I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
,
p
p
.
4
7
0
3
~
4
7
1
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
6
.
p
p
4
7
0
3
-
4
7
1
0
4703
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Deep learni
ng
-
ba
sed featu
re sele
cti
o
n f
o
r lung a
deno
ca
rcino
ma
cla
ss
ificatio
n and
bio
ma
rker disco
v
ery
Sa
ra
H
a
dd
o
u B
o
ua
zz
a
1
,
J
iha
d H
a
dd
o
u
B
o
ua
zz
a
2
1
LA
M
I
G
EP
La
b
o
r
a
t
o
r
y
,
M
o
r
o
c
c
a
n
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
s (E
M
S
I
)
,
M
a
r
r
a
k
e
c
h
,
M
o
r
o
c
c
o
2
S
e
n
i
o
r
F
u
l
l
S
t
a
c
k
D
e
v
e
l
o
p
e
r
a
n
d
Te
c
h
L
e
a
d
,
N
e
x
u
l
a
r
C
o
r
p
.
,
C
a
sa
b
l
a
n
c
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
9
,
2
0
2
5
R
ev
is
ed
Au
g
2
3
,
2
0
2
5
Acc
ep
ted
Sep
7
,
2
0
2
5
Lu
n
g
a
d
e
n
o
c
a
rc
in
o
m
a
,
a
lea
d
in
g
c
a
u
se
o
f
c
a
n
c
e
r
-
re
late
d
m
o
rtalit
y
,
u
n
d
e
rsc
o
re
s
th
e
n
e
e
d
f
o
r
re
li
a
b
l
e
d
iag
n
o
stic
to
o
ls.
Th
is
stu
d
y
p
ro
p
o
se
s
a
ro
b
u
st
m
u
lt
i
-
sta
g
e
fe
a
tu
re
se
lec
ti
o
n
a
n
d
c
las
sifica
ti
o
n
fra
m
e
wo
rk
f
o
r
b
io
m
a
rk
e
r
d
isc
o
v
e
ry
,
u
sin
g
th
e
c
a
n
c
e
r
g
e
n
o
m
e
a
tl
a
s
lu
n
g
a
d
e
n
o
c
a
rc
in
o
m
a
(
TCG
A
-
LUAD
)
a
s
th
e
p
rima
ry
d
a
tas
e
t
a
n
d
G
S
E1
9
1
8
8
fo
r
in
d
e
p
e
n
d
e
n
t
v
a
li
d
a
ti
o
n
.
Th
e
fra
m
e
wo
rk
c
o
m
b
in
e
s
d
i
ffe
re
n
ti
a
l
e
x
p
re
ss
io
n
a
n
a
ly
si
s
(W
il
c
o
x
o
n
ra
n
k
-
su
m
tes
t),
j
o
in
t
m
u
tu
a
l
in
f
o
rm
a
ti
o
n
m
a
x
imiz
a
ti
o
n
(JMIM
)
,
a
n
d
sp
a
rse
a
u
t
o
e
n
c
o
d
e
r
-
b
a
se
d
re
fin
e
m
e
n
t
to
id
e
n
t
ify
a
c
o
m
p
a
c
t
a
n
d
p
re
d
ictiv
e
se
t
o
f
fi
v
e
g
e
n
e
s.
T
h
e
se
g
e
n
e
s
a
re
i
n
v
o
lv
e
d
i
n
k
e
y
lu
n
g
c
a
n
c
e
r
p
a
th
wa
y
s,
in
c
l
u
d
i
n
g
e
p
i
d
e
rm
a
l
g
r
o
wth
fa
c
to
r
re
c
e
p
to
r
(
EG
F
R
)
sig
n
a
li
n
g
,
c
e
ll
c
y
c
le
re
g
u
latio
n
,
a
n
d
imm
u
n
e
r
e
sp
o
n
se
,
a
n
d
in
c
lu
d
e
b
i
o
m
a
rk
e
rs
su
c
h
a
s
su
rfa
c
tan
t
p
ro
tein
A2
(
S
F
TP
A
2
)
,
n
a
p
sin
a
n
a
sp
a
rti
c
p
e
p
ti
d
a
se
(
NA
P
S
A
)
,
a
n
d
T
-
b
o
x
tran
sc
rip
t
io
n
fa
c
to
r
4
(
T
BX4
)
.
Th
e
h
y
b
r
id
d
e
e
p
lea
rn
in
g
c
las
sifier
a
c
h
iev
e
d
h
i
g
h
a
c
c
u
ra
c
y
(9
8
.
4
%
)
a
n
d
a
re
a
u
n
d
e
r
th
e
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic
c
u
rv
e
(
AUC
-
ROC
)
(0
.
9
9
6
)
o
n
TCG
A
-
LUAD
,
with
stro
n
g
g
e
n
e
ra
li
z
a
ti
o
n
o
n
G
S
E1
9
1
8
8
(
a
c
c
u
ra
c
y
:
9
6
.
7
%
,
AU
C
-
ROC:
0
.
9
9
3
%
)
.
Ov
e
ra
ll
,
t
h
e
fra
m
e
wo
rk
o
ffe
rs
a
n
i
n
terp
re
tab
le
a
n
d
e
ffe
c
ti
v
e
s
o
l
u
ti
o
n
f
o
r
LUAD
c
las
sifica
ti
o
n
a
n
d
b
i
o
m
a
rk
e
r
id
e
n
ti
fica
ti
o
n
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
C
an
ce
r
class
if
icatio
n
C
o
m
p
u
ter
s
cien
ce
Featu
r
e
s
elec
tio
n
Ma
ch
in
e
lear
n
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sar
a
Had
d
o
u
B
o
u
az
z
a
L
AM
I
GE
P
L
ab
o
r
ato
r
y
,
Mo
r
o
cc
an
Sch
o
o
l
o
f
E
n
g
in
ee
r
in
g
Scien
ce
s
(
E
MSI
)
Ma
r
r
ak
ec
h
,
M
o
r
o
cc
o
E
m
ail: sar
a.
h
b
.
s
ar
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
an
c
e
r
r
e
m
ai
n
s
a
lea
d
i
n
g
g
l
o
b
al
ca
u
s
e
o
f
d
ea
t
h
,
w
it
h
l
u
n
g
c
an
ce
r
b
e
in
g
th
e
m
o
s
t
p
r
e
v
a
le
n
t
a
n
d
f
at
al
s
u
b
ty
p
e.
P
r
o
g
n
o
s
is
is
o
f
t
en
p
o
o
r
d
u
e
t
o
lat
e
d
i
a
g
n
o
s
is
a
n
d
t
u
m
o
r
h
et
er
o
g
e
n
e
it
y
,
u
n
d
er
s
co
r
i
n
g
t
h
e
n
e
e
d
f
o
r
ea
r
l
y
an
d
a
cc
u
r
ate
d
e
te
cti
o
n
.
G
en
e
ex
p
r
ess
i
o
n
p
r
o
f
ili
n
g
is
a
p
o
w
e
r
f
u
l
t
o
o
l
f
o
r
i
d
e
n
ti
f
y
i
n
g
d
i
a
g
n
o
s
ti
c
a
n
d
p
r
o
g
n
o
s
tic
m
a
r
k
e
r
s
,
y
et
i
ts
h
i
g
h
d
i
m
e
n
s
i
o
n
ali
ty
a
n
d
i
n
h
e
r
e
n
t
n
o
is
e
co
m
p
lic
ate
cl
ass
i
f
ic
ati
o
n
tas
k
s
[
1
]
–
[
3
]
.
T
o
m
iti
g
a
te
th
es
e
c
h
al
le
n
g
es
,
f
ea
t
u
r
e
s
el
ec
t
io
n
is
a
c
r
u
ci
al
p
r
ep
r
o
c
ess
i
n
g
s
tep
t
h
at
i
m
p
r
o
v
es
m
o
d
el
i
n
t
e
r
p
r
et
ab
ilit
y
,
r
ed
u
c
es
co
m
p
u
tati
o
n
a
l
c
o
s
t
,
a
n
d
e
n
h
a
n
ce
s
c
lass
i
f
i
ca
t
io
n
ac
c
u
r
a
c
y
.
T
r
ad
i
ti
o
n
al
m
e
th
o
d
s
f
ilt
er
,
w
r
a
p
p
e
r
,
a
n
d
e
m
b
e
d
d
ed
h
a
v
e
s
h
o
w
n
p
o
te
n
t
ial
b
u
t
o
f
ten
s
u
f
f
e
r
f
r
o
m
r
e
d
u
n
d
a
n
c
y
,
o
v
e
r
f
itti
n
g
,
a
n
d
s
c
ala
b
i
lit
y
l
im
it
ati
o
n
s
i
n
h
i
g
h
-
th
r
o
u
g
h
p
u
t
d
at
a
co
n
t
e
x
ts
[
4
]
–
[
6
]
.
R
e
ce
n
t
m
ac
h
i
n
e
le
a
r
n
in
g
ad
v
a
n
ce
m
e
n
ts
h
av
e
l
e
d
t
o
h
y
b
r
id
a
n
d
en
s
em
b
l
e
-
b
as
ed
f
e
at
u
r
e
s
ele
cti
o
n
te
ch
n
i
q
u
es
t
h
at
i
m
p
r
o
v
e
r
o
b
u
s
t
n
ess
a
n
d
ac
c
u
r
ac
y
.
H
o
w
e
v
e
r
,
m
an
y
s
ti
ll
n
eg
le
ct
b
i
o
l
o
g
ic
al
p
at
h
wa
y
r
ele
v
an
ce
a
n
d
g
e
n
e
r
e
g
u
la
to
r
y
in
te
r
a
cti
o
n
s
,
l
im
iti
n
g
t
h
ei
r
cli
n
ic
al
a
p
p
li
ca
b
il
it
y
[
7
]
–
[
1
0
]
.
T
h
is
s
tu
d
y
ad
d
r
ess
es
th
ese
is
s
u
es
b
y
le
v
er
ag
in
g
g
e
n
e
e
x
p
r
es
s
io
n
d
ata
f
r
o
m
th
e
ca
n
c
er
g
en
o
m
e
atla
s
(
T
C
GA)
,
f
o
cu
s
in
g
o
n
th
e
lu
n
g
ad
en
o
ca
r
cin
o
m
a
(
L
UAD)
d
ataset.
T
C
GA
p
r
o
v
id
es
lar
g
e
-
s
ca
le
m
o
lecu
lar
an
d
clin
ical
d
ata,
e
n
ab
lin
g
b
io
lo
g
ically
g
r
o
u
n
d
e
d
a
n
d
s
tatis
tically
r
ig
o
r
o
u
s
b
io
m
ar
k
er
d
is
co
v
er
y
.
Ou
r
p
r
o
p
o
s
ed
m
eth
o
d
c
o
m
b
in
es
a
d
v
an
ce
d
e
n
s
em
b
le
lear
n
in
g
with
f
ea
tu
r
e
en
g
in
ee
r
i
n
g
to
id
en
tif
y
a
c
o
m
p
ac
t,
in
ter
p
r
etab
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
7
0
3
-
4
7
1
0
4704
g
en
e
s
u
b
s
et
r
ele
v
an
t
to
L
UAD
class
if
icatio
n
.
Un
lik
e
tr
ad
it
io
n
al
ap
p
r
o
ac
h
es,
o
u
r
f
r
am
ew
o
r
k
p
r
io
r
itizes
b
o
t
h
p
r
ed
ictiv
e
p
e
r
f
o
r
m
an
ce
an
d
b
i
o
lo
g
ical
in
s
ig
h
t,
s
u
p
p
o
r
tin
g
p
e
r
s
o
n
alize
d
ca
n
ce
r
d
iag
n
o
s
tics
.
T
h
e
r
em
ain
d
er
o
f
th
is
p
ap
er
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws
.
S
ec
t
io
n
2
r
ev
iews
r
elate
d
wo
r
k
.
Sectio
n
3
p
r
esen
ts
o
u
r
m
eth
o
d
o
l
o
g
y
.
Sectio
n
4
d
etails
th
e
ex
p
er
im
en
t
al
s
etu
p
an
d
r
esu
lts
.
Sectio
n
5
co
n
clu
d
es
with
k
e
y
co
n
tr
ib
u
tio
n
s
an
d
f
u
tu
r
e
d
ir
ec
t
io
n
s
.
2.
RE
L
AT
E
D
WO
RK
F
e
a
t
u
r
e
s
e
l
e
c
ti
o
n
i
s
es
s
e
n
ti
al
f
o
r
a
n
a
l
y
z
i
n
g
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
g
e
n
e
e
x
p
r
e
s
s
i
o
n
d
a
t
a
i
n
c
a
n
c
e
r
c
l
a
s
s
i
f
ic
a
t
i
o
n
.
R
e
c
e
n
t
a
d
v
a
n
c
es
,
s
u
c
h
a
s
t
h
e
s
i
g
n
a
l
-
to
-
n
o
is
e
r
a
t
i
o
-
o
p
t
i
m
i
z
e
d
g
e
n
e
s
el
e
c
ti
o
n
a
n
d
c
l
u
s
t
e
r
i
n
g
f
o
r
c
a
n
c
e
r
c
l
as
s
i
f
i
c
at
i
o
n
(
S
NR
-
OG
SC
C
)
m
e
t
h
o
d
in
[
1
1
]
h
a
v
e
i
m
p
r
o
v
e
d
a
c
c
u
r
a
c
y
b
y
c
o
m
b
i
n
i
n
g
o
p
t
i
m
i
z
e
d
g
e
n
e
s
e
l
e
ct
i
o
n
wi
t
h
cl
u
s
t
e
r
i
n
g
,
e
f
f
ec
t
i
v
e
l
y
r
e
d
u
c
i
n
g
r
e
d
u
n
d
a
n
c
y
an
d
e
n
h
a
n
c
i
n
g
c
o
m
p
u
t
a
t
i
o
n
a
l
ef
f
i
c
i
e
n
c
y
.
H
o
we
v
e
r
,
t
r
a
d
i
t
i
o
n
a
l
m
et
h
o
d
s
f
i
lt
e
r
,
w
r
ap
p
e
r
,
e
m
b
e
d
d
e
d
,
a
n
d
h
y
b
r
i
d
s
t
i
l
l
f
a
c
e
is
s
u
e
s
li
k
e
r
e
d
u
n
d
a
n
c
y
,
o
v
e
r
f
i
t
t
i
n
g
,
l
i
m
it
e
d
b
i
o
l
o
g
i
c
a
l
r
e
l
e
v
a
n
ce
,
a
n
d
s
c
al
ab
i
l
i
t
y
,
li
m
i
ti
n
g
t
h
e
i
r
c
li
n
i
c
a
l
u
t
i
li
t
y
[
1
2
]
,
[
1
3
]
.
