I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
A
I
)
V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024, pp.
4344
~
4351
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v13.i
4
.pp
4344
-
4351
4344
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
A
m
ac
h
i
n
e
l
e
ar
n
i
n
g
b
ase
d
f
r
am
e
w
or
k
f
or
b
r
e
ast
c
an
c
e
r
p
r
e
d
i
c
t
i
on
u
si
n
g
b
i
o
m
ar
k
e
r
s
A
p
u
r
va V
as
h
is
t
, A
n
il
K
u
m
ar
S
agar
, A
n
j
al
i
G
oyal
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
a
nd E
ngi
ne
e
r
i
ng, S
ha
r
da
U
ni
ve
r
s
i
t
y, G
r
e
a
t
e
r
N
oi
da
, I
ndi
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
N
ov
17
,
2023
R
e
vi
s
e
d
A
pr
3
,
2024
A
c
c
e
pt
e
d
A
pr
17
,
2024
Breast
cancer
is
the
most
frequent
cancer
in
women
and
the
second
-
l
eading
cause
of
cancer
-
related
deaths
globally.
The
main
problems
in
ma
naging
breast
cancer
are
high
heterogeneity
and
the
formation
of
ther
apeutic
resistance.
White
blood
cells,
omics
and
large
Wisconsin
diagnostic
breast
cancer
datasets
present
the
three
-
decade
genomic
revolution
and
adva
nce
the
understanding of cellular function. The
precision of cancer
diagnosis
h
as also
increase
d
over
the
past
decade
s.
High
throughput
sequencin
g,
screen
in
g,
and
artificial
intell
igence tech
nologi
es have
signi
ficantly
improv
ed
and inc
reased
the
methodologies
used
for
diagnosis,
prognosis,
and
therapy.
This
paper
follows
several
phases
of
breast
cancer,
studies
datasets
and
evaluate
many
algorit
hms
of
machi
ne
learning
(ML)
used
for
analysis
and
feature
se
lection
i.e.
k
-
means,
similarity
correlation,
genetic
algorithm
,
and
pr
incipal
component
analysis
,
have
been
used
to
recognize
the
subset
of
protei
ns
with
the
highest
significance
for
breast
cancer
predictio
n
by
using
di
fferent
biomarkers.
The
best
correlation,
as
determined
by
Pearson
corre
lation,
between copy number and pr
otein
is 0.014, and
the accuracy a
chieved
by the
genetic algorithm is 93.5% using multi
-
omics datasets.
K
e
y
w
o
r
ds
:
B
io
m
a
r
ke
r
s
B
r
e
a
s
t
c
a
n
c
e
r
pr
e
di
c
ti
on
F
e
a
tu
r
e
s
e
le
c
ti
on
G
e
ne
G
e
ne
ti
c
a
lg
or
it
hm
R
N
A
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
A
pur
va
V
a
s
hi
s
t
D
e
pa
r
tm
e
nt
of
C
om
put
e
r
S
c
ie
nc
e
a
nd E
ngi
ne
e
r
in
g, S
ha
r
da
U
ni
ve
r
s
it
y
G
r
e
a
te
r
N
oi
da
,
U
tt
a
r
P
r
a
de
s
h
,
I
ndi
a
E
m
a
il
:
a
pur
va
.va
s
hi
s
t@gma
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
B
r
e
a
s
t
c
a
n
c
e
r
(
B
C
)
is
th
e
m
os
t
w
e
ll
-
known
m
a
li
gna
nc
y
th
a
t
dr
a
s
ti
c
a
ll
y
r
e
duc
e
s
th
e
w
e
ll
ne
s
s
of
w
om
e
n
th
r
oughout
th
e
w
or
ld
[
1]
.
U
nc
e
r
ta
in
ty
s
ur
r
ounds
th
e
c
ont
r
ib
ut
io
n
of
e
xoge
nous
f
e
m
a
le
hor
m
one
s
to
th
e
e
m
e
r
ge
nc
e
of
B
C
.
B
C
r
is
k
in
c
r
e
a
s
e
s
f
ol
lo
w
in
g
m
e
nopa
us
e
.
A
c
c
or
di
ng
to
De
S
a
nt
is
e
t
al
.
[
2
]
,
B
C
ha
ppe
ns
to
a
ppr
oxi
m
a
te
ly
17
m
il
li
on
c
a
s
e
s
a
nnu
a
ll
y,
w
hi
c
h
is
a
w
or
r
yi
n
g
in
c
r
e
a
s
e
.
I
n
th
e
U
ni
te
d
S
ta
te
s
,
th
e
r
e
w
e
r
e
a
ppr
oxi
m
a
te
ly
268,600
ne
w
c
a
s
e
s
of
B
C
r
e
por
te
d
in
2019;
th
e
r
e
w
e
r
e
a
ls
o
41,760
r
e
por
te
d
f
a
ta
li
ti
e
s
[
3]
.
C
a
nc
e
r
di
a
gnos
is
h
a
s
i
m
pr
ove
d
ove
r
t
he
pa
s
t
f
e
w
de
c
a
de
s
.
T
e
c
hnol
ogy
f
or
hi
gh t
hr
oughput s
e
que
nc
in
g
a
nd
s
c
r
e
e
ni
ng,
a
s
w
e
ll
a
s
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
(
A
I
)
,
ha
ve
ha
d
a
s
ig
ni
f
ic
a
nt
pos
it
iv
e
im
pa
c
t
on
th
e
a
ppr
oa
c
he
s
us
e
d
f
or
di
a
gnos
is
,
pr
ognos
is
,
a
nd
th
e
r
a
py
.
A
s
th
e
to
p
r
e
a
s
on
of
de
a
th
f
or
w
om
e
n
in
in
dus
tr
ia
li
z
e
d
c
ount
r
ie
s
,
B
C
ha
s
e
xc
e
e
de
d
a
ll
ot
he
r
m
a
li
gna
nc
ie
s
[
4]
.
