,
v
o
l.
8
,
n
o
.
2
,
p
p
.
1
-
1
4
,
2
0
1
9
.
[2
4
]
P
.
Jia
,
Z.
Qia
n
,
K.
F
e
n
g
,
W
.
L
u
,
Y.
L
i,
Y.
C
a
i,
Y.,
“
P
re
d
ictio
n
o
f
m
e
m
b
r
a
n
e
p
ro
tein
ty
p
e
s
in
a
h
y
b
rid
sp
a
c
e
”
,
J
o
u
rn
a
l
o
f
Pro
te
o
me
Res
e
a
rc
h
,
v
o
l.
7
,
n
o
.
3
,
p
p
.
1
1
3
1
-
1
1
3
7
,
2
0
0
8
.
[2
5
]
B.
Q.
L
i,
L
.
Hu
,
L
.
Ch
e
n
,
K.Y.
F
e
n
g
,
Y.D.
Ca
i,
K.C.
Ch
o
u
,
“
P
r
e
d
ictio
n
o
f
p
ro
tein
d
o
m
a
in
w
it
h
m
RM
R
fe
a
tu
re
se
lec
ti
o
n
a
n
d
a
n
a
ly
sis.”
,
P
L
o
S
On
e
,
v
o
l.
7
,
n
o
.
6
,
2
0
1
2
.
[2
6
]
S
.
Kh
a
n
,
“
M
a
c
h
i
n
e
L
e
a
rn
in
g
Ap
p
r
o
a
c
h
e
s
f
o
r
th
e
P
re
d
ictio
n
o
f
P
r
o
tein
S
e
q
u
e
n
c
e
s,”
P
h
.
D
d
isse
r
tatio
n
,
Ka
ra
c
h
i
In
stit
u
te
o
f
Eco
n
o
m
ics
a
n
d
T
e
c
h
n
o
lo
g
y
,
2
0
1
4
.
[2
7
]
C.
Din
g
,
&
H
.
P
e
n
g
,
“
M
in
im
u
m
re
d
u
n
d
a
n
c
y
f
e
a
tu
re
se
lec
ti
o
n
f
ro
m
m
icro
a
rra
y
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta,”
J
o
u
rn
a
l
o
f
Bi
o
in
fo
rm
a
t
ics
a
n
d
C
o
mp
u
ta
ti
o
n
a
l
Bi
o
lo
g
y
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
1
8
5
-
2
0
5
,
2
0
0
5
.
[2
8
]
W
.
L
u
m
c
h
a
n
o
w
,
S
.
Ud
o
m
siri,
“
I
m
a
g
e
c
la
ss
i
f
ica
ti
o
n
o
f
m
a
lari
a
u
sin
g
h
y
b
rid
a
lg
o
rit
h
m
s:
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
m
e
th
o
d
to
f
in
d
a
p
p
r
o
p
riate
K f
o
r
K
-
Ne
a
re
st
Ne
ig
h
b
o
u
r,
”
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ie
n
c
e
,
v
o
l.
1
6
,
n
o
.
1
,
p
p
.
3
8
2
-
3
8
8
,
2
0
1
9
.
[2
9
]
V
.
N.
V
a
p
n
ik
,
T
h
e
n
a
t
u
re
o
f
sta
ti
stica
l
lea
rn
in
g
th
e
o
ry
,
S
p
ri
n
g
e
r
,
1
9
9
5
.
[3
0
]
C.
Din
g
,
&
H
.
P
e
n
g
,
“
M
in
im
u
m
re
d
u
n
d
a
n
c
y
f
e
a
tu
re
se
lec
ti
o
n
f
ro
m
m
icro
a
rra
y
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta,”
J
o
u
rn
a
l
o
f
Bi
o
in
fo
rm
a
t
ics
a
n
d
C
o
mp
u
ta
ti
o
n
a
l
Bi
o
lo
g
y
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
1
8
5
-
2
0
5
,
2
0
0
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.