Fil
te
r
m
et
h
o
d
s
l
ik
e
m
i
n
i
m
u
m
r
ed
u
n
d
a
n
c
y
m
ax
im
u
m
r
e
le
v
a
n
c
e
(
m
R
MR
)
a
r
e
co
m
p
u
tat
io
n
all
y
e
f
f
ici
en
t
b
u
t
o
v
er
l
o
o
k
c
o
m
p
l
ex
f
e
at
u
r
e
i
n
t
er
ac
t
io
n
s
[
1
4
]
–
[
1
6
]
,
w
h
il
e
w
r
a
p
p
e
r
a
p
p
r
o
a
c
h
es
s
u
c
h
as
g
e
n
et
ic
a
lg
o
r
it
h
m
s
o
f
f
er
h
ig
h
a
cc
u
r
ac
y
at
t
h
e
c
o
s
t
o
f
i
n
c
r
e
ase
d
co
m
p
u
ta
ti
o
n
al
d
e
m
a
n
d
s
an
d
r
is
k
o
f
o
v
er
f
it
ti
n
g
[
1
7
]
.
E
m
b
e
d
d
e
d
tec
h
n
i
q
u
es
li
k
e
s
u
p
p
o
r
t
v
e
c
to
r
m
a
ch
in
e
-
r
ec
u
r
s
iv
e
f
ea
t
u
r
e
e
li
m
i
n
at
io
n
(
S
VM
-
R
FE
)
an
d
r
et
r
o
n
li
b
r
a
r
y
r
e
co
m
b
i
n
ee
r
i
n
g
(
R
L
R
)
i
n
te
g
r
a
te
s
e
lec
ti
o
n
i
n
t
o
t
r
ai
n
i
n
g
b
u
t
o
f
te
n
r
e
ly
o
n
li
n
ea
r
ass
u
m
p
ti
o
n
s
[
1
8
]
.
H
y
b
r
i
d
a
n
d
en
s
em
b
l
e
m
et
h
o
d
s
,
s
u
c
h
as
ex
tr
e
m
e
g
r
ad
ie
n
t
b
o
o
s
ti
n
g
(
X
GB
o
o
s
t
)
c
o
m
b
in
e
d
w
it
h
g
e
n
eti
c
a
lg
o
r
it
h
m
s
,
s
tr
ik
e
a
b
al
a
n
ce
b
et
we
en
a
cc
u
r
ac
y
a
n
d
ef
f
ic
ie
n
c
y
b
u
t
f
ac
e
i
n
te
r
p
r
eta
b
i
lit
y
an
d
c
o
m
p
l
e
x
it
y
c
h
al
le
n
g
es
[
1
9
]
.
I
n
l
u
n
g
c
a
n
c
e
r
s
t
u
d
i
e
s
,
e
n
s
e
m
b
l
e
a
n
d
e
m
b
e
d
d
e
d
m
e
t
h
o
d
s
h
a
v
e
a
c
h
i
e
v
e
d
u
p
t
o
9
7
.
9
9
%
a
c
c
u
r
a
c
y
i
n
L
U
A
D
b
i
o
m
a
r
k
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
[
2
0
]
,
y
e
t
m
a
n
y
a
p
p
r
o
a
c
h
e
s
e
m
p
h
a
s
i
z
e
p
r
e
d
i
c
t
i
o
n
o
v
e
r
b
i
o
l
o
g
i
c
a
l
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
.
T
e
c
h
n
i
q
u
e
s
l
i
k
e
S
N
R
-
O
G
S
C
C
a
d
d
r
e
s
s
t
h
i
s
b
y
m
i
n
i
m
i
z
i
n
g
r
e
d
u
n
d
a
n
c
y
a
n
d
s
e
l
e
c
t
i
n
g
m
i
n
i
m
a
l
y
e
t
i
n
f
o
r
m
a
t
i
v
e
g
e
n
e
s
e
t
s
.
O
u
r
p
r
o
p
o
s
e
d
m
u
l
t
i
-
s
t
a
g
e
f
r
a
m
e
w
o
r
k
b
u
i
l
d
s
o
n
t
h
e
s
e
e
f
f
o
r
t
s
b
y
i
n
t
e
g
r
a
t
i
n
g
r
e
d
u
n
d
a
n
c
y
r
e
d
u
c
t
i
o
n
,
p
a
t
h
w
a
y
-
b
a
s
e
d
b
i
o
l
o
g
i
c
a
l
v
a
l
i
d
a
t
i
o
n
,
a
n
d
a
t
t
e
n
t
i
o
n
-
g
u
i
d
e
d
d
e
e
p
l
e
a
r
n
i
n
g
t
o
e
n
h
a
n
c
e
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
.
V
a
l
i
d
a
t
e
d
o
n
i
n
d
e
p
e
n
d
e
n
t
d
a
t
a
s
e
t
s
,
t
h
e
f
r
a
m
e
w
o
r
k
d
e
m
o
n
s
t
r
a
t
e
s
s
t
r
o
n
g
r
o
b
u
s
t
n
e
s
s
a
n
d
s
c
a
l
a
b
i
l
i
t
y
,
o
f
f
e
r
i
n
g
a
m
e
a
n
i
n
g
f
u
l
a
d
v
a
n
c
e
t
o
w
a
r
d
b
i
o
l
o
g
i
c
a
l
l
y
g
r
o
u
n
d
e
d
c
a
n
c
e
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
f
o
r
p
r
e
c
i
s
i
o
n
o
n
c
o
l
o
g
y
.
3.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
m
u
lti
-
s
tag
e
f
ea
tu
r
e
s
elec
tio
n
an
d
c
lass
if
icatio
n
f
r
am
ewo
r
k
f
o
r
lu
n
g
ca
n
ce
r
g
en
e
e
x
p
r
ess
io
n
an
aly
s
is
,
u
ti
lizin
g
th
e
L
UAD
d
ataset
f
r
o
m
T
C
GA.
T
h
e
f
r
am
ew
o
r
k
a
im
s
to
id
e
n
tify
a
co
m
p
ac
t,
b
i
o
lo
g
ically
r
ele
v
an
t
s
u
b
s
et
o
f
g
en
es
u
s
in
g
s
tatis
tical
an
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es.
T
h
is
will
b
e
ex
p
lain
ed
as f
o
llo
ws.
3
.
1
.
Da
t
a
s
et
des
cr
iptio
n
T
h
is
s
tu
d
y
u
s
es
R
NA
s
eq
u
en
cin
g
(
R
NA
-
Seq
)
d
ata
f
r
o
m
th
e
T
C
GA
-
L
UAD
d
ataset,
wh
ich
in
clu
d
es
g
en
e
ex
p
r
ess
io
n
p
r
o
f
iles
f
r
o
m
5
8
5
lu
n
g
ad
en
o
ca
r
cin
o
m
a
an
d
5
9
n
o
r
m
al
lu
n
g
tis
s
u
e
s
am
p
les.
R
NA
-
Seq
p
r
o
v
id
es
h
ig
h
-
r
eso
lu
tio
n
,
g
en
o
m
e
-
wid
e
in
s
ig
h
ts
in
to
g
en
e
r
eg
u
latio
n
a
n
d
ce
llu
lar
f
u
n
ctio
n
,
with
th
e
d
ataset
co
v
er
in
g
ar
o
u
n
d
2
0
,
5
0
0
g
en
e
s
an
d
ac
c
o
m
p
an
ie
d
b
y
r
ic
h
cl
in
ical
an
n
o
tatio
n
s
.
L
ev
er
a
g
in
g
th
is
r
eso
u
r
ce
,
we
ap
p
ly
a
m
u
lti
-
s
tag
e
f
ea
tu
r
e
s
elec
tio
n
an
d
class
if
icatio
n
f
r
am
ewo
r
k
t
o
id
en
tif
y
a
co
m
p
ac
t,
b
io
lo
g
ically
m
ea
n
in
g
f
u
l
g
en
e
s
u
b
s
et
p
r
e
d
ictiv
e
o
f
L
UAD.
T
h
is
ap
p
r
o
ac
h
s
u
p
p
o
r
ts
b
io
m
a
r
k
er
d
is
co
v
er
y
a
n
d
o
f
f
er
s
a
r
o
b
u
s
t,
g
e
n
er
aliza
b
le
m
eth
o
d
f
o
r
im
p
r
o
v
in
g
lu
n
g
ca
n
ce
r
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t.
3
.
2
.
Da
t
a
p
re
pro
ce
s
s
ing
T
o
en
s
u
r
e
d
ata
q
u
ality
an
d
co
n
s
is
ten
cy
,
s
ev
er
al
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
wer
e
ap
p
lied
.
Gen
e
ex
p
r
ess
io
n
v
alu
es
wer
e
lo
g
2
-
tr
an
s
f
o
r
m
e
d
u
s
in
g
f
r
ag
m
en
ts
p
e
r
k
ilo
b
a
s
e
p
er
m
illi
o
n
m
ap
p
ed
f
r
ag
m
en
ts
(
FP
KM
+1
)
to
s
tab
ilize
v
ar
ian
ce
an
d
r
e
d
u
ce
h
eter
o
s
ce
d
asti
city
ac
r
o
s
s
s
am
p
les
[
2
1
]
.
B
atch
ef
f
ec
ts
f
r
o
m
tech
n
ical
v
ar
iatio
n
s
wer
e
co
r
r
ec
ted
u
s
in
g
th
e
co
m
b
attin
g
b
atch
e
f
f
ec
ts
(
C
o
m
B
at
)
alg
o
r
ith
m
,
wh
ich
ap
p
lie
s
an
em
p
ir
ical
B
ay
es
ap
p
r
o
ac
h
to
p
r
eser
v
e
b
io
l
o
g
ic
al
s
ig
n
als
wh
ile
m
in
im
izin
g
tech
n
ical
n
o
is
e
[
2
2
]
.
Gen
es
w
ith
lo
w
ex
p
r
ess
io
n
(
u
n
d
er
th
e
1
0
th
p
er
ce
n
tile)
we
r
e
r
em
o
v
ed
,
a
n
d
o
u
tlier
s
id
en
t
if
ied
v
ia
Ma
h
ala
n
o
b
is
d
is
tan
ce
ex
ce
ed
in
g
th
e
9
5
th
p
er
ce
n
tile
wer
e
ex
clu
d
e
d
to
r
ed
u
ce
n
o
is
e
an
d
im
p
r
o
v
e
r
o
b
u
s
tn
ess
[
2
3
]
.
T
h
ese
s
tep
s
p
r
o
d
u
ce
d
a
h
i
g
h
-
q
u
ality
d
ataset
s
u
itab
le
f
o
r
r
eliab
le
d
o
wn
s
tr
ea
m
an
aly
s
is
.
3
.
3
.
M
ulti
-
s
t
a
g
e
f
e
a
t
ure
s
elec
t
io
n f
ra
m
ew
o
rk
T
o
o
v
er
co
m
e
th
e
c
h
allen
g
es
o
f
h
i
g
h
d
im
en
s
io
n
ality
,
n
o
is
e,
an
d
r
ed
u
n
d
an
c
y
in
R
NA
-
Seq
d
ata,
we
d
esig
n
ed
a
m
u
lti
-
s
tag
e
f
ea
tu
r
e
s
elec
tio
n
f
r
am
ewo
r
k
th
at
co
m
b
in
es
s
tatis
tica
l
an
aly
s
is
,
en
t
r
o
p
y
-
b
ased
r
an
k
in
g
,
an
d
d
ee
p
lear
n
in
g
r
e
f
in
em
en
t.
T
h
is
ap
p
r
o
ac
h
e
n
s
u
r
es
a
r
o
b
u
s
t,
in
ter
p
r
etab
le,
a
n
d
b
io
lo
g
i
ca
lly
r
elev
an
t
g
en
e
s
u
b
s
et.
T
h
is
will b
e
ex
p
lain
ed
as f
o
llo
ws.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Dee
p
lea
r
n
in
g
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
fo
r
lu
n
g
a
d
en
o
ca
r
cin
o
ma
cla
s
s
ifica
tio
n
…
(
S
a
r
a
H
a
d
d
o
u
B
o
u
a
z
z
a
)
4705
3
.
3
.
1
.
Sta
g
e
1
:
s
t
a
t
is
t
ica
l r
elev
a
nce
a
nd
s
t
a
bil
it
y
a
na
ly
s
is
I
n
th
e
f
ir
s
t
s
tag
e,
d
if
f
er
en
tially
ex
p
r
ess
ed
g
en
es
b
etwe
en
tu
m
o
r
an
d
n
o
r
m
al
s
am
p
les
wer
e
id
en
tifie
d
u
s
in
g
th
e
W
ilco
x
o
n
r
an
k
-
s
u
m
test
,
a
n
o
n
-
p
ar
am
etr
ic
m
eth
o
d
s
u
itab
le
f
o
r
R
NA
-
Seq
d
ata
[
2
4
]
.
T
o
co
n
tr
o
l
f
alse
p
o
s
itiv
es,
th
e
B
en
jam
in
i
-
Ho
ch
b
er
g
p
r
o
ce
d
u
r
e
was
ap
p
lied
,
r
etain
in
g
g
en
es
with
a
f
alse
d
is
co
v
er
y
r
ate
(
FDR
)
u
n
d
er
0
.
0
5
[
2
5
]
.
T
o
f
u
r
t
h
er
i
m
p
r
o
v
e
r
o
b
u
s
tn
ess
an
d
r
e
d
u
c
e
n
o
is
e
s
en
s
itiv
ity
,
s
tab
ilit
y
s
elec
tio
n
v
ia
b
o
o
ts
tr
ap
r
esam
p
lin
g
was
p
er
f
o
r
m
ed
.
G
en
es
co
n
s
is
ten
tly
id
en
tifie
d
as si
g
n
if
ican
t
in
at
least
9
5
%
o
f
1
0
0
r
a
n
d
o
m
s
u
b
s
ets
wer
e
r
etain
ed
,
e
n
s
u
r
in
g
s
tab
ili
ty
ac
r
o
s
s
s
am
p
lin
g
v
ar
iatio
n
s
[
2
6
]
.
3
.
3
.
2
.
Sta
g
e
2
:
ent
ro
py
-
driv
en
f
ea
t
ure
ra
nk
ing
I
n
t
h
e
s
e
c
o
n
d
s
t
a
g
e
,
g
e
n
es
f
r
o
m
s
t
a
g
e
1
w
e
r
e
r
a
n
k
e
d
u
s
i
n
g
j
o
i
n
t
m
u
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
m
a
x
i
m
i
z
a
ti
o
n
(
J
M
I
M
)
[
2
7
]
,
w
h
i
c
h
e
v
a
l
u
a
t
es
e
a
c
h
g
e
n
e
’
s
a
b
i
l
it
y
t
o
r
e
d
u
c
e
u
n
c
e
r
t
a
i
n
t
y
a
b
o
u
t
c
l
a
s
s
l
a
b
el
s
w
h
i
l
e
m
i
n
i
m
iz
i
n
g
r
e
d
u
n
d
a
n
c
y
w
i
t
h
p
r
e
v
i
o
u
s
l
y
s
el
e
c
t
e
d
f
e
a
t
u
r
es
[
2
8
]
.