H
ow
e
ve
r
,
B
C
'
s
r
e
c
ur
r
e
nc
e
,
m
e
ta
s
ta
s
i
s
,
a
nd
qui
c
k
s
pr
e
a
d
ha
ve
not
ye
t
be
e
n
to
ta
ll
y
m
a
na
ge
d
a
nd
ha
ve
be
c
om
e
a
m
a
jo
r
c
ha
ll
e
ng
e
f
or
c
li
ni
c
a
l
m
a
na
ge
m
e
nt
.
S
o,
it
is
im
pe
r
a
ti
ve
to
lo
ok
f
o
r
m
or
e
r
e
li
a
bl
e
pr
ognos
ti
c
bi
om
a
r
ke
r
s
a
s
pr
os
pe
c
ti
ve
ta
r
ge
ts
to
c
om
pr
e
he
nd
pr
oba
bl
e
pa
th
w
a
ys
,
e
nha
nc
e
th
e
r
a
pe
ut
ic
e
f
f
e
c
ti
ve
ne
s
s
,
a
nd
d
e
c
r
e
a
s
e
di
s
ta
nt
m
e
ta
s
ta
s
is
,
a
ll
o
f
w
hi
c
h
w
il
l
in
c
r
e
a
s
e
th
e
s
ur
vi
va
l
r
a
te
.
M
a
ny
bi
om
a
r
ke
r
s
ha
ve
be
e
n us
e
d t
o da
te
f
or
s
c
r
e
e
ni
ng, dia
gno
s
in
g, a
nd ke
e
pi
ng t
r
a
c
k of
B
C
r
e
c
ur
r
e
nc
e
.
B
io
m
a
r
ke
r
s
a
r
e
m
ol
e
c
ul
e
s
th
a
t
in
di
c
a
te
w
h
e
th
e
r
a
phys
io
l
ogi
c
a
l
a
c
ti
vi
ty
oc
c
ur
s
nor
m
a
ll
y
or
a
bnor
m
a
ll
y.
T
he
y
c
a
n
a
l
s
o
be
s
ig
ns
of
a
n
unde
r
ly
in
g
c
ondi
t
io
n
or
il
ln
e
s
s
.
D
if
f
e
r
e
nt
ty
pe
s
of
m
ol
e
c
ul
e
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
m
ac
hi
ne
l
e
ar
ni
ng bas
e
d f
r
am
e
w
o
r
k
f
or
b
r
e
as
t
c
an
c
e
r
p
r
e
di
c
ti
on us
in
g bi
om
ar
k
e
r
s
(
A
pur
v
a V
as
hi
s
t)
4345
in
c
lu
di
ng
R
N
A
(
m
iR
N
A
a
nd
m
R
N
A
)
,
hor
m
one
s
,
pr
ot
e
in
s
,
a
nd
D
N
A
(
ge
ne
s
)
,
c
a
n
a
c
t
a
s
bi
om
a
r
ke
r
s
.
B
io
m
a
r
ke
r
s
a
r
e
di
s
c
ove
r
e
d
to
di
s
ti
ngui
s
h
c
a
nc
e
r
vi
a
knowle
dge
-
ba
s
e
d
ge
ne
s
e
le
c
ti
on,
ge
ne
e
xpr
e
s
s
io
n
pr
of
il
in
g,
o
r
pr
o
te
in
pr
of
il
in
g.
T
he
r
e
a
r
e
va
r
io
us
f
a
c
to
r
s
t
ha
t
c
on
tr
ib
ut
e
to
B
C
,
th
e
m
a
jo
r
it
y
im
p
ly
a
lt
e
r
a
ti
ons
in
th
e
e
xpr
e
s
s
io
n
of
ge
n
e
s
,
li
ke
m
ic
r
oR
N
A
s
(
m
iR
N
A
s
)
.
m
iR
N
A
s
c
a
n
r
e
gul
a
te
s
ig
na
li
ng
p
a
th
w
a
ys
,
w
hi
c
h
h
a
s
a
n
im
pa
c
t
on
c
a
r
c
in
oge
ne
s
is
a
nd
ot
he
r
a
s
pe
c
ts
of
c
a
nc
e
r
pr
ogr
e
s
s
io
n
[
5]
.
N
um
e
r
ous
bi
om
a
r
ke
r
s
ha
ve
be
e
n
e
m
pl
oye
d
in
th
e
de
te
c
ti
on,
pr
e
di
c
ti
on,
di
a
gnos
is
,
a
nd
m
oni
to
r
in
g
of
B
C
r
e
c
ur
r
e
nc
e
.
F
or
in
s
ta
nc
e
,
hum
a
n
e
pi
de
r
m
a
l
gr
ow
th
f
a
c
to
r
r
e
c
e
pt
or
2
(
H
E
R
2)
,
w
hi
c
h
w
a
s
di
s
c
ov
e
r
e
d
a
s
a
pr
e
di
c
to
r
of
poor
pr
ognos
is
25
y
e
a
r
s
a
go
[
6]
, i
s
ove
r
e
xpr
e
s
s
e
d i
n 15%
o
f
B
C
pa
ti
e
nt
s
. A
c
r
uc
ia
l
c
e
ll
pr
ol
if
e
r
a
ti
on
-
r
e
la
te
d bi
om
a
r
ke
r
c
a
ll
e
d a
nt
ig
e
n
KI
-
67, whic
h i
s
e
nc
ode
d by the
M
K
I
67 ge
ne
, ha
s
be
e
n e
m
pl
oy
e
d i
n c
li
ni
c
a
l
s
e
tt
in
gs
a
s
a
pr
e
di
c
ti
ve
i
ndi
c
a
ti
on
of
t
um
or
r
e
c
ur
r
e
nc
e
a
nd c
li
ni
c
a
l
pr
ognos
is
[
7]
.
F
ur
th
e
r
m
or
e
,
c
o
-
tr
a
ns
c
r
ip
ti
ona
l
r
e
gul
a
to
r
m
iR
N
A
s
in
B
C
a
r
e
e
xpe
c
te
d
to
in
te
r
a
c
t
w
it
h
th
e
ir
ta
r
ge
t
m
R
N
A
s
in
bot
h
f
a
vor
a
bl
e
a
nd
unf
a
vor
a
bl
e
w
a
ys
.
m
iR
-
1307
-
3
p,
m
iR
-
940,
a
nd
m
iR
-
340
-
3
p
w
e
r
e
f
ound
to
ha
ve
ne
ga
ti
ve
e
f
f
e
c
ts
on
ov
e
r
a
ll
s
ur
vi
va
l
in
B
C
pa
ti
e
nt
s
[
8]
.