T
h
i
s
e
n
s
u
r
e
s
s
el
e
c
t
i
o
n
o
f
f
e
a
t
u
r
e
s
t
h
a
t
a
r
e
b
o
t
h
r
e
l
e
v
a
n
t
a
n
d
c
o
m
p
l
e
m
e
n
t
a
r
y
.
T
h
e
t
o
p
2
0
0
g
e
n
e
s
w
i
t
h
t
h
e
h
i
g
h
e
s
t
m
u
t
u
a
l
in
f
o
r
m
a
t
i
o
n
(
MI
)
s
c
o
r
e
s
w
e
r
e
r
e
t
a
i
n
e
d
f
o
r
t
h
e
n
e
x
t
s
t
a
g
e
,
a
t
h
r
e
s
h
o
l
d
c
h
o
s
e
n
t
o
b
a
la
n
c
e
d
i
m
e
n
s
i
o
n
al
i
t
y
r
e
d
u
c
ti
o
n
w
i
t
h
b
i
o
l
o
g
i
c
al
d
i
v
e
r
s
i
t
y
a
n
d
i
n
t
e
r
p
r
e
t
a
b
i
li
t
y
.
3
.
3
.
3
.
Sta
g
e
3
:
s
pa
rse
a
uto
en
co
der
f
o
r
f
e
a
t
ure
re
f
inem
ent
T
h
e
f
in
al
s
tag
e
em
p
lo
y
ed
a
s
p
ar
s
e
au
to
en
co
d
e
r
to
r
ef
i
n
e
th
e
s
elec
ted
f
ea
tu
r
es
f
u
r
th
er
.
As
an
u
n
s
u
p
er
v
is
ed
d
ee
p
lear
n
i
n
g
m
o
d
el,
th
e
au
t
o
en
co
d
er
lear
n
s
co
m
p
r
ess
ed
r
ep
r
esen
tatio
n
s
b
y
ac
tiv
atin
g
o
n
ly
a
s
u
b
s
et
o
f
n
eu
r
o
n
s
,
th
u
s
f
o
c
u
s
in
g
o
n
th
e
m
o
s
t
in
f
o
r
m
ativ
e
f
ea
tu
r
es
[
2
9
]
,
[
3
0
]
.
T
h
e
m
o
d
el
in
clu
d
ed
an
i
n
p
u
t
lay
er
f
o
r
th
e
2
0
0
g
en
es,
two
h
id
d
en
lay
er
s
with
1
2
8
an
d
6
4
n
eu
r
o
n
s
,
an
d
an
o
u
tp
u
t
lay
e
r
m
ir
r
o
r
in
g
th
e
in
p
u
t.
R
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
was
u
s
ed
,
with
a
s
p
ar
s
ity
co
n
s
tr
ain
t
(
β=0
.
0
5
)
to
s
u
p
p
r
ess
n
o
is
e.
T
r
ain
in
g
was
p
er
f
o
r
m
ed
u
s
in
g
th
e
Ad
am
o
p
tim
izer
(
lear
n
in
g
r
ate=
0
.
0
0
1
)
f
o
r
1
0
0
ep
o
c
h
s
.
Af
ter
tr
ain
i
n
g
,
en
co
d
er
weig
h
ts
wer
e
an
aly
z
ed
,
an
d
th
e
to
p
1
0
g
en
es
with
th
e
h
ig
h
est
co
n
tr
ib
u
tio
n
s
to
laten
t
f
ea
tu
r
es
wer
e
s
elec
ted
,
y
ield
in
g
a
c
o
m
p
ac
t a
n
d
in
ter
p
r
etab
le
s
et
f
o
r
class
if
icatio
n
.
3
.
4
.
F
r
a
m
ewo
r
k
inte
g
r
a
t
io
n
a
nd
bio
lo
g
ica
l r
elev
a
nce
T
h
e
th
r
ee
-
s
tag
e
f
r
a
m
ewo
r
k
wa
s
d
esig
n
ed
to
p
r
o
g
r
ess
iv
ely
r
ef
in
e
th
e
f
ea
tu
r
e
s
et
wh
ile
ad
d
r
e
s
s
in
g
k
ey
ch
allen
g
es
in
R
NA
-
Seq
d
ata
an
aly
s
is
.
Stag
e
1
f
o
cu
s
es
o
n
s
ta
tis
tical
s
ig
n
if
ican
ce
an
d
r
o
b
u
s
tn
ess
,
en
s
u
r
in
g
th
at
th
e
s
elec
ted
f
ea
tu
r
es
a
r
e
r
ep
r
o
d
u
cib
le
an
d
b
i
o
lo
g
icall
y
r
elev
a
n
t.
Stag
e
2
p
r
i
o
r
itizes
p
r
ed
ictiv
e
a
n
d
co
m
p
lem
en
tar
y
g
en
es,
r
ed
u
ci
n
g
r
ed
u
n
d
a
n
cy
a
n
d
f
o
cu
s
in
g
o
n
th
o
s
e
f
ea
tu
r
es
th
at
co
n
tr
ib
u
te
th
e
m
o
s
t
to
class
if
icatio
n
.
Fin
ally
,
s
tag
e
3
lev
er
ag
es
d
ee
p
lear
n
i
n
g
to
r
e
f
in
e
th
e
f
ea
tu
r
e
s
et
f
u
r
th
e
r
,
ca
p
tu
r
in
g
n
o
n
-
lin
ea
r
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
am
o
n
g
g
en
es.
T
o
g
eth
er
,
th
ese
s
tag
es
p
r
o
d
u
ce
a
co
m
p
ac
t,
b
io
l
o
g
ically
m
ea
n
i
n
g
f
u
l
f
ea
tu
r
e
s
et
o
p
tim
ized
f
o
r
ca
n
c
er
class
if
icatio
n
.
3
.
5
.
Cla
s
s
if
ica
t
io
n f
r
a
m
ewo
r
k
T
h
e
s
elec
ted
f
ea
tu
r
es
wer
e
u
s
ed
to
tr
ain
a
h
y
b
r
id
d
ee
p
lear
n
in
g
class
if
ier
,
co
m
b
in
in
g
a
d
en
s
e
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
with
an
atten
tio
n
m
ec
h
an
is
m
.
A
d
e
n
s
e
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
is
a
ty
p
e
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
wh
e
r
e
d
ata
f
lo
ws
s
eq
u
en
tially
th
r
o
u
g
h
lay
er
s
,
m
ak
in
g
it
well
-
s
u
i
ted
f
o
r
s
u
p
er
v
is
ed
lear
n
in
g
task
s
[
3
1
]
.
T
h
e
a
r
c
h
itectu
r
e
co
n
s
is
ted
o
f
th
r
ee
h
id
d
en
lay
er
s
with
1
2
8
,
6
4
,
an
d
3
2
n
e
u
r
o
n
s
,
r
esp
ec
tiv
ely
,
ea
ch
em
p
lo
y
in
g
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
s
to
in
tr
o
d
u
ce
n
o
n
-
lin
ea
r
tr
an
s
f
o
r
m
atio
n
s
,
en
ab
lin
g
th
e
m
o
d
el
to
ca
p
tu
r
e
c
o
m
p
lex
p
att
er
n
s
in
th
e
d
ata
[
3
2
]
.
Dr
o
p
o
u
t la
y
er
s
with
a
r
ate
o
f
0
.
5
wer
e
i
n
clu
d
ed
a
f
ter
ea
ch
h
id
d
en
la
y
er
to
r
ed
u
ce
o
v
er
f
itti
n
g
b
y
r
an
d
o
m
ly
d
ea
ctiv
atin
g
a
f
r
ac
tio
n
o
f
n
e
u
r
o
n
s
d
u
r
in
g
tr
ain
in
g
.
T
o
en
h
a
n
ce
th
e
m
o
d
el’
s
in
ter
p
r
etab
ilit
y
an
d
f
o
cu
s
o
n
th
e
m
o
s
t
cr
itical
f
ea
tu
r
es,
atten
tio
n
m
ec
h
an
is
m
was
in
co
r
p
o
r
ate
d
.
T
h
e
atten
t
io
n
m
ec
h
a
n
is
m
ass
ig
n
s
weig
h
ts
to
f
ea
tu
r
es
(
g
en
es),
allo
win
g
th
e
m
o
d
el
to
p
r
io
r
itize
th
o
s
e
m
o
s
t
i
n
f
lu
en
t
ial
f
o
r
class
if
icatio
n
.
T
h
ese
weig
h
ts
also
p
r
o
v
id
e
in
s
ig
h
ts
in
to
th
e
b
io
lo
g
ica
l
im
p
o
r
tan
ce
o
f
in
d
iv
id
u
al
g
en
e
s
,
lin
k
in
g
co
m
p
u
tatio
n
al
p
r
ed
i
ctio
n
s
to
p
o
ten
tial b
io
l
o
g
ical
r
elev
an
ce
[
3
3
]
.
T
h
e
m
o
d
el
was
tr
ai
n
ed
u
s
in
g
th
e
Ad
a
m
o
p
tim
izer
[
3
4
]
,
a
g
r
ad
ie
n
t
-
b
ased
o
p
tim
izatio
n
alg
o
r
ith
m
k
n
o
wn
f
o
r
its
ad
ap
tiv
e
lear
n
in
g
r
ate,
with
a
lear
n
in
g
r
ate
o
f
0
.
0
0
0
5
an
d
a
b
atch
s
ize
o
f
3
2
.
T
h
e
lo
s
s
f
u
n
ctio
n
u
s
ed
was
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
,
a
s
tan
d
a
r
d
m
et
r
ic
f
o
r
m
u
lti
-
class
class
if
icat
io
n
task
s
,
wh
ich
m
in
im
izes
th
e
d
if
f
er
en
ce
b
etwe
en
p
r
e
d
icted
an
d
ac
tu
al
class
p
r
o
b
ab
ilit
ies.
E
ar
ly
s
to
p
p
in
g
,
b
ased
o
n
v
alid
atio
n
lo
s
s
,
was
em
p
lo
y
ed
t
o
p
r
e
v
en
t
o
v
e
r
f
it
tin
g
b
y
h
altin
g
tr
ain
in
g
o
n
ce
p
er
f
o
r
m
an
ce
im
p
r
o
v
e
m
en
ts
p
latea
u
ed
.
T
h
is
f
r
am
ewo
r
k
was
ev
alu
ated
u
s
i
n
g
5
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
,
e
n
s
u
r
in
g
r
o
b
u
s
t
esti
m
ates
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
b
y
iter
ativ
ely
tr
ain
in
g
a
n
d
test
in
g
th
e
class
if
ier
o
n
d
if
f
er
e
n
t su
b
s
ets o
f
th
e
d
ata.
3
.
6
.
P
a
t
hwa
y
-
enriched
bio
lo
g
ica
l v
a
lid
a
t
io
n
T
o
v
al
id
at
e
th
e
b
io
lo
g
i
ca
l
r
ele
v
a
n
c
e
o
f
t
h
e
s
e
le
cte
d
g
e
n
es
,
p
at
h
wa
y
e
n
r
ic
h
m
e
n
t
a
n
aly
s
is
was
p
e
r
f
o
r
m
e
d
u
s
i
n
g
t
h
e
K
y
o
t
o
en
cy
cl
o
p
e
d
ia
o
f
g
e
n
es
an
d
g
e
n
o
m
es
(
KE
G
G
)
a
n
d
g
e
n
e
o
n
to
lo
g
y
(
GO
)
d
at
ab
ases
.
KE
GG
p
r
o
v
i
d
es
c
u
r
ate
d
i
n
f
o
r
m
at
io
n
o
n
m
o
le
c
u
la
r
p
at
h
w
ay
s
,
wh
ile
GO
a
n
n
o
tat
es
g
e
n
es
a
c
r
o
s
s
th
r
e
e
d
o
m
a
in
s
:
b
i
o
l
o
g
ic
al
p
r
o
ce
s
s
es,
c
ell
u
l
ar
c
o
m
p
o
n
e
n
ts
,
a
n
d
m
o
le
c
u
la
r
f
u
n
cti
o
n
s
.
T
h
es
e
t
o
o
ls
o
f
f
e
r
c
o
m
p
lem
en
ta
r
y
i
n
s
i
g
h
ts
in
t
o
t
h
e
r
o
l
es
o
f
g
e
n
es w
it
h
i
n
t
h
e
b
r
o
a
d
er
b
i
o
l
o
g
ica
l
co
n
t
e
x
t
o
f
l
u
n
g
ca
n
c
er
[
3
5
]
,
[
3
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
7
0
3
-
4
7
1
0
4706
T
h
e
an
aly
s
is
was
co
n
d
u
cted
u
s
in
g
d
atab
ase
f
o
r
a
n
n
o
tatio
n
,
v
is
u
aliza
tio
n
,
an
d
in
teg
r
ated
d
is
co
v
er
y
(
DAVI
D
)
an
d
E
n
r
ich
r
,
two
wid
ely
u
s
ed
to
o
ls
f
o
r
f
u
n
ctio
n
al
an
n
o
tatio
n
a
n
d
e
n
r
ich
m
en
t
an
aly
s
is
.
T
h
ese
to
o
ls
co
m
p
ar
e
th
e
s
elec
ted
g
en
e
s
et
ag
ain
s
t
r
ef
er
en
ce
g
en
e
s
ets
t
o
id
en
tify
s
tatis
tically
o
v
er
r
ep
r
esen
ted
p
ath
way
s
.
T
h
e
en
r
ich
m
en
t
an
aly
s
is
f
o
cu
s
ed
o
n
p
ath
wa
y
s
k
n
o
wn
to
b
e
in
v
o
l
v
ed
in
l
u
n
g
ca
n
ce
r
p
r
o
g
r
ess
io
n
,
s
u
ch
as
th
e
ep
id
er
m
al
g
r
o
wth
f
ac
t
o
r
r
ec
e
p
to
r
(
E
GFR
)
s
ig
n
alin
g
p
ath
way
,
ce
ll
cy
cle
r
eg
u
latio
n
,
an
d
im
m
u
n
e
r
esp
o
n
s
e.
T
h
ese
p
ath
way
s
p
lay
cr
itical
r
o
les in
tu
m
o
r
p
r
o
life
r
atio
n
,
th
e
r
ap
y
r
esis
tan
ce
,
an
d
th
e
tu
m
o
r
m
icr
o
en
v
ir
o
n
m
en
t
[
3
7
]
,
[
3
8
]
.
T
h
is
s
tep
en
s
u
r
es
th
at
th
e
s
elec
ted
f
ea
tu
r
es
ar
e
n
o
t
o
n
ly
p
r
e
d
ictiv
e
b
u
t
also
b
io
lo
g
ically
m
ea
n
in
g
f
u
l,
b
r
i
d
g
in
g
th
e
g
a
p
b
etwe
en
co
m
p
u
tatio
n
al
r
esu
lts
an
d
r
ea
l
-
w
o
r
ld
b
i
o
lo
g
ical
im
p
licatio
n
s
.
3
.
7
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n a
nd
cr
o
s
s
-
da
t
a
s
et
v
a
lid
a
t
io
n
T
h
e
class
if
ier
’
s
p
er
f
o
r
m
an
ce
was
ev
alu
ated
u
s
in
g
k
ey
m
etr
ics:
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
ar
ea
u
n
d
er
th
e
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
te
r
is
tic
cu
r
v
e
(
AUC
-
R
O
C
)
.
Acc
u
r
ac
y
r
ef
lects
o
v
er
all
p
r
ed
ictio
n
co
r
r
ec
tn
ess
;
p
r
ec
is
io
n
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
tio
n
o
f
tr
u
e
p
o
s
itiv
es
am
o
n
g
p
r
e
d
icted
p
o
s
itiv
es;
r
ec
all
(
s
en
s
itiv
ity
)
ass
es
s
es
th
e
ab
ilit
y
to
d
etec
t
t
r
u
e
p
o
s
itiv
es;
an
d
th
e
F1
-
s
co
r
e
b
alan
ce
s
p
r
ec
is
io
n
an
d
r
ec
all.
T
h
e
AUC
-
R
OC
ca
p
tu
r
es
th
e
tr
ad
e
-
o
f
f
b
etwe
en
s
en
s
itiv
ity
an
d
s
p
ec
if
icit
y
ac
r
o
s
s
th
r
esh
o
ld
s
,
o
f
f
er
i
n
g
a
c
o
m
p
r
eh
en
s
iv
e
m
ea
s
u
r
e
o
f
m
o
d
el
p
e
r
f
o
r
m
an
c
e
[
3
9
]
.
A
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
s
tr
ateg
y
was
ap
p
lied
to
en
s
u
r
e
r
eliab
le
an
d
u
n
b
iased
ev
alu
atio
n
.
T
h
e
d
ataset
was
s
p
lit
in
to
f
iv
e
p
ar
t
s
,
with
ea
ch
s
u
b
s
et
u
s
ed
o
n
ce
as
th
e
test
s
et
wh
ile
th
e
o
t
h
er
s
s
er
v
ed
f
o
r
tr
ain
i
n
g
,
an
d
r
esu
lts
wer
e
a
v
er
ag
e
d
to
r
ed
u
ce
s
am
p
lin
g
b
ias.
T
o
ass
ess
g
en
er
aliza
b
ilit
y
,
cr
o
s
s
-
d
at
aset
v
alid
atio
n
was
co
n
d
u
cte
d
u
s
in
g
t
h
e
GSE1
9
1
8
8
d
ataset
f
r
o
m
th
e
g
en
e
e
x
p
r
e
s
s
io
n
o
m
n
ib
u
s
(
GE
O
)
r
ep
o
s
ito
r
y
,
w
h
ich
in
clu
d
es
m
icr
o
ar
r
ay
-
b
ased
e
x
p
r
ess
io
n
p
r
o
f
iles
o
f
lu
n
g
ad
en
o
ca
r
cin
o
m
a
an
d
n
o
r
m
al
s
am
p
les.
Pre
p
r
o
ce
s
s
in
g
s
tep
s
s
u
ch
as
n
o
r
m
aliza
tio
n
,
lo
g
tr
an
s
f
o
r
m
atio
n
,
an
d
alig
n
m
en
t
to
T
C
GA
p
r
o
to
co
ls
en
s
u
r
ed
co
m
p
atib
ilit
y
.
T
h
is
v
alid
atio
n
co
n
f
ir
m
ed
th
e
f
r
a
m
ewo
r
k
’
s
r
o
b
u
s
tn
ess
ac
r
o
s
s
d
if
f
er
en
t d
ata
p
latf
o
r
m
s
an
d
ex
p
er
im
en
tal
co
n
d
itio
n
s
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
f
in
d
in
g
s
o
f
th
e
m
u
lti
-
s
tag
e
f
ea
tu
r
e
s
elec
tio
n
an
d
class
if
icatio
n
f
r
am
ewo
r
k
ap
p
lied
to
th
e
T
C
GA
-
L
UA
D
d
ataset
an
d
v
alid
ated
o
n
th
e
in
d
ep
en
d
e
n
t
GSE1
9
1
8
8
d
ataset.
T
h
e
r
esu
lts
h
ig
h
lig
h
t
th
e
f
r
a
m
ewo
r
k
’
s
ab
ilit
y
to
s
elec
t
b
io
lo
g
ically
m
ea
n
in
g
f
u
l
f
ea
t
u
r
es
an
d
ac
h
iev
e
r
o
b
u
s
t
class
if
icatio
n
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
iv
er
s
e
d
a
tasets
.
T
h
is
will b
e
ex
p
lain
ed
as f
o
llo
ws.
4
.
1
.
Da
t
a
s
et
prepro
ce
s
s
ing
T
h
e
T
C
GA
-
L
UAD
d
ataset,
co
m
p
r
is
in
g
R
NA
-
Seq
p
r
o
f
iles
f
r
o
m
5
8
5
tu
m
o
r
an
d
5
9
n
o
r
m
al
l
u
n
g
tis
s
u
e
s
am
p
les,
u
n
d
er
we
n
t
r
ig
o
r
o
u
s
p
r
ep
r
o
ce
s
s
in
g
.
Gen
e
ex
p
r
ess
io
n
v
alu
es
we
r
e
lo
g
2
(
FP
KM
+1
)
tr
an
s
f
o
r
m
ed
to
s
tab
ilize
v
ar
ian
ce
,
an
d
b
atch
ef
f
ec
ts
wer
e
co
r
r
ec
ted
u
s
in
g
th
e
C
o
m
B
at
alg
o
r
ith
m
to
p
r
eser
v
e
b
io
lo
g
ical
s
ig
n
als.
Gen
es
with
lo
w
ex
p
r
ess
io
n
(
u
n
d
e
r
th
e
1
0
th
p
er
ce
n
tile)
wer
e
r
em
o
v
ed
,
r
esu
ltin
g
in
a
r
ef
in
e
d
s
et
o
f
1
4
,
0
0
0
g
en
es.
Ou
tlier
s
,
id
e
n
t
if
ied
v
ia
Ma
h
alan
o
b
is
d
is
tan
ce
,
wer
e
e
x
clu
d
ed
,
y
ield
i
n
g
a
f
in
al
d
ataset
o
f
5
7
0
tu
m
o
r
a
n
d
5
9
n
o
r
m
al
s
am
p
les
en
s
u
r
in
g
d
ata
q
u
ality
f
o
r
s
u
b
s
eq
u
en
t f
ea
tu
r
e
s
elec
tio
n
a
n
d
class
if
icatio
n
.
4
.
2
.
M
ulti
-
s
t
a
g
e
f
e
a
t
ure
s
elec
t
io
n r
esu
lt
s
4
.
2
.
1
.
Sta
g
e
1
:
s
t
a
t
is
t
ica
l r
elev
a
nce
a
nd
s
t
a
bil
it
y
a
na
ly
s
is
Dif
f
er
en
tial
ex
p
r
ess
io
n
an
al
y
s
is
u
s
in
g
th
e
W
i
lco
x
o
n
r
a
n
k
-
s
u
m
test
id
en
tifie
d
4
,
2
0
0
g
en
es
as
s
ig
n
if
ican
tly
d
if
f
e
r
en
tially
ex
p
r
ess
ed
(
FDR
<0
.
0
5
)
.
T
o
en
h
an
ce
r
o
b
u
s
tn
ess
,
s
tab
ilit
y
s
elec
ti
o
n
u
s
in
g
b
o
o
ts
tr
ap
r
esam
p
lin
g
was
p
e
r
f
o
r
m
ed
,
r
e
tain
in
g
3
,
8
0
0
g
e
n
es
co
n
s
is
ten
tly
id
en
tifie
d
as
s
ig
n
if
ican
t
ac
r
o
s
s
1
0
0
iter
atio
n
s
.
Var
ian
ce
f
ilter
in
g
f
u
r
th
er
r
ed
u
ce
d
th
e
f
ea
tu
r
e
s
et
to
3
,
0
0
0
g
e
n
es,
f
o
cu
s
in
g
o
n
th
o
s
e
with
th
e
h
ig
h
est v
ar
iab
ilit
y
an
d
b
io
l
o
g
ical
r
elev
a
n
ce
.
4
.
2
.
2
.
Sta
g
e
2
:
ent
ro
py
-
driv
en
f
ea
t
ure
ra
nk
ing
T
h
e
3
,
0
0
0
g
en
es
wer
e
r
an
k
ed
u
s
in
g
J
MI
M,
wh
ich
ev
alu
ates
th
e
r
elatio
n
s
h
ip
b
etwe
en
ea
ch
g
en
e
an
d
class
lab
el
s
wh
ile
m
in
im
izin
g
r
ed
u
n
d
a
n
cy
am
o
n
g
f
ea
tu
r
es.
T
h
e
to
p
2
0
0
g
en
es
with
th
e
h
ig
h
est
MI
s
co
r
es
wer
e
s
elec
ted
f
o
r
f
u
r
th
e
r
r
ef
in
em
en
t.
T
h
is
th
r
esh
o
ld
was
ch
o
s
en
to
b
alan
ce
d
im
e
n
s
io
n
ality
r
e
d
u
ctio
n
with
th
e
r
eten
tio
n
o
f
s
u
f
f
icien
t b
i
o
lo
g
ic
al
d
iv
er
s
ity
,
en
s
u
r
in
g
r
o
b
u
s
t d
o
wn
s
tr
ea
m
class
if
icatio
n
.
4
.
2
.
3
.
Sta
g
e
3
:
s
pa
rse
a
uto
en
co
der
f
o
r
f
e
a
t
ure
re
f
inem
ent
A
s
p
ar
s
e
au
to
en
co
d
er
r
ef
i
n
ed
th
e
f
ea
tu
r
e
s
et
b
y
a
n
aly
zin
g
g
e
n
e
co
n
tr
ib
u
tio
n
s
to
laten
t
r
ep
r
esen
tatio
n
s
.
T
h
e
a
u
to
en
c
o
d
er
,
co
m
p
r
is
in
g
two
h
id
d
en
lay
er
s
(
1
2
8
an
d
6
4
n
eu
r
o
n
s
)
,
was
tr
ain
ed
f
o
r
1
0
0
ep
o
ch
s
u
s
in
g
t
h
e
Ad
am
o
p
tim
izer
(
lear
n
in
g
r
ate=
0
.
0
0
1
)
with
a
s
p
ar
s
ity
co
n
s
tr
ain
t
(
β=0
.
0
5
)
.
T
h
e
e
n
co
d
e
r
weig
h
ts
wer
e
an
aly
ze
d
,
a
n
d
th
e
1
0
g
en
es
with
th
e
h
ig
h
est
c
o
n
tr
ib
u
tio
n
s
wer
e
r
etain
e
d
as
th
e
f
in
al
f
ea
tu
r
e
s
et.
T
h
is
co
m
p
ac
t
f
ea
tu
r
e
s
et
e
n
s
u
r
es
in
ter
p
r
etab
ilit
y
an
d
b
io
lo
g
ical
r
elev
an
ce
wh
ile
m
ain
tain
in
g
s
tr
o
n
g
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Dee
p
lea
r
n
in
g
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
fo
r
lu
n
g
a
d
en
o
ca
r
cin
o
ma
cla
s
s
ifica
tio
n
…
(
S
a
r
a
H
a
d
d
o
u
B
o
u
a
z
z
a
)
4707
4
.
3
.
Cla
s
s
if
ica
t
io
n per
f
o
r
m
a
nce
T
h
e
f
in
al
1
0
s
elec
ted
g
en
es
wer
e
u
s
ed
to
tr
ain
a
h
y
b
r
id
d
ee
p
lear
n
in
g
class
if
ier
co
m
b
in
in
g
a
d
en
s
e
f
ee
d
f
o
r
war
d
n
e
u
r
al
n
etwo
r
k
with
an
atten
tio
n
m
ec
h
a
n
is
m
.
E
v
alu
ated
u
s
in
g
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
o
n
th
e
T
C
GA
-
L
UAD
d
ataset,
th
e
m
o
d
el
ac
h
iev
e
d
ex
ce
llen
t
p
er
f
o
r
m
a
n
ce
:
9
9
.
3
%
ac
cu
r
ac
y
,
9
9
.
0
%
p
r
ec
is
io
n
,
9
9
.
5
%
r
ec
all,
9
9
.
2
%
F1
-
s
co
r
e
,
an
d
an
AUC
-
R
OC
o
f
0
.
9
9
8
,
d
em
o
n
s
tr
atin
g
its
ab
ilit
y
to
d
is
tin
g
u
is
h
b
etwe
en
tu
m
o
r
an
d
n
o
r
m
al
s
am
p
les
with
m
in
im
al
m
is
class
if
icatio
n
.
T
o
ev
alu
ate
g
en
er
aliza
b
ilit
y
,
th
e
m
o
d
el
was
test
ed
o
n
th
e
in
d
ep
e
n
d
en
t
GSE1
9
1
8
8
d
ataset
co
n
tain
i
n
g
m
icr
o
ar
r
ay
p
r
o
f
iles
o
f
4
5
L
UAD
a
n
d
6
5
n
o
r
m
al
s
am
p
les
.
Desp
ite
p
latf
o
r
m
d
if
f
er
en
ce
s
,
th
e
class
if
ier
r
etain
ed
h
ig
h
p
er
f
o
r
m
an
ce
with
9
8
.
7
%
ac
cu
r
ac
y
,
9
8
.
3
%
p
r
ec
is
io
n
,
9
9
.
0
% r
ec
all,
9
8
.
6
% F1
-
s
co
r
e
,
an
d
an
AUC
-
R
O
C
o
f
0
.
9
9
5
.
4
.
4
.
Dis
cus
s
io
n o
f
re
s
ults
T
h
is
s
tu
d
y
in
tr
o
d
u
ce
s
a
n
o
v
el
m
u
lti
-
s
tag
e
f
ea
tu
r
e
s
elec
tio
n
f
r
am
ewo
r
k
co
m
b
i
n
ed
with
a
h
y
b
r
id
d
ee
p
lear
n
in
g
class
if
ier
f
o
r
L
UA
D
class
if
icatio
n
u
s
in
g
R
NA
-
Seq
d
ata.
B
y
co
m
p
a
r
in
g
o
u
r
r
esu
lts
to
ex
is
tin
g
r
esear
ch
,
it
is
ev
id
en
t
th
at
th
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
a
d
d
r
ess
es
k
ey
lim
itatio
n
s
r
elate
d
to
f
ea
tu
r
e
r
ed
u
n
d
a
n
cy
,
b
io
lo
g
ical
in
ter
p
r
etab
ilit
y
,
an
d
class
if
icatio
n
r
o
b
u
s
tn
ess
,
d
em
o
n
s
tr
atin
g
s
u
p
er
i
o
r
p
er
f
o
r
m
an
ce
.