T
he
hs
a
-
miR
-
503,
hs
a
-
miR
-
1307,
hs
a
-
miR
-
212,
a
nd
hs
a
-
miR
-
592
e
xpr
e
s
s
io
n
c
ha
nge
s
a
r
e
s
ig
ni
f
ic
a
nt
ly
c
or
r
e
la
te
d
w
it
h
B
C
pr
ognos
is
[
1]
.
D
ue
to
th
e
la
c
k
o
f
c
ons
is
te
nc
y,
th
e
a
ppr
oxi
m
a
ti
on
of
K
I
-
67
a
nd
th
e
s
e
m
i
R
N
A
s
in
B
C
ha
s
not
ye
t
b
e
e
n
w
id
e
ly
us
e
d
a
s
a
bi
om
a
r
ke
r
in
th
e
c
li
ni
c
.
S
o,
to
in
c
r
e
a
s
e
th
e
pr
e
c
is
io
n
of
B
C
di
a
gnos
i
s
,
m
or
e
pr
e
c
is
e
bi
om
a
r
ke
r
s
m
u
s
t
be
f
ound.
W
e
ha
ve
e
m
pha
s
iz
e
d
th
e
va
lu
e
of
om
ic
s
da
ta
s
e
ts
a
nd
bi
ol
ogi
c
a
l
in
f
or
m
a
ti
on
f
or
e
nha
nc
in
g
th
e
pr
e
di
c
ti
ve
c
a
pa
c
it
y
of
va
r
io
us
m
a
c
hi
ne
le
a
r
ni
ng
(
M
L
)
m
e
th
ods
.
A
ls
o,
th
e
b
e
ne
f
it
s
of
M
L
in
m
e
ta
bol
ic
a
ppl
ic
a
ti
ons
li
ke
pr
ot
e
in
e
ngi
ne
e
r
in
g,
de
s
ig
ni
ng
ge
ne
c
ir
c
ui
ts
a
nd
pa
th
w
a
ys
,
a
nd
opt
im
iz
in
g
bi
opr
oc
e
s
s
e
s
a
r
e
pr
e
s
e
nt
e
d.
T
he
c
ha
ll
e
nge
s
of
de
ve
lo
pi
ng
M
L
te
c
hni
que
s
f
or
gr
ow
in
g
de
s
ig
ne
r
m
ic
r
obe
s
w
it
h
e
nh
a
nc
e
d
pr
oduc
ti
on
h
a
ve
a
l
s
o
be
e
n
e
m
pha
s
iz
e
d.
2.
L
I
T
E
R
A
T
U
R
E
R
E
V
I
E
W
A
th
or
ough
a
s
s
e
s
s
m
e
nt
of
th
e
li
te
r
a
tu
r
e
on
B
C
pr
e
di
c
ti
on
is
p
r
e
s
e
nt
e
d
in
th
i
s
s
e
c
ti
on.
T
hi
s
s
e
c
ti
on
s
ur
ve
ye
d
28
p
a
pe
r
s
publ
i
s
he
d
in
s
im
il
a
r
dom
a
in
.
T
a
ghi
z
a
d
e
h
e
t
al
.
[
5]
us
e
d
762
B
C
pa
ti
e
nt
s
a
nd
138
s
ol
id
ti
s
s
ue
nor
m
a
l
pa
r
ti
c
ip
a
nt
s
to
in
ve
s
ti
ga
te
r
e
le
v
a
nt
B
C
c
ha
r
a
c
te
r
is
ti
c
s
.
T
he
r
e
w
e
r
e
th
r
e
e
c
a
te
gor
ie
s
of
M
L
a
lg
or
it
hm
s
be
in
g
us
e
d:
f
e
a
tu
r
e
s
e
le
c
ti
on
te
c
hni
que
s
,
f
e
a
tu
r
e
e
xt
r
a
c
ti
on
a
ppr
oa
c
h:
pr
in
c
ip
a
l
c
om
pone
nt
a
na
ly
s
is
(
P
C
A
)
,
13
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
a
lo
ng
w
it
h
a
ut
om
a
t
e
d
M
L
hype
r
pa
r
a
m
e
te
r
a
dj
us
tm
e
nt
.
A
yool
a
a
nd
O
gunf
unm
i
[
9]
f
ound a
m
ode
l
th
a
t
is
m
os
t
s
ui
te
d f
o
r
f
o
r
e
c
a
s
ti
ng t
ype
of
t
um
o
r
c
e
ll
.
G
e
ne
ti
c
a
lg
or
it
hm
i
s
us
e
d
to
c
hoos
e
th
e
s
ubc
a
te
gor
ie
s
of
in
put
f
e
a
tu
r
e
s
th
a
t
a
r
e
m
os
t
pe
r
ti
ne
nt
to
th
e
ta
r
ge
t
va
r
ia
bl
e
on
th
e
W
is
c
ons
in
B
C
da
ta
s
e
t.
5
M
L
r
e
gr
e
s
s
io
n
c
l
a
s
s
if
ie
r
s
w
e
r
e
c
om
p
a
r
e
d
in
c
lu
di
ng
s
uppor
t
ve
c
to
r
r
e
gr
e
s
s
io
n,
lo
gi
s
ti
c
r
e
gr
e
s
s
io
n
(
L
R
)
, r
a
ndom f
o
r
e
s
t
(
R
F
)
, a
nd de
c
is
io
n t
r
e
e
s
(
D
T
)
.
I
n
a
c
c
or
da
nc
e
w
it
h
r
e
c
e
nt
r
e
s
e
a
r
c
h
by
N
oui
r
a
e
t
al
.
[
10]
th
e
pe
r
f
or
m
a
nc
e
of
c
la
s
s
if
ie
r
s
c
a
n
be
im
pr
ove
d
by
r
e
m
ovi
ng
noi
s
e
a
nd
uni
m
por
ta
nt
da
ta
dur
in
g
da
ta
pr
e
pa
r
a
ti
on
us
in
g
a
f
e
a
tu
r
e
s
e
le
c
ti
on
s
tr
a
te
gy,
s
uc
h
a
s
th
e
ge
ne
ti
c
a
lg
or
it
hm
.
T
he
c
om
pa
r
a
ti
ve
ly
hi
gh
a
c
c
ur
a
c
y
of
s
om
e
M
L
r
e
gr
e
s
s
io
n
a
ppr
oa
c
he
s
w
a
s
a
l
s
o
hi
ghl
ig
ht
e
d
a
s
a
r
e
s
ul
t.
I
n
th
is
w
or
k,
m
R
N
A
g
e
ne
e
xpr
e
s
s
io
n
da
ta
w
e
r
e
s
ubj
e
c
te
d
to
s
e
ve
r
a
l
f
e
a
tu
r
e
s
e
le
c
ti
on/
c
ol
le
c
ti
on mode
ls
e
s
ta
bl
is
h
e
d f
or
c
a
nc
e
r
c
la
s
s
if
ic
a
ti
on a
nd me
di
c
a
l
out
c
om
e
pr
e
di
c
ti
on.
R
e
s
e
a
r
c
h by
A
lc
udi
a
a
nd
R
odr
ig
ue
s
[
11]
,
hybr
id
bi
oi
ns
pi
r
e
d
m
ode
ls
-
ba
s
e
d
a
lg
or
it
hm
s
ha
ve
be
e
n
de
v
e
lo
pe
d
to
c
hoos
e
a
s
e
le
c
ti
on
of
r
e
le
va
nt
ge
n
e
s
w
it
h
c
a
nc
e
r
pr
e
di
c
ti
on
pe
r
f
or
m
a
nc
e
r
e
le
va
nc
y.
I
t
bl
e
nds
in
s
tr
uc
ti
ona
l
m
ode
l
s
w
it
h
a
n
a
r
ti
f
ic
ia
l
be
e
c
ol
ony
(
A
B
C
)
,
f
ir
s
t
us
in
g
a
r
a
nki
ng
a
ppr
oa
c
h
to
c
on
de
ns
e
th
e
a
v
a
il
a
bl
e
s
pa
c
e
a
nd
th
e
n
us
in
g
A
B
C
t
o s
e
le
c
t
th
e
m
os
t
r
e
le
va
nt
ge
n
e
s
ubs
e
t.
Z
e
nbout
e
t
al
.
[
12]
us
e
s
th
e
pr
ot
e
in
-
pr
ot
e
in
in
te
r
a
c
ti
on
(
P
P
I
)
f
or
c
or
r
e
la
ti
ng
pr
ot
e
om
ic
s
a
nd
th
e
c
lu
s
te
r
-
ba
s
e
d
gr
e
y
w
ol
f
opt
im
iz
a
ti
on
a
lg
o
r
it
hm
(
C
B
-
G
W
O
)
m
e
th
o
d
f
or
f
e
a
tu
r
e
s
e
le
c
ti
on.
T
o
f
or
e
c
a
s
t
c
li
ni
c
a
l
out
c
om
e
s
,
us
e
a
de
e
p
s
ta
c
ke
d
c
a
noni
c
a
l
r
e
la
ti
ons
hi
p
a
ut
o
e
nc
ode
r
.
F
or
f
e
a
tu
r
e
s
e
le
c
ti
on,
a
C
B
-
G
W
O
a
nd
a
de
e
p
s
ta
c
ke
d
c
a
noni
c
a
l
c
or
r
e
la
ti
on
a
ut
oe
nc
od
e
r
(
D
S
C
C
-
A
E
)
f
or
c
li
ni
c
a
l
e
ndpoint
pr
e
di
c
ti
on
a
r
e
th
e
e
s
s
e
nt
ia
l
c
om
pone
nt
s
of
th
is
de
s
ig
n.
I
s
ik
a
nd
E
r
c
a
n
[
13]
e
m
pl
oye
d
th
e
P
P
I
s
ys
te
m
to
f
in
d
th
e
m
a
xi
m
um
a
s
s
oc
ia
te
d
pr
ot
e
in
s
a
nd
th
e
c
odi
ng
ge
ne
s
of
th
os
e
pr
ot
e
in
s
to
p
r
e
di
c
t
th
e
m
e
di
c
a
l
out
c
om
e
s
of
pa
ti
e
nt
s
,
s
e
r
ve
d
a
s
th
e
ba
s
is
f
or
our
r
e
ve
r
s
e
pha
s
e
pr
ot
e
in
a
r
r
a
y
(
R
P
P
A
)
-
ba
s
e
d
om
ic
s
bi
om
a
r
ke
r
id
e
nt
if
ic
a
ti
on
m
e
th
od.
2018
put
s
pe
c
i
a
l
e
m
pha
s
is
on
th
e
M
L
m
ode
l'
s
c
l
a
s
s
if
ic
a
ti
on
te
c
hni
que
f
or
c
a
nc
e
r
pr
e
di
c
ti
on.
T
he
y
f
ound
good
a
c
c
ur
a
c
y
us
in
g
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
s
,
li
ne
a
r
r
e
gr
e
s
s
io
n,
a
nd
k
-
ne
a
r
e
s
t
ne
ig
h
bor
s
(
KNN
)
on
th
e
W
is
c
ons
in
B
C
da
ta
s
e
t.
D
a
ta
s
our
c
e
,
da
ta
c
om
pr
e
he
ns
i
on
a
nd
pr
e
pa
r
a
ti
on,
f
e
a
tu
r
e
tr
a
in
in
g
a
nd
s
e
le
c
ti
on,
a
nd
c
la
s
s
if
ic
a
ti
on
m
e
th
odol
ogy
a
ppl
ie
d.
T
hr
ough
B
C
s
ur
vi
va
l
pr
e
di
c
ti
on
ba
s
e
d
on
pa
th
w
a
y
a
c
ti
vi
ty
in
f
e
r
e
nc
e
,
K
im
a
nd
T
a
gkopoulos
[
14]
e
xpl
or
e
d
bi
ol
ogi
c
a
l
m
e
th
ods
a
nd
im
pl
ic
a
ti
ons
of
le
a
r
nt
f
e
a
tu
r
e
s
.