Fo
r
in
s
tan
ce
,
L
i
et
a
l.
[
4
0
]
ac
h
iev
e
d
an
AU
C
o
f
0
.
8
7
,
co
n
s
id
er
a
b
ly
lo
wer
th
an
o
u
r
m
o
d
el’
s
AUC o
f
0
.
9
9
8
o
n
T
C
GA
-
L
UAD
an
d
0
.
9
9
5
o
n
GSE1
9
1
8
8
.
T
h
e
ir
r
elian
ce
o
n
d
if
f
er
e
n
tial
ex
p
r
ess
io
n
an
aly
s
is
with
o
u
t
r
o
b
u
s
t
f
ea
tu
r
e
s
elec
tio
n
co
n
tr
ib
u
tes
to
s
u
b
o
p
tim
al
p
er
f
o
r
m
an
ce
,
u
n
lik
e
o
u
r
m
u
lti
-
s
tag
e
ap
p
r
o
ac
h
th
at
in
te
g
r
ates
s
tatis
t
ical
f
ilter
in
g
,
en
tr
o
p
y
-
b
ased
r
a
n
k
in
g
,
an
d
s
p
ar
s
e
au
to
en
co
d
er
r
ef
i
n
em
en
t f
o
r
co
m
p
ac
t a
n
d
i
n
f
o
r
m
ativ
e
g
e
n
e
s
elec
tio
n
.
Similar
ly
,
Z
h
en
g
et
a
l.
[
4
1
]
r
ep
o
r
ted
AUC
v
alu
es
r
an
g
i
n
g
f
r
o
m
0
.
8
5
to
0
.
9
2
o
n
T
C
GA
-
L
UAD
an
d
f
r
o
m
0
.
8
3
to
0
.
9
0
o
n
GSE1
9
1
8
8
.
Alth
o
u
g
h
th
is
s
tu
d
y
lev
er
ag
ed
n
etwo
r
k
-
b
ased
m
et
h
o
d
s
f
o
r
b
io
m
ar
k
e
r
id
en
tific
atio
n
,
it
lack
e
d
ad
v
an
ce
d
m
ec
h
an
is
m
s
to
m
itig
ate
f
ea
tu
r
e
r
ed
u
n
d
an
c
y
o
r
i
m
p
r
o
v
e
b
io
lo
g
ical
in
ter
p
r
etab
ilit
y
.
I
n
c
o
n
tr
ast,
o
u
r
m
eth
o
d
i
n
co
r
p
o
r
ates
s
tab
ilit
y
s
elec
tio
n
an
d
en
tr
o
p
y
-
d
r
iv
e
n
s
co
r
in
g
,
f
o
llo
wed
b
y
atten
tio
n
-
b
ased
d
ee
p
lear
n
i
n
g
to
e
n
s
u
r
e
b
o
t
h
r
elev
a
n
ce
an
d
n
o
n
-
r
ed
u
n
d
a
n
cy
in
t
h
e
s
elec
ted
f
ea
tu
r
es.
Sh
er
af
atian
an
d
Ar
jm
an
d
[
4
2
]
em
p
lo
y
ed
in
ter
p
r
etab
le
d
ec
is
io
n
tr
ee
class
if
ier
s
b
u
t
r
ep
o
r
ted
an
AUC
o
f
o
n
l
y
0
.
9
1
a
n
d
a
n
ac
cu
r
ac
y
o
f
8
7
.
9
%.
W
h
ile
d
ec
is
io
n
tr
ee
s
o
f
f
er
tr
a
n
s
p
ar
en
cy
,
th
ey
ar
e
o
f
ten
to
o
s
im
p
lis
tic
to
ca
p
tu
r
e
th
e
co
m
p
lex
,
n
o
n
-
l
in
ea
r
p
atter
n
s
with
in
h
ig
h
-
d
i
m
en
s
io
n
al
tr
an
s
cr
ip
to
m
ic
d
ata
.
Ou
r
d
ee
p
lear
n
in
g
class
if
ier
with
an
atten
tio
n
m
ec
h
a
n
is
m
o
v
e
r
co
m
es
t
h
e
s
e
lim
itatio
n
s
,
ac
h
iev
in
g
9
9
.
3
%
ac
cu
r
ac
y
a
n
d
h
ig
h
lig
h
tin
g
th
e
m
o
s
t b
io
lo
g
ic
ally
in
f
o
r
m
ativ
e
f
ea
tu
r
es.
R
an
a
et
a
l.
[
4
3
]
ac
h
iev
ed
an
AUC
o
f
0
.
9
2
a
n
d
ap
p
r
o
x
im
at
ely
9
4
%
ac
cu
r
ac
y
b
y
a
p
p
ly
in
g
iter
ativ
e
f
ea
tu
r
e
s
elec
tio
n
.
Ho
wev
er
,
t
h
eir
r
elian
ce
o
n
lin
ea
r
r
ed
u
n
d
an
cy
r
e
d
u
ctio
n
m
ay
f
ail
to
ca
p
tu
r
e
in
tr
icate
g
en
e
in
ter
ac
tio
n
s
.
B
y
in
co
r
p
o
r
atin
g
a
s
p
ar
s
e
au
to
en
co
d
er
in
th
e
f
in
al
s
tag
e
o
f
o
u
r
s
elec
tio
n
p
r
o
ce
s
s
,
we
s
u
cc
ess
f
u
lly
d
etec
t n
o
n
-
lin
ea
r
d
ep
en
d
e
n
cies,
f
u
r
th
e
r
im
p
r
o
v
i
n
g
p
er
f
o
r
m
a
n
ce
an
d
r
o
b
u
s
tn
ess
.
L
astl
y
,
W
ei
et
a
l.
[
4
4
]
r
e
p
o
r
te
d
an
AUC
o
f
0
.
9
9
5
8
u
s
in
g
lo
g
is
tic
r
eg
r
ess
io
n
ap
p
lied
to
m
u
lti
-
o
m
ics
d
ata.
Alth
o
u
g
h
im
p
r
ess
iv
e,
th
eir
m
o
d
el
in
tr
o
d
u
ce
s
s
ig
n
if
ican
t
co
m
p
lex
ity
d
u
e
to
t
h
e
in
teg
r
atio
n
o
f
h
eter
o
g
en
e
o
u
s
d
ata
ty
p
es.
I
n
co
n
tr
ast,
o
u
r
s
in
g
le
-
o
m
i
cs
R
NA
-
Seq
-
b
ased
m
eth
o
d
ac
h
iev
es
s
im
ilar
p
er
f
o
r
m
an
ce
with
r
ed
u
ce
d
d
a
ta
b
u
r
d
e
n
.
Mo
r
eo
v
er
,
wh
ile
t
h
at
s
tu
d
y
em
p
lo
y
s
Sh
ap
ley
a
d
d
itiv
e
ex
p
la
n
atio
n
s
(
SHAP)
f
o
r
in
ter
p
r
etab
ilit
y
,
o
u
r
ap
p
r
o
ac
h
p
r
o
v
id
es
d
ir
ec
t
b
io
lo
g
ical
v
alid
atio
n
v
ia
p
a
th
way
en
r
ich
m
e
n
t
an
aly
s
is
,
o
f
f
er
i
n
g
m
o
r
e
in
ter
p
r
etab
le
a
n
d
clin
ically
m
ea
n
i
n
g
f
u
l
in
s
ig
h
ts
in
to
L
UAD
-
r
e
lev
an
t
m
ec
h
an
is
m
s
s
u
ch
as E
GFR
s
ig
n
alin
g
,
im
m
u
n
e
r
esp
o
n
s
e,
an
d
ce
ll c
y
cle
d
y
s
r
eg
u
latio
n
.
I
n
co
n
clu
s
io
n
,
b
y
co
m
b
in
in
g
s
tatis
t
ical
f
ilter
in
g
,
en
tr
o
p
y
-
b
ased
r
an
k
in
g
,
s
p
ar
s
e
au
t
o
en
c
o
d
in
g
,
a
n
d
atten
tio
n
-
d
r
iv
e
n
class
if
icatio
n
,
o
u
r
f
r
a
m
ewo
r
k
a
d
d
r
ess
es
lim
itatio
n
s
s
ee
n
ac
r
o
s
s
cu
r
r
en
t
L
UAD
s
tu
d
ies.
I
t
d
eliv
er
s
co
m
p
ac
t,
p
r
ed
ictiv
e,
an
d
b
io
lo
g
ically
in
ter
p
r
eta
b
le
g
en
e
s
u
b
s
ets
v
alid
ated
ac
r
o
s
s
d
atasets
.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
o
u
r
m
eth
o
d
’
s
p
o
te
n
tial
f
o
r
u
s
e
i
n
tr
a
n
s
latio
n
al
r
esear
ch
an
d
p
r
ec
is
io
n
o
n
co
lo
g
y
,
en
ab
lin
g
r
eliab
le
b
io
m
ar
k
er
d
is
co
v
e
r
y
a
n
d
p
er
s
o
n
alize
d
d
iag
n
o
s
tics
.
4
.
5
.
B
io
lo
g
ic
a
l v
a
lid
a
t
io
n
o
f
s
elec
t
ed
f
ea
t
ures
Path
way
en
r
ich
m
e
n
t
a
n
aly
s
is
co
n
f
i
r
m
ed
th
e
b
io
lo
g
ical
r
el
ev
an
ce
o
f
t
h
e
1
0
s
elec
ted
g
e
n
es
in
lu
n
g
ad
en
o
ca
r
cin
o
m
a,
h
ig
h
lig
h
tin
g
th
eir
in
v
o
l
v
em
en
t
in
k
ey
c
an
ce
r
-
r
elate
d
p
ath
way
s
u
s
in
g
KE
GG
an
d
GO
d
atab
ases
.
No
tab
ly
,
th
e
E
GFR
s
ig
n
alin
g
p
ath
way
ce
n
tr
al
t
o
tu
m
o
r
p
r
o
life
r
atio
n
,
an
g
io
g
en
esis
,
an
d
th
er
a
p
y
r
esis
tan
ce
was
s
ig
n
if
ican
tly
en
r
ich
ed
,
alo
n
g
with
p
ath
wa
y
s
r
elate
d
t
o
ce
ll
c
y
cle
r
e
g
u
latio
n
an
d
im
m
u
n
e
r
esp
o
n
s
e,
u
n
d
er
s
co
r
in
g
d
is
r
u
p
tio
n
s
in
ce
ll
d
iv
is
io
n
an
d
tu
m
o
r
-
im
m
u
n
e
in
ter
ac
tio
n
s
.
T
h
e
g
en
e
s
et
in
clu
d
e
d
well
-
estab
lis
h
ed
b
io
m
ar
k
er
s
s
u
ch
as
s
u
r
f
a
ctan
t
p
r
o
tein
A2
(
SF
T
PA2
)
,
a
k
e
y
p
lay
er
i
n
lu
n
g
f
u
n
ctio
n
an
d
d
iag
n
o
s
tics
;
n
ap
s
in
a
n
asp
ar
tic
p
ep
tid
ase
(
NAPSA
)
,
a
p
r
o
tea
s
e
u
s
ed
to
d
is
tin
g
u
is
h
lu
n
g
ad
en
o
ca
r
cin
o
m
a
f
r
o
m
o
th
er
ca
n
ce
r
s
; a
n
d
T
-
b
o
x
t
r
an
s
cr
ip
tio
n
f
ac
to
r
4
(
T
B
X4
)
,
in
v
o
lv
ed
in
lu
n
g
d
e
v
elo
p
m
e
n
t a
n
d
o
n
co
g
e
n
esis
.
I
n
ad
d
itio
n
to
th
ese
k
n
o
wn
m
ar
k
er
s
,
two
n
o
v
el
g
e
n
es
Mu
cin
1
6
(
MU
C
1
6
)
an
d
tar
g
etin
g
p
r
o
tein
f
o
r
x
en
o
p
u
s
k
in
esin
-
lik
e
p
r
o
tein
2
(
T
PX2
)
wer
e
id
en
tifie
d
.
MU
C
1
6
is
l
in
k
ed
to
im
m
u
n
e
ev
asio
n
an
d
ep
ith
elial
-
m
esen
ch
y
m
al
tr
an
s
itio
n
(
E
MT
)
,
co
n
tr
ib
u
tin
g
t
o
tu
m
o
r
p
r
o
g
r
ess
io
n
an
d
m
etastas
is
,
wh
ile
T
PX2
,
ass
o
ciate
d
with
m
ito
tic
s
p
in
d
le
f
o
r
m
atio
n
,
p
r
o
m
o
tes
u
n
co
n
tr
o
lled
ce
ll
p
r
o
life
r
atio
n
.
T
h
eir
in
clu
s
io
n
d
em
o
n
s
tr
ates
th
e
f
r
am
ewo
r
k
’
s
ab
ilit
y
t
o
d
etec
t
b
o
th
estab
lis
h
ed
an
d
p
r
e
v
io
u
s
l
y
u
n
r
ec
o
g
n
ized
b
io
m
ar
k
er
s
,
o
f
f
er
in
g
n
ew
in
s
ig
h
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
7
0
3
-
4
7
1
0
4708
f
o
r
d
iag
n
o
s
tic
an
d
th
e
r
ap
eu
tic
s
tr
ateg
ies
in
lu
n
g
ad
en
o
ca
r
cin
o
m
a
an
d
s
u
p
p
o
r
tin
g
ad
v
an
ce
m
en
ts
i
n
p
er
s
o
n
alize
d
an
d
tr
an
s
latio
n
al
o
n
co
lo
g
y
.
4
.
6
.
Dis
cus
s
io
n a
nd
lim
it
a
t
io
ns
T
h
e
f
in
d
i
n
g
s
v
alid
ate
th
e
p
r
o
p
o
s
ed
m
u
lti
-
s
tag
e
f
ea
tu
r
e
s
elec
tio
n
f
r
am
ewo
r
k
as
a
r
o
b
u
s
t
an
d
in
ter
p
r
etab
le
to
o
l
f
o
r
l
u
n
g
c
an
ce
r
class
if
icatio
n
.
B
y
in
c
o
r
p
o
r
atin
g
s
tatis
tical,
en
tr
o
p
y
-
d
r
iv
en
,
an
d
d
ee
p
lear
n
in
g
m
eth
o
d
o
l
o
g
ies,
th
e
f
r
am
ewo
r
k
ef
f
ec
tiv
ely
tac
k
les
k
ey
ch
allen
g
es
in
h
e
r
en
t
in
h
ig
h
-
d
im
en
s
io
n
al
R
NA
-
Seq
d
ata,
in
clu
d
in
g
is
s
u
es
s
u
ch
as
n
o
is
e,
r
ed
u
n
d
an
cy
,
an
d
o
v
e
r
f
itti
n
g
.