O
m
ic
s
da
ta
s
e
t
s
e
r
ve
d
a
s
a
n
in
s
pi
r
a
ti
on
f
or
th
is
e
f
f
or
t.
R
e
c
e
nt
de
c
a
de
s
ha
ve
s
e
e
n
a
th
or
ough
in
ve
s
ti
ga
ti
on
of
num
e
r
ous
a
r
ti
f
ic
ia
ll
y
a
s
s
is
te
d
s
ys
te
m
s
f
or
c
a
nc
e
r
a
na
ly
s
is
,
w
h
e
th
e
r
th
r
ough
om
ic
s
da
ta
a
na
ly
s
i
s
[
15]
or
m
e
di
c
a
l
im
a
ge
a
na
ly
s
i
s
.
N
um
e
r
ous
s
tu
di
e
s
ha
ve
a
l
s
o
be
e
n
c
onduc
t
e
d
to
in
c
or
por
a
te
om
ic
s
da
ta
to
bui
ld
m
ode
ls
th
a
t
c
a
n
pr
e
di
c
t
m
e
di
c
a
l
out
c
om
e
s
a
nd
e
nha
nc
e
c
a
nc
e
r
-
r
e
la
te
d
m
e
di
c
a
l
d
e
c
is
io
ns
B
is
w
a
s
a
nd
C
ha
kr
a
ba
r
ti
[
16]
.
T
he
in
te
gr
a
ti
ve
f
r
a
m
e
w
or
k
pr
e
s
e
nt
e
d
in
th
is
pa
pe
r
ge
ne
r
a
te
s
a
f
in
di
ng
m
ode
l
bui
lt
on
a
bi
oi
ns
pi
r
e
d
f
e
a
tu
r
e
c
hoi
c
e
m
e
th
od,
a
lo
ng
w
it
h
tr
a
in
e
d
M
L
m
ode
ls
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024:
4344
-
4351
4346
th
a
t
c
oul
d be
us
e
d
a
s
c
a
n
c
e
r
pr
e
di
c
ti
on t
ool
s
.
T
a
bl
e
1
pr
e
s
e
nt
s
a
n ove
r
vi
e
w
of
pa
s
t
s
tu
di
e
s
i
n t
he
br
oa
d
doma
in
of
B
C
pr
e
di
c
ti
on us
in
g M
L
t
e
c
hni
que
s
.
T
a
bl
e
1. C
om
pa
r
is
on of
M
L
ba
s
e
d a
ppr
oa
c
h
e
s
R
e
f
e
r
e
nc
e
T
e
c
hni
que
us
e
d
E
xpe
r
i
m
e
nt
a
l
da
t
a
s
e
t
P
a
r
a
m
e
t
e
r
M
e
t
hod s
um
m
a
r
y a
nd
m
e
r
i
t
s
R
e
m
a
r
ks
[
4]
M
L
(
K
N
N
, C
4.5,
S
V
M
)
W
B
C
a
nd f
i
ne
ne
e
dl
e
a
s
pi
r
a
t
e
(
F
N
A
)
E
a
r
l
y
-
s
t
a
ge
pr
e
di
c
t
i
on
B
C
di
a
gnos
i
s
a
nd
pr
ognos
i
s
C
l
a
s
s
i
f
i
c
a
t
i
on
a
c
c
ur
a
c
y be
t
t
e
r
t
ha
n
c
l
us
t
e
r
i
ng 81%
[
17]
S
uppor
t
ve
c
t
or
c
l
a
s
s
i
f
i
e
r
s
,
RF
,
K
N
N
s
, a
nd
LR
W
i
s
c
ons
i
n H
o
s
pi
t
a
l
da
t
a
s
e
t
f
r
om
K
a
ggl
e
.c
om
B
r
e
a
s
t
t
e
m
pe
r
a
t
ur
e
m
oni
t
or
i
ng, M
R
I
H
i
s
t
or
i
c
a
l
i
m
a
ge
a
na
l
ys
i
s
a
nd us
e
of
ha
e
m
a
t
oxyl
i
n
a
nd e
os
i
n
96.23%
i
n K
N
N
,
96.28%
i
n
RF
,
98.11%
i
n S
V
M
,
a
nd
98.18%
i
n
LR
[
18]
S
V
M
,
de
c
i
s
i
on
t
r
e
e
, R
F
, a
nd
LR
W
i
s
c
ons
i
n B
C
da
t
a
s
e
t
S
um
m
a
r
y a
nd
de
s
c
r
i
pt
i
on
V
e
s
s
a
l
s
of
pl
a
s
m
a
a
nd
l
ym
ph ve
s
s
a
l
s
H
i
ghe
s
t
a
c
c
ur
a
c
y
gi
ve
n by
RF
98.24%
[
1
9
]
M
L
a
l
gor
i
t
hm
s
w
i
t
h
I
oT
W
D
B
C
S
um
m
a
r
y a
nd
de
s
c
r
i
pt
i
on
A
ge
, gl
uc
os
e
a
nd r
e
s
i
s
t
i
n
e
f
f
e
c
t
i
ve
bi
om
a
r
ke
r
f
or
BC
A
s
c
om
pa
r
e
d t
o L
R
a
nd R
F
, M
L
P
pr
oduc
e
s
gr
e
a
t
e
r
a
c
c
ur
a
c
y w
i
t
h l
ow
e
r
f
a
ul
t
r
a
t
e
[
20]
R
F
, L
R
, S
V
M
,
a
nd G
a
us
s
i
a
n
p
r
oc
e
s
s
(
G
P
)
c
l
a
s
s
i
f
i
e
r
s
N
ove
l
bi
om
a
r
ke
r
s
S
um
m
a
r
y a
nd
de
s
c
r
i
pt
i
on
T
he
c
om
pl
e
xi
t
y of
ge
ne
s
a
nd t
he
i
nt
e
r
c
onne
c
t
i
ons
be
t
w
e
e
n t
he
m
ne
e
d f
or
a
dva
nc
e
d A
I
m
ode
l
s
G
P
pe
r
f
or
m
e
d =90%
[
21]
S
V
M
,
LR
,
RF
,
a
nd B
a
ye
s
i
a
n
c
l
a
s
s
i
f
i
c
a
t
i
on
C
ohor
t
c
om
pr
i
s
e
d 302
pa
t
i
e
nt
s
S
um
m
a
r
y a
nd
de
s
c
r
i
pt
i
on
H
um
a
n e
pi
de
r
m
a
l
gr
ow
t
h
f
a
c
t
or
r
e
c
e
pt
or
T
o f
or
e
c
a
s
t
B
C
m
e
t
a
s
t
a
s
e
s
a
t
l
e
a
s
t
t
hr
e
e
m
ont
hs
i
n
a
dva
nc
e
, us
e
a
RF
m
ode
l
[
22]
ML
R
a
w
da
t
a
S
um
m
a
r
y a
nd
de
s
c
r
i
pt
i
on
c
om
bi
ni
ng r
a
di
om
i
c
va
r
i
a
bl
e
, c
l
i
ni
c
a
l
da
t
a
, a
nd
pa
t
hol
ogi
c
a
l
da
t
a
on M
R
I
m
os
t
a
c
c
ur
a
t
e
pr
e
di
c
t
i
on w
a
s
m
a
de
by R
F
[
23]
M
L
a
l
gor
i
t
hm
(
R
F
, L
R
, A
N
N
,
a
nd S
V
M
)
G
S
E
20271 a
nd
G
S
E
22093, us
e
d 134
ge
ne
s
a
s
di
a
gnos
t
i
c
i
ndi
c
a
t
or
s
S
u
m
m
a
r
y
a
n
d
d
e
s
c
r
i
p
t
i
o
n
(
c
o
r
r
e
c
t
d
i
s
c
r
i
m
i
n
a
t
i
on
o
f
p
a
t
i
e
n
t
s
)
G
e
ne
w
i
s
e
e
i
ge
nv
e
c
t
or
C
a
nc
e
r
s
t
a
gi
ng
pr
e
di
c
t
i
on
S
V
M
pe
r
f
or
m
e
d
a
c
c
ur
a
c
y 92.21%
[
24]
ML
G
e
ne
e
xpr
e
s
s
i
on,
D
N
A
, m
i
R
N
A
e
xpr
e
s
s
i
on, m
ul
t
i
-
om
i
c
s
da
t
a
S
um
m
a
r
y a
nd
de
s
c
r
i
pt
i
on
M
L
pi
pe
l
i
ne
s
ur
vi
va
l
pr
e
di
c
t
i
ons
i
n c
om
pa
r
i
s
on
t
o s
i
ngl
e
-
m
oda
l
i
t
y da
t
a
-
ba
s
e
d f
or
e
c
a
s
t
s
A
U
C
a
c
c
ur
a
c
y 87%
3.
R
O
L
E
OF
m
iRN
A
I
N
B
R
E
A
S
T
C
A
N
C
E
R
P
R
E
D
I
C
T
I
O
N
O
ne
of
th
e
m
os
t
r
e
s
e
a
r
c
he
d
m
ol
e
c
ul
e
s
w
it
h
th
e
pot
e
nt
ia
l
to
s
e
r
ve
a
s
c
a
nc
e
r
bi
om
a
r
ke
r
s
is
m
iR
N
A
.
D
e
r
e
gul
a
te
d
m
iR
N
A
e
xpr
e
s
s
io
n
is
a
ha
ll
m
a
r
k
of
a
ll
c
a
nc
e
r
ty
pe
s
,
a
nd
it
ha
s
b
e
e
n
li
nke
d
to
th
e
ons
e
t,
pr
ogr
e
s
s
io
n,
a
nd
r
e
s
pons
e
to
tr
e
a
tm
e
nt
.
M
or
e
ov
e
r
,
m
iR
N
A
s
a
r
e
s
ta
bl
e
,
br
ie
f
,
a
nd
th
e
ir
e
xpr
e
s
s
io
n
in
ti
s
s
ue
s
a
nd
body
f
lu
id
s
m
a
y
be
e
a
s
il
y
f
ound.
T
he
s
e
f
e
a
tu
r
e
s
of
m
iR
N
A
s
ha
ve
m
a
de
th
e
m
pot
e
nt
ia
ll
y
us
e
f
ul
bi
om
a
r
ke
r
s
f
or
c
a
nc
e
r
r
e
s
e
a
r
c
h,
in
c
lu
di
ng
di
a
gnos
ti
c
,
pr
ognos
ti
c
,
a
nd
pr
e
di
c
ti
ve
pur
pos
e
s
.
A
lt
hough
di
f
f
e
r
e
nt
ia
l
e
xpr
e
s
s
io
n
is
th
e
m
e
th
od
us
e
d
in
m
a
ny
c
a
nc
e
r
r
e
s
e
a
r
c
h
bi
om
a
r
ke
r
s
tu
di
e
s
to
id
e
nt
if
y
bi
om
a
r
ke
r
s
,
th
e
r
e
is
a
n
in
c
r
e
a
s
in
g
te
nde
nc
y
to
w
a
r
ds
th
e
u
s
a
ge
a
nd
us
e
of
M
L
t
e
c
hni
que
s
f
or
pr
e
di
c
ti
ve
m
ode
ll
in
g
a
nd
da
t
a
m
in
in
g.
Y
e
t,
s
om
e
m
iR
N
A
s
th
a
t
ha
ve
b
e
e
n
li
nke
d
to
B
C
h
a
ve
be
e
n
f
ound
to
ha
v
e
dys
r
e
gul
a
te
d
e
xpr
e
s
s
io
n,
w
hi
c
h
m
a
y
ha
v
e
a
n
im
pa
c
t
on
th
e
ons
e
t
a
nd
s
pr
e
a
d
of
th
e
di
s
e
a
s
e
.
T
he
s
e
in
c
lu
de
,
a
m
ong
ot
he
r
s
,
m
iR
-
21,
miR
-
155,
m
iR
-
10b,
m
iR
-
210,
a
nd
m
iR
-
146a
.
m
iR
N
A
s
ha
ve
r
e
c
e
iv
e
d
s
ub
s
ta
nt
ia
l
r
e
s
e
a
r
c
h
a
s
pot
e
nt
ia
l
in
di
c
a
to
r
s
f
or
th
e
di
a
gnos
is
a
nd
pr
ognos
is
of
B
C
.