T
h
e
f
r
am
ewo
r
k
'
s
s
tr
o
n
g
p
er
f
o
r
m
an
ce
o
n
b
o
th
th
e
T
C
GA
-
L
UAD
an
d
GSE1
9
1
8
8
d
atasets
u
n
d
er
s
co
r
es
its
p
o
ten
t
ial
ap
p
licab
ilit
y
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
,
p
ar
ticu
la
r
ly
in
b
io
m
ar
k
er
d
is
co
v
er
y
an
d
ca
n
ce
r
d
iag
n
o
s
tics
.
Desp
ite
th
ese
p
r
o
m
is
in
g
r
esu
l
ts
,
s
ev
er
al
lim
itatio
n
s
s
h
o
u
ld
b
e
n
o
ted
.
First,
wh
ile
th
e
f
in
a
l
s
u
b
s
et
o
f
1
0
g
en
es
is
h
ig
h
ly
in
ter
p
r
eta
b
le,
it
m
ay
o
v
er
lo
o
k
f
ea
tu
r
es
ass
o
ciate
d
with
less
co
m
m
o
n
p
ath
way
s
o
r
r
ar
e
s
u
b
ty
p
es
o
f
lu
n
g
a
d
en
o
ca
r
cin
o
m
a.
Seco
n
d
,
p
latf
o
r
m
v
a
r
iab
ilit
y
b
etwe
en
R
NA
-
Seq
an
d
m
icr
o
ar
r
ay
d
atasets
,
th
o
u
g
h
ad
d
r
ess
ed
in
th
e
an
aly
s
is
,
co
u
ld
im
p
ac
t
th
e
g
e
n
er
aliza
b
ilit
y
o
f
th
e
f
in
d
in
g
s
ac
r
o
s
s
d
if
f
er
en
t
tech
n
o
lo
g
ical
p
latf
o
r
m
s
.
L
astl
y
,
wh
ile
p
ath
way
en
r
ich
m
e
n
t
an
aly
s
is
s
u
p
p
o
r
ts
th
e
b
io
lo
g
ical
s
ig
n
if
ican
ce
o
f
th
e
s
elec
ted
g
en
es,
ad
d
itio
n
al
ex
p
er
im
en
tal
v
alid
atio
n
is
n
ee
d
ed
to
co
n
f
ir
m
th
eir
f
u
n
cti
o
n
al
r
o
les
in
lu
n
g
ad
en
o
ca
r
cin
o
m
a
p
r
o
g
r
ess
io
n
.
No
n
eth
eless
,
th
is
s
tu
d
y
r
ep
r
esen
ts
a
s
ig
n
if
ican
t
ad
v
an
ce
m
en
t
in
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
f
o
r
ca
n
ce
r
class
if
icatio
n
.
T
h
e
f
r
am
ewo
r
k
n
o
t
o
n
ly
en
h
an
ce
s
th
e
i
n
ter
p
r
etab
ilit
y
o
f
s
elec
ted
b
io
m
ar
k
e
r
s
b
u
t
also
p
r
o
v
id
es
a
f
o
u
n
d
atio
n
f
o
r
f
u
tu
r
e
r
es
ea
r
ch
to
ex
p
l
o
r
e
t
h
e
clin
ic
al
p
o
ten
tial
o
f
t
h
ese
b
io
m
a
r
k
er
s
.
B
y
b
r
id
g
i
n
g
co
m
p
u
tatio
n
al
p
r
ed
ictio
n
s
w
ith
b
io
lo
g
ical
in
s
ig
h
ts
,
th
is
ap
p
r
o
ac
h
p
av
es
th
e
way
f
o
r
ad
v
an
ce
m
e
n
ts
in
p
r
ec
is
io
n
o
n
c
o
lo
g
y
an
d
th
e
d
e
v
elo
p
m
en
t
o
f
p
e
r
s
o
n
alize
d
d
ia
g
n
o
s
tic
an
d
th
e
r
ap
eu
tic
s
tr
ateg
ies.
5.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
we
d
e
v
elo
p
ed
a
r
o
b
u
s
t
an
d
in
ter
p
r
etab
le
m
u
lti
-
s
tag
e
f
ea
tu
r
e
s
elec
tio
n
a
n
d
cla
s
s
if
icatio
n
f
r
am
ewo
r
k
tailo
r
e
d
to
lu
n
g
ad
en
o
ca
r
cin
o
m
a
d
iag
n
o
s
is
u
s
in
g
R
NA
-
Seq
g
en
e
ex
p
r
ess
io
n
d
ata.
B
y
in
teg
r
atin
g
s
tatis
t
ical
s
ig
n
if
ican
ce
,
en
tr
o
p
y
-
d
r
iv
en
r
a
n
k
in
g
,
an
d
s
p
ar
s
e
au
to
en
co
d
er
r
ef
in
e
m
e
n
t,
th
e
f
r
am
ewo
r
k
s
u
cc
ess
f
u
lly
id
en
tifie
d
a
co
m
p
ac
t
s
u
b
s
et
o
f
1
0
b
io
lo
g
ic
ally
r
elev
an
t
g
en
es,
v
alid
ate
d
th
r
o
u
g
h
p
ath
way
en
r
ich
m
en
t
an
d
h
i
g
h
class
if
ic
atio
n
p
e
r
f
o
r
m
an
ce
ac
r
o
s
s
T
C
GA
an
d
GE
O
d
atasets
.
T
h
e
h
y
b
r
id
d
ee
p
lear
n
i
n
g
m
o
d
el
in
co
r
p
o
r
atin
g
atten
tio
n
m
ec
h
an
is
m
s
n
o
t
o
n
ly
ac
h
ie
v
ed
s
tate
-
of
-
th
e
-
ar
t
ac
cu
r
ac
y
b
u
t
also
p
r
eser
v
e
d
b
io
lo
g
ical
in
s
ig
h
t
b
y
h
ig
h
lig
h
tin
g
cr
itical
b
io
m
ar
k
e
r
s
s
u
ch
as
SF
T
P
A2
,
NAPSA,
T
B
X4
,
MU
C
1
6
,
an
d
T
PX2
.
C
r
o
s
s
-
p
latf
o
r
m
v
alid
atio
n
co
n
f
ir
m
ed
t
h
e
m
eth
o
d
’
s
g
e
n
er
a
lizab
ilit
y
,
wh
ile
th
e
in
clu
s
io
n
o
f
n
o
v
el
m
a
r
k
er
s
s
u
g
g
ests
p
r
o
m
is
in
g
av
en
u
es
f
o
r
tr
an
s
latio
n
al
ca
n
ce
r
r
esear
ch
.
T
h
ese
f
in
d
in
g
s
u
n
d
er
s
co
r
e
th
e
f
r
am
ewo
r
k
'
s
p
o
ten
tial
as
a
v
alu
ab
le
to
o
l
i
n
p
r
ec
is
io
n
o
n
c
o
lo
g
y
,
with
f
u
tu
r
e
ex
ten
s
io
n
s
p
o
ten
tially
in
co
r
p
o
r
atin
g
m
u
lti
-
o
m
ics in
teg
r
atio
n
a
n
d
n
etwo
r
k
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
to
f
u
r
th
er
en
h
a
n
ce
its
clin
ical
u
tili
ty
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Sar
a
Had
d
o
u
B
o
u
az
z
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
J
ih
ad
Had
d
o
u
B
o
u
az
za
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Dee
p
lea
r
n
in
g
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
fo
r
lu
n
g
a
d
en
o
ca
r
cin
o
ma
cla
s
s
ifica
tio
n
…
(
S
a
r
a
H
a
d
d
o
u
B
o
u
a
z
z
a
)
4709
I
NF
O
RM
E
D
CO
NS
E
N
T
T
h
is
s
tu
d
y
d
i
d
n
o
t
in
v
o
lv
e
in
d
iv
id
u
als
n
o
r
an
y
p
er
s
o
n
al
id
en
tific
atio
n
in
f
o
r
m
atio
n
t
h
at
co
u
ld
r
eq
u
i
r
e
an
y
in
f
o
r
m
ed
co
n
s
en
t.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
p
ap
er
d
o
es
n
o
t
in
v
o
lv
e
p
eo
p
le
o
r
an
im
als;
n
o
in
v
e
s
tig
atio
n
h
as
in
v
o
lv
e
d
h
u
m
a
n
s
u
b
jects.
T
h
er
ef
o
r
e,
th
e
a
u
th
o
r
s
d
i
d
n
o
t
s
ee
k
ap
p
r
o
v
al
f
r
o
m
an
y
in
s
titu
tio
n
al
r
ev
iew
b
o
a
r
d
.
DATA AV
AI
L
AB
I
L
I
T
Y
D
a
t
a
a
v
a
il
a
b
i
li
t
y
is
n
o
t
a
p
p
l
i
ca
b
l
e
t
o
t
h
is
p
a
p
e
r
a
s
n
o
n
e
w
d
at
a
w
e
r
e
c
r
e
a
t
e
d
o
r
a
n
al
y
z
e
d
i
n
t
h
is
s
t
u
d
y
.
R
E
F
E
RE
NC
E
S
[
1
]
R
.
H
.
E
l
d
e
n
,
V
.
F
.
G
h
o
n
i
m
,
M
.
M
.
A
.
H
a
d
h
o
u
d
,
a
n
d
W
.
A
l
-
A
t
a
b
a
n
y
,
“
Tr
a
n
s
c
r
i
p
t
o
mi
c
m
a
r
k
e
r
s
c
r
e
e
n
i
n
g
f
o
r
e
v
a
l
u
a
t
i
n
g
t
h
e
m
o
r
t
a
l
i
t
y
r
a
t
e
o
f
p
e
d
i
a
t
r
i
c
s
e
p
si
s
b
a
se
d
o
n
H
e
n
r
y
g
a
s
s
o
l
u
b
i
l
i
t
y
o
p
t
i
m
i
z
a
t
i
o
n
,
”
A
l
e
x
a
n
d
ri
a
E
n
g
i
n
e
e
r
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
6
8
,
p
p
.
6
9
3
–
7
0
7
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
2
.
1
2
.
0
2
7
.
[
2
]
M
.
El
l
o
u
m
i
,
M
.
A
.
A
h
ma
d
,
A
.
H
.
S
a
mak
,
A
.
M
.
A
.
-
S
h
a
r
a
f
i
,
D
.
K
i
h
a
r
a
,
a
n
d
A
.
I
.
Ta
l
o
b
a
,
“
Er
r
o
r
c
o
r
r
e
c
t
i
o
n
a
l
g
o
r
i
t
h
ms
i
n
n
o
n
-
n
u
l
l
a
sp
h
e
r
i
c
t
e
st
i
n
g
n
e
x
t
g
e
n
e
r
a
t
i
o
n
s
e
q
u
e
n
c
i
n
g
d
a
t
a
,
”
Al
e
x
a
n
d
r
i
a
E
n
g
i
n
e
e
ri
n
g
J
o
u
r
n
a
l
,
v
o
l
.
6
1
,
n
o
.
1
2
,
p
p
.
9
8
1
9
–
9
8
2
9
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
2
.
0
3
.
0
4
1
.
[
3
]
A
.
A
k
g
ü
l
,
S
.
H
.
A
.
K
h
o
s
h
n
a
w
,
a
n
d
H
.
M
.
R
a
s
o
o
l
,
“
M
i
n
i
mi
z
i
n
g
c
e
l
l
s
i
g
n
a
l
l
i
n
g
p
a
t
h
w
a
y
e
l
e
me
n
t
s
u
s
i
n
g
l
u
m
p
i
n
g
p
a
r
a
me
t
e
r
s,
”
Al
e
x
a
n
d
ri
a
E
n
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
5
9
,
n
o
.
4
,
p
p
.
2
1
6
1
–
2
1
6
9
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
0
.
0
1
.
0
4
1
.
[
4
]
Y
.
Esm
a
e
i
l
i
e
t
a
l
.
,
“
Ex
p
l
o
r
i
n
g
t
h
e
e
v
o
l
u
t
i
o
n
o
f
t
i
ss
u
e
e
n
g
i
n
e
e
r
i
n
g
s
t
r
a
t
e
g
i
e
s
o
v
e
r
t
h
e
p
a
s
t
d
e
c
a
d
e
:
f
r
o
m
c
e
l
l
-
b
a
sed
st
r
a
t
e
g
i
e
s
t
o
g
e
n
e
-
a
c
t
i
v
a
t
e
d
ma
t
r
i
x
,
”
Al
e
x
a
n
d
r
i
a
E
n
g
i
n
e
e
r
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
8
1
,
p
p
.
1
3
7
–
1
6
9
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
3
.
0
8
.
0
8
0
.
[
5
]
M
.
S
h
a
h
e
e
n
,
N
.
N
a
h
e
e
d
,
a
n
d
A
.
A
h
s
a
n
,
“
R
e
l
e
v
a
n
c
e
-
d
i
v
e
r
si
t
y
a
l
g
o
r
i
t
h
m
f
o
r
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
mo
d
i
f
i
e
d
B
a
y
e
s
f
o
r
p
r
e
d
i
c
t
i
o
n
,
”
Al
e
x
a
n
d
ri
a
E
n
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
6
6
,
p
p
.
3
2
9
–
3
4
2
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
2
.
1
1
.
0
0
2
.
[
6
]
L.
Z
h
a
n
g
,
L.
Li
,
M
.
Ta
n
g
,
Y
.
H
u
a
n
,
X
.
Zh
a
n
g
,
a
n
d
X
.
Z
h
e
,
“
A
n
e
w
a
p
p
r
o
a
c
h
t
o
d
i
a
g
n
o
si
n
g
p
r
o
st
a
t
e
c
a
n
c
e
r
t
h
r
o
u
g
h
m
a
g
n
e
t
i
c
r
e
so
n
a
n
c
e
i
m
a
g
i
n
g
,
”
Al
e
x
a
n
d
ri
a
En
g
i
n
e
e
ri
n
g
J
o
u
r
n
a
l
,
v
o
l
.
6
0
,
n
o
.
1
,
p
p
.
8
9
7
–
9
0
4
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
0
.
1
0
.
0
1
8
.
[
7
]
S
.
J
.
S
u
sm
i
,
H
.
K
.
N
e
h
e
m
i
a
h
,
A
.
K
a
n
n
a
n
,
a
n
d
J
.
C
h
r
i
st
o
p
h
e
r
,
“
R
e
l
e
v
a
n
t
g
e
n
e
se
l
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
l
e
u
k
e
mi
a
g
e
n
e
e
x
p
r
e
ss
i
o
n
d
a
t
a
,
”
i
n
Em
e
r
g
i
n
g
Re
se
a
rc
h
i
n
C
o
m
p
u
t
i
n
g
,
I
n
f
o
rm
a
t
i
o
n
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
1
6
,
p
p
.