L
it
tl
e
non
-
c
odi
ng
R
N
A
m
ol
e
c
ul
e
s
known
a
s
m
iR
N
A
s
a
r
e
c
r
uc
ia
l
f
or
pos
t
-
tr
a
ns
c
r
ip
ti
ona
l
ge
ne
c
ont
r
ol
,
a
nd
de
r
e
gul
a
ti
on
of
th
e
s
e
m
ol
e
c
ul
e
s
ha
s
be
e
n
li
nke
d
to
s
e
ve
r
a
l
il
ln
e
s
s
e
s
, i
n
c
lu
di
ng c
a
nc
e
r
.
T
he
de
v
e
lo
pm
e
nt
of
M
L
a
lg
or
it
hm
s
th
a
t
c
a
n
pr
e
di
c
t
out
c
om
e
s
of
m
e
ta
bol
ic
e
ngi
n
e
e
r
in
g
de
pe
nd
s
he
a
vi
ly
on e
xpe
r
im
e
nt
a
l
da
ta
s
e
ts
a
nd omi
c
s
d
a
ta
. M
L
of
f
e
r
s
s
ta
t
is
ti
c
a
l
te
c
hni
que
s
f
or
da
ta
e
xpl
or
a
ti
on t
ha
t
c
a
n
be
us
e
d
to
tr
a
in
c
om
put
e
r
s
to
pr
e
di
c
t
th
e
out
c
om
e
s
o
f
ge
ne
ti
c
t
he
r
a
py.
T
he
th
r
e
e
pa
r
a
di
gm
s
of
r
e
in
f
or
c
e
m
e
nt
le
a
r
ni
ng,
uns
upe
r
vi
s
e
d
le
a
r
ni
ng,
a
nd
s
up
e
r
vi
s
e
d
le
a
r
ni
ng
a
r
e
ty
pi
c
a
ll
y
us
e
d
to
c
a
te
gor
iz
e
M
L
r
e
s
e
a
r
c
h.
I
n
th
e
la
s
t
te
n ye
a
r
s
, va
r
io
us
i
nt
e
r
a
c
ti
ve
da
ta
b
a
s
e
s
ha
ve
be
e
n
c
r
e
a
te
d f
or
or
ga
ni
z
in
g bi
ol
ogi
c
a
l
da
ta
i
n
s
uc
h e
nor
m
ous
qua
nt
it
ie
s
[
25]
.
F
in
a
ll
y,
m
iR
N
A
s
ha
ve
th
e
pot
e
nt
ia
l
to
be
im
po
r
ta
nt
c
om
pone
nt
s
of
B
C
pr
e
di
c
ti
ve
m
ode
ll
in
g
.
T
o
tr
a
ns
la
te
m
iR
N
A
r
e
s
e
a
r
c
h
in
to
c
li
ni
c
a
ll
y
us
e
f
ul
a
ppl
ic
a
ti
ons
,
it
is
im
pe
r
a
ti
ve
to
s
ol
ve
th
e
di
f
f
ic
ul
ti
e
s
r
e
la
te
d
to
th
e
ir
us
a
ge
a
s
bi
om
a
r
ke
r
s
.
F
or
be
tt
e
r
B
C
di
a
g
no
s
is
,
pr
ognos
is
,
a
nd
tr
e
a
tm
e
nt
pl
a
nni
ng,
ongoing
r
e
s
e
a
r
c
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
m
ac
hi
ne
l
e
ar
ni
ng bas
e
d f
r
am
e
w
o
r
k
f
or
b
r
e
as
t
c
an
c
e
r
p
r
e
di
c
ti
on us
in
g bi
om
ar
k
e
r
s
(
A
pur
v
a V
as
hi
s
t)
4347
a
tt
e
m
pt
s
to
im
pr
ove
e
xpe
r
im
e
nt
a
l
s
tr
a
te
gi
e
s
,
va
li
da
t
e
m
iR
N
A
-
ba
s
e
d
pr
e
di
c
ti
ve
m
ode
ls
,
a
nd
im
pr
ove
da
t
a
pr
oc
e
s
s
in
g t
e
c
hni
que
s
.
3.1. Ap
p
li
c
at
io
n
s
of
m
ac
h
in
e
l
e
ar
n
in
g
f
or
b
io
lo
gi
c
al
f
u
n
c
t
io
n
s
V
a
r
io
us
M
L
t
e
c
hni
que
s
c
ov
e
r
e
d i
n t
he
pr
e
c
e
di
ng s
e
c
ti
on pr
odu
c
e
t
ool
s
t
o
s
ol
ve
di
ve
r
s
e
di
f
f
ic
ul
ti
e
s
i
n
c
r
e
a
ti
ng
bi
ol
ogi
c
a
l
s
ys
te
m
s
.
M
L
m
ode
ls
c
a
n
be
us
e
d
to
c
r
e
a
te
s
ys
te
m
-
le
ve
l
c
e
ll
s
by
e
m
pl
oyi
ng
qua
nt
if
ia
bl
e
in
put
a
nd
out
put
va
r
ia
bl
e
s
.
B
e
c
a
u
s
e
th
e
y
a
r
e
tr
a
in
e
d
us
in
g
e
xp
e
r
im
e
nt
a
l
da
ta
,
th
e
s
e
da
ta
-
dr
iv
e
n
m
ode
ls
po
s
s
e
s
s
pr
e
di
c
ti
ve
a
bi
li
ty
w
it
hout
ne
c
e
s
s
it
a
ti
ng
a
th
or
ough
gr
a
s
p
of
m
e
c
ha
ni
s
m
s
.
A
w
e
ll
-
f
r
a
m
e
d
m
ode
l
m
ig
ht
f
or
e
s
e
e
th
e
e
f
f
e
c
ts
of
f
ut
ur
e
in
s
il
ic
o
tr
ia
ls
,
w
hi
c
h
c
oul
d
upgr
a
d
e
e
xpe
r
im
e
nt
a
l
a
ppr
oa
c
he
s
f
o
r
opt
im
um
bi
o
s
ys
te
m
de
s
ig
n
in
a
w
a
y
th
a
t
is
bot
h
e
c
onomi
c
a
l
a
nd
la
bor
-
in
te
ns
iv
e
[
26]
.