5
0
3
–
5
1
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
10
-
0
2
8
7
-
8
_
4
7
.
[
8
]
A
.
S
.
M
.
S
h
a
f
i
,
M
.
M
.
I
.
M
o
l
l
a
,
J
.
J
.
Ju
i
,
a
n
d
M
.
M
.
R
a
h
ma
n
,
“
D
e
t
e
c
t
i
o
n
o
f
c
o
l
o
n
c
a
n
c
e
r
b
a
s
e
d
o
n
m
i
c
r
o
a
r
r
a
y
d
a
t
a
s
e
t
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
s
a
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
S
N
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
2
,
n
o
.
7
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
4
5
2
-
0
2
0
-
3
0
5
1
-
2.
[
9
]
N
.
K
,
H
.
R
a
j
a
g
u
r
u
,
a
n
d
R
.
P
,
“
M
i
c
r
o
a
r
r
a
y
p
r
o
st
a
t
e
c
a
n
c
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
e
mi
n
e
n
t
g
e
n
e
s
,
”
i
n
2
0
2
1
S
m
a
rt
T
e
c
h
n
o
l
o
g
i
e
s,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
R
o
b
o
t
i
c
s
,
I
EEE,
O
c
t
.
2
0
2
1
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
S
TC
R
5
1
6
5
8
.
2
0
2
1
.
9
5
8
8
8
1
1
.
[
1
0
]
E
.
B
a
d
r
,
S
.
A
l
m
o
t
a
i
r
i
,
M
.
A
.
S
a
l
a
m
,
a
n
d
H
.
A
h
m
e
d
,
“
N
e
w
s
e
q
u
e
n
t
i
a
l
a
n
d
p
a
r
a
l
l
e
l
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
w
i
t
h
g
r
e
y
w
o
l
f
o
p
t
i
m
i
z
e
r
f
o
r
b
r
e
a
s
t
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
,”
A
l
e
x
a
n
d
r
i
a
E
n
g
i
n
e
e
r
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
6
1
,
n
o
.
3
,
p
p
.
2
5
2
0
–
2
5
3
4
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
1
.
0
7
.
0
2
4
.
[
1
1
]
S
.
H
.
B
o
u
a
z
z
a
a
n
d
J
.
H
.
B
o
u
a
z
z
a
,
“
R
e
v
o
l
u
t
i
o
n
i
z
i
n
g
c
a
n
c
e
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
:
t
h
e
S
N
R
-
O
G
S
C
C
m
e
t
h
o
d
f
o
r
i
m
p
r
o
v
e
d
g
e
n
e
s
e
l
e
c
t
i
o
n
a
n
d
c
l
u
s
t
e
r
i
n
g
,
”
I
A
E
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
4
6
6
-
472
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
4
.
i
1
.
p
p
4
6
6
-
472.
[
1
2
]
T
.
A
l
t
h
o
b
a
i
t
i
,
S
.
A
l
t
h
o
b
a
i
t
i
,
a
n
d
M
.
M
.
S
e
l
i
m
,
“
A
n
o
p
t
i
m
i
z
e
d
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
d
e
t
e
c
t
i
o
n
m
o
d
e
l
f
o
r
i
m
p
r
o
v
e
d
p
r
e
d
i
c
t
i
o
n
o
f
a
c
c
u
r
a
c
y
a
n
d
c
l
i
n
i
c
a
l
d
e
c
i
s
i
o
n
-
m
a
k
i
n
g
,
”
A
l
e
x
a
n
d
r
i
a
E
n
g
i
n
e
e
r
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
9
4
,
p
p
.
3
1
1
–
3
2
4
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
4
.
0
3
.
0
4
4
.
[
1
3
]
F
.
N
o
ma
n
e
t
a
l
.
,
“
M
u
l
t
i
st
e
p
s
h
o
r
t
-
t
e
r
m
w
i
n
d
sp
e
e
d
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
n
o
n
l
i
n
e
a
r
a
u
t
o
-
r
e
g
r
e
ssi
v
e
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
e
x
o
g
e
n
o
u
s
v
a
r
i
a
b
l
e
se
l
e
c
t
i
o
n
,
”
Al
e
x
a
n
d
r
i
a
E
n
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
6
0
,
n
o
.
1
,
p
p
.
1
2
2
1
–
1
2
2
9
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
0
.
1
0
.
0
4
5
.
[
1
4
]
L.
Za
n
e
l
l
a
,
P
.
F
a
c
c
o
,
F
.
B
e
z
z
o
,
a
n
d
E.
C
i
me
t
t
a
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
m
o
l
e
c
u
l
a
r
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
a
n
c
e
r
p
h
e
n
o
t
y
p
e
s
:
a
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
M
o
l
e
c
u
l
a
r
S
c
i
e
n
c
e
s
,
v
o
l
.
2
3
,
n
o
.
1
6
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
ms
2
3
1
6
9
0
8
7
.
[
1
5
]
S
.
H
.
B
o
u
a
z
z
a
a
n
d
J.
H
.
B
o
u
a
z
z
a
,
“
C
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
a
n
d
c
o
mp
u
t
e
r
v
i
si
o
n
t
e
c
h
n
i
q
u
e
s,”
I
T
M
W
e
b
o
f
C
o
n
f
e
re
n
c
e
s
,
v
o
l
.
6
9
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
5
1
/
i
t
mc
o
n
f
/
2
0
2
4
6
9
0
2
0
0
2
.
[
1
6
]
S
.
H
.
B
o
u
a
z
z
a
a
n
d
J
.
H
.
B
o
u
a
z
z
a
,
“
O
p
t
i
mi
z
e
d
c
o
l
o
n
c
a
n
c
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
v
i
a
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
B
u
l
l
e
t
i
n
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
1
4
7
6
–
1
4
8
5
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
4
i
2
.
9
2
7
0
.
[
1
7
]
W
.
A
l
i
a
n
d
F
.
S
a
e
e
d
,
“
H
y
b
r
i
d
f
i
l
t
e
r
a
n
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
-
b
a
se
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
f
o
r
i
mp
r
o
v
i
n
g
c
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
mi
c
r
o
a
r
r
a
y
d
a
t
a
,”
Pro
c
e
s
ses
,
v
o
l
.
1
1
,
n
o
.
2
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
p
r
1
1
0
2
0
5
6
2
.
[
1
8
]
Y
.
S
u
n
,
V
.
U
r
q
u
i
d
i
,
a
n
d
S
.
G
o
o
d
i
s
o
n
,
“
D
e
r
i
v
a
t
i
o
n
o
f
m
o
l
e
c
u
l
a
r
s
i
g
n
a
t
u
r
e
s
f
o
r
b
r
e
a
s
t
c
a
n
c
e
r
r
e
c
u
r
r
e
n
c
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
a
t
w
o
-
w
a
y
v
a
l
i
d
a
t
i
o
n
a
p
p
r
o
a
c
h
,
”
B
r
e
a
s
t
C
a
n
c
e
r
R
e
s
e
a
r
c
h
a
n
d
T
r
e
a
t
m
e
n
t
,
v
o
l
.
1
1
9
,
n
o
.
3
,
p
p
.
5
9
3
–
5
9
9
,
F
e
b
.
2
0
1
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
4
9
-
009
-
0
3
6
5
-
6.
[
1
9
]
X
.
D
e
n
g
,
M
.
L
i
,
S
.
D
e
n
g
,
a
n
d
L.
W
a
n
g
,
“
H
y
b
r
i
d
g
e
n
e
s
e
l
e
c
t
i
o
n
a
p
p
r
o
a
c
h
u
si
n
g
X
G
B
o
o
st
a
n
d
m
u
l
t
i
-
o
b
j
e
c
t
i
v
e
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
f
o
r
c
a
n
c
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
M
e
d
i
c
a
l
&
Bi
o
l
o
g
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
&
C
o
m
p
u
t
i
n
g
,
v
o
l
.
6
0
,
n
o
.
3
,
p
p
.
6
6
3
–
6
8
1
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
1
7
-
0
2
1
-
0
2
4
7
6
-
x.
[
2
0
]
O
.
A
b
d
e
l
w
a
h
a
b
,
N
.
A
w
a
d
,
M
.
El
s
e
r
a
f
y
,
a
n
d
E
.
B
a
d
r
,
“
A
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
-
b
a
se
d
f
r
a
m
e
w
o
r
k
t
o
i
d
e
n
t
i
f
y
b
i
o
m
a
r
k
e
r
s
f
o
r
c
a
n
c
e
r
d
i
a
g
n
o
si
s
:
a
f
o
c
u
s
o
n
l
u
n
g
a
d
e
n
o
c
a
r
c
i
n
o
m
a
,
”
PLO
S
O
N
E
,
v
o
l
.
1
7
,
n
o
.
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
6
9
1
2
6
.
[
2
1
]
K
.
M
y
a
c
h
e
v
a
,
A
.
W
a
l
sh
,
M
.
R
i
e
st
e
r
,
G
.
P
e
l
o
s
,
J.
C
a
r
l
,
a
n
d
S
.
D
i
e
d
e
r
i
c
h
s,
“
C
R
I
S
P
R
i
scre
e
n
i
n
g
i
d
e
n
t
i
f
i
e
s
C
A
S
P
8
A
P
2
a
s
a
n
e
sse
n
t
i
a
l
v
i
a
b
i
l
i
t
y
f
a
c
t
o
r
i
n
l
u
n
g
c
a
n
c
e
r
c
o
n
t
r
o
l
l
i
n
g
t
u
mo
r
c
e
l
l
d
e
a
t
h
v
i
a
t
h
e
A
P
-
1
p
a
t
h
w
a
y
,
”
C
a
n
c
e
r
L
e
t
t
e
rs
,
v
o
l
.
5
5
2
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
a
n
l
e
t
.
2
0
2
2
.
2
1
5
9
5
8
.
[
2
2
]
J.
P
.
R
o
ss
,
S
.
v
.
D
i
j
k
,
M
.
P
h
a
n
g
,
M
.
R
.
S
k
i
l
t
o
n
,
P
.
L
.
M
o
l
l
o
y
,
a
n
d
Y
.
O
y
t
a
m,
“
B
a
t
c
h
-
e
f
f
e
c
t
d
e
t
e
c
t
i
o
n
,
c
o
r
r
e
c
t
i
o
n
a
n
d
c
h
a
r
a
c
t
e
r
i
s
a
t
i
o
n
i
n
I
l
l
u
m
i
n
a
H
u
m
a
n
M
e
t
h
y
l
a
t
i
o
n
4
5
0
a
n
d
M
e
t
h
y
l
a
t
i
o
n
EPI
C
B
e
a
d
C
h
i
p
a
r
r
a
y
d
a
t
a
,
”
C
l
i
n
i
c
a
l
Ep
i
g
e
n
e
t
i
c
s
,
v
o
l
.
1
4
,
n
o
.
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
1
4
8
-
022
-
0
1
2
7
7
-
9.
[
2
3
]
K
.
D
a
s
h
d
o
n
d
o
v
a
n
d
M
.
-
H
.
K
i
m,
“
M
a
h
a
l
a
n
o
b
i
s
d
i
s
t
a
n
c
e
b
a
se
d
m
u
l
t
i
v
a
r
i
a
t
e
o
u
t
l
i
e
r
d
e
t
e
c
t
i
o
n
t
o
i
m
p
r
o
v
e
p
e
r
f
o
r
ma
n
c
e
o
f
h
y
p
e
r
t
e
n
si
o
n
p
r
e
d
i
c
t
i
o
n
,
”
N
e
u
r
a
l
Pr
o
c
e
ssi
n
g
L
e
t
t
e
rs
,
v
o
l
.
5
5
,
n
o
.
1
,
p
p
.
2
6
5
–
2
7
7
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
6
3
-
0
2
1
-
1
0
6
6
3
-
y.
[
2
4
]
Y
.
L
i
,
X
.
G
e
,
F
.
P
e
n
g
,
W
.
Li
,
a
n
d
J.
J.
L
i
,
“
E
x
a
g
g
e
r
a
t
e
d
f
a
l
s
e
p
o
s
i
t
i
v
e
s b
y
p
o
p
u
l
a
r
d
i
f
f
e
r
e
n
t
i
a
l
e
x
p
r
e
ss
i
o
n
me
t
h
o
d
s
w
h
e
n
a
n
a
l
y
z
i
n
g
h
u
m
a
n
p
o
p
u
l
a
t
i
o
n
sa
mp
l
e
s
,
”
G
e
n
o
m
e
Bi
o
l
o
g
y
,
v
o
l
.
2
3
,
n
o
.
1
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
3
0
5
9
-
022
-
0
2
6
4
8
-
4.
[
2
5
]
O
.
M
e
n
y
h
a
r
t
,
B
.
W
e
l
t
z
,
a
n
d
B
.
G
y
ő
r
f
f
y
,
“
M
u
l
t
i
p
l
e
T
e
st
i
n
g
.
c
o
m:
a
t
o
o
l
f
o
r
l
i
f
e
s
c
i
e
n
c
e
r
e
sea
r
c
h
e
r
s
f
o
r
mu
l
t
i
p
l
e
h
y
p
o
t
h
e
si
s
t
e
s
t
i
n
g
c
o
r
r
e
c
t
i
o
n
,
”
PLO
S
O
N
E
,
v
o
l
.
1
6
,
n
o
.
6
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
4
5
8
2
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
7
0
3
-
4
7
1
0
4710
[
2
6
]
R
.
H
y
d
e
,
L
.
O
’
G
r
a
d
y
,
a
n
d
M
.
G
r
e
e
n
,
“
S
t
a
b
i
l
i
t
y
s
e
l
e
c
t
i
o
n
f
o
r
m
i
x
e
d
e
f
f
e
c
t
mo
d
e
l
s
w
i
t
h
l
a
r
g
e
n
u
m
b
e
r
s
o
f
p
r
e
d
i
c
t
o
r
v
a
r
i
a
b
l
e
s
:
a
si
mu
l
a
t
i
o
n
st
u
d
y
,
”
Pre
v
e
n
t
i
v
e
Ve
t
e
r
i
n
a
ry
Me
d
i
c
i
n
e
,
v
o
l
.
2
0
6
,
p
.
1
0
5
7
1
4
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
e
v
e
t
m
e
d
.
2
0
2
2
.
1
0
5
7
1
4
.
[
2
7
]
O
.
A
.
M
.
S
a
l
e
m,
F
.
Li
u
,
Y
.
-
P
.
P
.
C
h
e
n
,
A
.
H
a
me
d
,
a
n
d
X
.
C
h
e
n
,
“
F
u
z
z
y
j
o
i
n
t
m
u
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
b
a
s
e
d
o
n
i
d
e
a
l
v
e
c
t
o
r
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
9
3
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
1
.
1
1
6
4
5
3
.
[
2
8
]
Y
.
Ta
n
g
a
n
d
A
.
H
o
f
f
ma
n
n
,
“
Q
u
a
n
t
i
f
y
i
n
g
i
n
f
o
r
m
a
t
i
o
n
o
f
i
n
t
r
a
c
e
l
l
u
l
a
r
s
i
g
n
a
l
i
n
g
:
p
r
o
g
r
e
ss
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Re
p
o
r
t
s
o
n
Pro
g
ress
i
n
P
h
y
s
i
c
s
,
v
o
l
.
8
5
,
n
o
.
8
,
p
.
0
8
6
6
0
2
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
8
/
1
3
6
1
-
6
6
3
3
/
a
c
7
a
4
a
.
[
2
9
]
S
.
C
h
e
n
a
n
d
W
.
G
u
o
,
“
A
u
t
o
-
e
n
c
o
d
e
r
s
i
n
d
e
e
p
l
e
a
r
n
i
n
g
—
a
r
e
v
i
e
w
w
i
t
h
n
e
w
p
e
r
sp
e
c
t
i
v
e
s
,
”
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
mat
h
1
1
0
8
1
7
7
7
.
[
3
0
]
K
.
N
.
R
a
o
,
K
.
V
.
R
a
o
,
a
n
d
P
.
R
.
P
.
V
.
G
.
D
.
,
“
A
h
y
b
r
i
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
b
a
se
d
o
n
s
p
a
r
se
a
u
t
o
e
n
c
o
d
e
r
a
n
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
C
o
m
p
u
t
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
0
,
p
p
.
7
7
–
8
8
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mc
o
m.
2
0
2
1
.
0
8
.
0
2
6
.
[
3
1
]
M
.
J
a
me
i
,
I
.
A
.
O
l
u
me
g
b
o
n
,
M
.
K
a
r
b
a
s
i
,
I
.
A
h
ma
d
i
a
n
f
a
r
,
A
.
A
sa
d
i
,
a
n
d
M
.
M
.
-
D
e
h
k
o
r
d
i
,
“
O
n
t
h
e
t
h
e
r
mal
c
o
n
d
u
c
t
i
v
i
t
y
a
ssessm
e
n
t
o
f
o
i
l
-
b
a
s
e
d
h
y
b
r
i
d
n
a
n
o
f
l
u
i
d
s
u
s
i
n
g
e
x
t
e
n
d
e
d
K
a
l
ma
n
f
i
l
t
e
r
i
n
t
e
g
r
a
t
e
d
w
i
t
h
f
e
e
d
-
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
H
e
a
t
a
n
d
M
a
ss Tra
n
sf
e
r
,
v
o
l
.
1
7
2
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
h
e
a
t
mass
t
r
a
n
sf
e
r
.
2
0
2
1
.
1
2
1
1
5
9
.
[
3
2
]
B
.
O
l
i
m
o
v
,
S
.
K
a
r
s
h
i
e
v
,
E.
Ja
n
g
,
S
.
D
i
n
,
A
.
P
a
u
l
,
a
n
d
J
.
K
i
m,
“
W
e
i
g
h
t
i
n
i
t
i
a
l
i
z
a
t
i
o
n
b
a
se
d
‐
r
e
c
t
i
f
i
e
d
l
i
n
e
a
r
u
n
i
t
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
t
o
i
m
p
r
o
v
e
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
a
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
,
”
C
o
n
c
u
rr
e
n
c
y
a
n
d
C
o
m
p
u
t
a
t
i
o
n
:
Pra
c
t
i
c
e
a
n
d
E
x
p
e
r
i
e
n
c
e
,
v
o
l
.
3
3
,
n
o
.
2
2
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
c
p
e
.
6
1
4
3
.
[
3
3
]
Z.
N
i
u
,
G
.
Z
h
o
n
g
,
a
n
d
H
.
Y
u
,
“
A
r
e
v
i
e
w
o
n
t
h
e
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
o
f
d
e
e
p
l
e
a
r
n
i
n
g
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
5
2
,
p
p
.
4
8
–
6
2
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
2
1
.
0
3
.
0
9
1
.
[
3
4
]
R
.
O
.
O
g
u
n
d
o
k
u
n
,
R
.
M
a
sk
e
l
i
u
n
a
s
,
S
.
M
i
sr
a
,
a
n
d
R
.
D
a
ma
še
v
i
č
i
u
s,
“
I
mp
r
o
v
e
d
C
N
N
b
a
s
e
d
o
n
b
a
t
c
h
n
o
r
ma
l
i
z
a
t
i
o
n
a
n
d
A
d
a
m
o
p
t
i
m
i
z
e
r
,
”
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
a
n
d
I
t
s
A
p
p
l
i
c
a
t
i
o
n
s
–
I
C
C
S
A
2
0
2
2
Wo
r
k
sh
o
p
s
,
S
p
r
i
n
g
e
r
,
C
h
a
m,
2
0
2
2
,
p
p
.
5
9
3
–
604
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
1
0
5
4
8
-
7
_
4
3
.
[
3
5
]
L
.
Y
a
n
g
,
Y
.
-
H
.
Z
h
a
n
g
,
F
.
H
u
a
n
g
,
Z
.
L
i
,
T
.
H
u
a
n
g
,
a
n
d
Y
.
-
D
.
C
a
i
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
r
o
t
e
i
n
–
p
r
o
t
e
i
n
i
n
t
e
r
a
c
t
i
o
n
a
s
s
o
c
i
a
t
e
d
f
u
n
c
t
i
o
n
s
b
a
s
e
d
o
n
g
e
n
e
o
n
t
o
l
o
g
y
a
n
d
K
E
G
G
p
a
t
h
w
a
y
,
”
F
r
o
n
t
i
e
r
s
i
n
G
e
n
e
t
i
c
s
,
v
o
l
.
1
3
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
g
e
n
e
.
2
0
2
2
.
1
0
1
1
6
5
9
.
[
3
6
]
S
.
A
.
A
l
e
k
sa
n
d
e
r
e
t
a
l
.
,
“
T
h
e
g
e
n
e
o
n
t
o
l
o
g
y
k
n
o
w
l
e
d
g
e
b
a
s
e
i
n
2
0
2
3
,
”
G
e
n
e
t
i
c
s
,
v
o
l
.
2
2
4
,
n
o
.
1
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
9
3
/
g
e
n
e
t
i
c
s
/
i
y
a
d
0
3
1
.
[
3
7
]
B
.
T
.
S
h
e
r
ma
n
e
t
a
l
.
,
“
D
A
V
I
D
:
a
w
e
b
s
e
r
v
e
r
f
o
r
f
u
n
c
t
i
o
n
a
l
e
n
r
i
c
h
me
n
t
a
n
a
l
y
si
s
a
n
d
f
u
n
c
t
i
o
n
a
l
a
n
n
o
t
a
t
i
o
n
o
f
g
e
n
e
l
i
s
t
s
(
2
0
2
1
u
p
d
a
t
e
)
,
”
N
u
c
l
e
i
c
A
c
i
d
s R
e
se
a
rc
h
,
v
o
l
.
5
0
,
n
o
.
W
1
,
p
p
.
W
2
1
6
–
W
2
2
1
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
9
3
/
n
a
r
/
g
k
a
c
1
9
4
.
[
3
8
]
Z.
X
i
e
e
t
a
l
.
,
“
G
e
n
e
s
e
t
k
n
o
w
l
e
d
g
e
d
i
s
c
o
v
e
r
y
w
i
t
h
e
n
r
i
c
h
r
,
”
C
u
rr
e
n
t
P
ro
t
o
c
o
l
s
,
v
o
l
.
1
,
n
o
.
3
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
c
p
z
1
.
9
0
.
[
3
9
]
J.
M
i
a
o
a
n
d
W
.
Z
h
u
,
“
P
r
e
c
i
s
i
o
n
–
r
e
c
a
l
l
c
u
r
v
e
(
P
R
C
)
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
r
e
e
s
,
”
Ev
o
l
u
t
i
o
n
a
ry
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
1
5
4
5
–
1
5
6
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
0
6
5
-
021
-
0
0
5
6
5
-
2.
[
4
0
]
Z.
L
i
,
F
.
Q
i
,
a
n
d
F
.
Li
,
“
Est
a
b
l
i
s
h
men
t
o
f
a
g
e
n
e
s
i
g
n
a
t
u
r
e
t
o
p
r
e
d
i
c
t
p
r
o
g
n
o
s
i
s
f
o
r
p
a
t
i
e
n
t
s
w
i
t
h
l
u
n
g
a
d
e
n
o
c
a
r
c
i
n
o
m
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
o
l
e
c
u
l
a
r
S
c
i
e
n
c
e
s
,
v
o
l
.
2
1
,
n
o
.
2
2
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
ms2
1
2
2
8
4
7
9
.
[
4
1
]
Q
.
Zh
e
n
g
,
S
.
M
i
n
,
a
n
d
Q
.
Z
h
o
u
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
o
t
e
n
t
i
a
l
d
i
a
g
n
o
s
t
i
c
a
n
d
p
r
o
g
n
o
s
t
i
c
b
i
o
m
a
r
k
e
r
s
f
o
r
LU
A
D
b
a
sed
o
n
T
C
G
A
a
n
d
G
EO
d
a
t
a
b
a
s
e
s,
”
B
i
o
s
c
i
e
n
c
e
Re
p
o
rt
s
,
v
o
l
.
4
1
,
n
o
.
6
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
4
2
/
B
S
R
2
0
2
0
4
3
7
0
.
[
4
2
]
M
.
S
h
e
r
a
f
a
t
i
a
n
a
n
d
F
.
A
r
j
ma
n
d
,
“
D
e
c
i
si
o
n
t
r
e
e
‑
b
a
s
e
d
c
l
a
ss
i
f
i
e
r
s
f
o
r
l
u
n
g
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
a
n
d
su
b
t
y
p
i
n
g
u
si
n
g
TC
G
A
mi
R
N
A
e
x
p
r
e
ss
i
o
n
d
a
t
a
,
”
O
n
c
o
l
o
g
y
L
e
t
t
e
rs
,
v
o
l
.
1
8
,
n
o
.
2
,
p
p
.
2
1
2
5
–
2
1
3
1
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
3
8
9
2
/
o
l
.
2
0
1
9
.
1
0
4
6
2
.
[
4
3
]
P
.
R
a
n
a
,
P
.
T
h
a
i
,
T.
D
i
n
h
,
a
n
d
P
.
G
h
o
s
h
,
“
R
e
l
e
v
a
n
t
a
n
d
non
-
r
e
d
u
n
d
a
n
t
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
f
o
r
c
a
n
c
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
s
u
b
t
y
p
e
d
e
t
e
c
t
i
o
n
,
”
C
a
n
c
e
rs
,
v
o
l
.
1
3
,
n
o
.
1
7
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
c
a
n
c
e
r
s1
3
1
7
4
2
9
7
.
[
4
4
]
J.
W
e
i
,
X
.
W
a
n
g
,
H
.
G
u
o
,
L
.
Z
h
a
n
g
,
Y
.
S
h
i
,
a
n
d
X
.
W
a
n
g
,
“
S
u
b
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
l
u
n
g
a
d
e
n
o
c
a
r
c
i
n
o
ma
t
h
r
o
u
g
h
c
o
mp
r
e
h
e
n
s
i
v
e
mu
l
t
i
-
o
mi
c
s
d
a
t
a
t
o
b
e
n
e
f
i
t
su
r
v
i
v
a
l
o
u
t
c
o
mes,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
Bi
o
l
o
g
y
a
n
d
C
h
e
m
i
st
r
y
,
v
o
l
.
1
1
2
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
l
c
h
e
m
.
2
0
2
4
.
1
0
8
1
5
0
.
B
I
O
G
R
A
P
H
I
E
S
O
F
AU
T
H
O
R
S
S
a
r
a
H
a
d
d
o
u
Bo
u
a
z
z
a
h
o
l
d
s
a
D
o
c
to
ra
te
i
n
E
lec
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
In
fo
rm
a
ti
c
s,
a
s
we
ll
a
s
a
M
a
st
e
r'
s
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
fr
o
m
Ca
d
i
Ay
y
a
d
Un
i
v
e
rsity
,
M
a
rra
k
e
c
h
.
S
h
e
a
lso
c
o
m
p
lete
d
h
e
r
Ba
c
h
e
lo
r'
s
in
P
h
y
sic
a
l
S
c
ien
c
e
s.
Cu
rre
n
tl
y
,
sh
e
is
a
P
ro
fe
ss
o
r
a
n
d
Re
se
a
rc
h
e
r
a
t
th
e
L
AMIG
EP
lab
o
ra
to
ry
,
EM
S
I
M
a
rra
k
e
c
h
.
He
r
re
se
a
rc
h
in
c
lu
d
e
s
AI
tec
h
n
iq
u
e
s
fo
r
c
a
n
c
e
r
c
las
sifica
ti
o
n
,
g
e
n
e
e
x
p
re
ss
io
n
a
n
a
l
y
sis,
a
n
d
se
c
u
rit
y
c
h
a
l
len
g
e
s
i
n
I
o
T
e
n
v
iro
n
m
e
n
ts.
S
h
e
h
a
s
p
u
b
li
sh
e
d
n
u
m
e
ro
u
s
p
a
p
e
rs,
in
c
lu
d
i
n
g
re
c
e
n
t
wo
r
k
o
n
leu
k
e
m
ia
c
las
sifica
ti
o
n
a
n
d
AI
in
CN
S
tu
m
o
rs.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
emai
l:
sa
ra
.
h
b
.
sa
ra
@g
m
a
il
.
c
o
m
.
J
ih
a
d
H
a
d
d
o
u
B
o
u
a
z
z
a
is
a
n
e
n
g
in
e
e
r
s
p
e
c
ializin
g
in
so
ftwa
re
e
n
g
i
n
e
e
rin
g
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
fro
m
IG
A
In
stit
u
t
S
u
p
é
rieu
r
d
u
G
é
n
ieA
p
p
li
q
u
é
,
M
a
rra
k
e
c
h
.
Cu
rre
n
tl
y
,
h
e
se
rv
e
s
a
s
a
se
n
io
r
fu
ll
sta
c
k
d
e
v
e
l
o
p
e
r
a
n
d
tec
h
lea
d
a
t
Ne
x
u
lar
Co
rp
.
He
is
c
e
rti
fied
in
P
y
t
h
o
n
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
a
s
a
c
e
rti
f
ied
n
e
two
rk
se
c
u
rit
y
sp
e
c
ialist
(CNSS
).
His
re
se
a
rc
h
in
c
lu
d
e
s
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
u
si
n
g
a
rti
fici
a
l
in
telli
g
e
n
c
e
,
wit
h
a
p
u
b
li
c
a
ti
o
n
p
re
se
n
ted
a
t
th
e
G
AST
2
4
c
o
n
g
re
ss
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
d
d
o
u
.
j
ih
a
d
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.