M
ode
ls
a
r
e
of
te
n
tr
a
in
e
d
a
nd
ve
r
if
ie
d
us
in
g
e
xi
s
ti
ng
in
f
or
m
a
ti
on
a
nd
da
ta
ga
th
e
r
e
d
f
r
om
e
xpe
r
im
e
nt
s
.
Y
e
t
c
hoos
in
g
th
e
be
s
t
m
ode
l
to
us
e
is
a
c
r
it
ic
a
l
unde
r
ta
ki
ng
th
a
t
m
os
tl
y
de
pe
nds
on
dom
a
in
knowle
dge
a
nd
a
n
a
s
s
e
s
s
m
e
nt
of
a
lt
e
r
na
ti
ve
pr
om
is
in
g
m
ode
l
s
.
T
he
m
ode
l
w
it
h
hi
ghe
r
pr
e
di
c
ti
ve
pow
e
r
i
s
ut
il
iz
e
d
f
or
e
xpe
r
im
e
nt
a
l
va
li
da
ti
on
a
f
te
r
s
e
le
c
ti
on
pr
oc
e
dur
e
. T
he
ne
w
ly
a
c
qui
r
e
d da
ta
i
s
i
nc
or
por
a
te
d i
nt
o t
he
m
ode
l
to
i
m
pr
ove
i
t
a
nd give
i
t
be
tt
e
r
f
or
e
c
a
s
ti
ng powe
r
.
I
n
num
e
r
ous
ba
c
te
r
ia
l
a
nd
ye
a
s
t
ge
ne
r
a
,
M
L
ha
s
be
e
n
u
s
e
d
to
pr
e
c
is
e
ly
pr
e
di
c
t
th
e
R
N
A
a
c
ti
vi
ti
e
s
.
O
n
ta
r
ge
t
m
ove
m
e
nt
pr
e
di
c
to
r
s
ha
ve
be
e
n
de
ve
lo
pe
d
u
s
in
g
a
va
r
ie
t
y
of
M
L
m
e
th
ods
,
f
r
om
s
tr
a
ig
ht
f
or
w
a
r
d
li
ne
a
r
r
e
gr
e
s
s
io
n t
o i
nt
r
ic
a
te
, c
onvolut
e
d ne
ur
a
l
ne
twor
ks
. M
or
e
ove
r
,
non
-
li
ne
a
r
pa
r
a
m
e
te
r
S
V
M
m
ode
ls
w
it
h
s
in
gl
e
gui
de
R
N
A
(
s
gR
N
A
)
s
c
or
e
r
a
nd
c
lu
s
te
r
e
d
r
e
gul
a
r
ly
in
te
r
s
pa
c
e
d
s
hor
t
pa
li
ndr
om
ic
r
e
p
e
a
t
D
N
A
ta
r
ge
ti
ng
(
C
R
I
S
P
R
-
DT
)
[
27]
ha
ve
be
e
n
c
ons
tr
uc
te
d.
G
e
ne
ti
c
c
ir
c
ui
ts
a
r
e
s
pe
c
ia
li
z
e
d
gr
oups
of
D
N
A
s
e
qu
e
nc
e
s
th
a
t
e
na
bl
e
in
te
r
c
e
ll
ul
a
r
c
om
m
uni
c
a
ti
on
to
pe
r
f
or
m
a
s
pe
c
if
ic
pur
pos
e
a
nd
c
ode
f
or
a
pa
r
ti
c
ul
a
r
R
N
A
or
pr
ot
e
in
.
T
he
s
e
ne
twor
k
s
c
a
n
c
ont
r
ol
a
va
r
ie
ty
of
c
e
ll
be
ha
vi
or
s
ba
s
e
d
on
in
put
s
f
r
om
th
e
s
ur
r
ounding
e
nvi
r
onm
e
nt
.
A
c
onve
nt
io
na
l
ge
ne
c
ir
c
ui
t
de
s
ig
n
s
tr
a
te
gy
in
vol
ve
s
put
ti
ng
f
or
th
a
s
ys
te
m
,
u
s
in
g
c
om
put
a
ti
ona
l
m
e
th
ods
to
id
e
nt
if
y
a
w
or
ka
bl
e
r
ol
e
,
a
nd
a
dj
us
ti
ng
th
e
pa
r
a
m
e
te
r
s
a
s
ne
c
e
s
s
a
r
y.
I
n
te
r
m
s
of
M
L
,
a
n
id
e
a
l
pur
pos
e
c
a
n
be
c
r
e
a
te
d by it
e
r
a
ti
ve
ly
e
xa
m
in
in
g t
he
be
s
t
f
it
f
r
om
a
l
ib
r
a
r
y of
po
te
nt
ia
l
s
ys
te
m
a
r
r
a
nge
m
e
nt
s
.
3.2. P
r
ot
e
in
e
n
gi
n
e
e
r
in
g
I
n huma
n body, pr
ot
e
in
s
pe
r
f
or
m
a
w
id
e
r
a
nge
of
f
unc
ti
ons
, s
uc
h a
s
pr
e
s
e
r
vi
ng t
he
phys
ic
a
l
in
te
gr
it
y
of
c
e
ll
s
, a
c
ti
ng a
s
e
ne
r
gy s
to
r
a
ge
uni
ts
, a
s
s
is
ti
ng i
n t
he
m
ove
m
e
nt
of
m
ol
e
c
ul
e
s
a
c
r
os
s
m
e
m
br
a
ne
s
, a
nd t
a
ki
ng
pa
r
t
in
a
va
r
ie
ty
of
m
ol
e
c
ul
a
r
pr
oc
e
s
s
e
s
li
ke
D
N
A
r
e
pl
ic
a
ti
on
a
nd
tr
a
ns
c
r
ip
ti
on.
T
he
a
m
in
o
a
c
id
c
om
pone
nt
s
th
a
t
m
a
ke
up
th
e
e
nt
ir
e
pr
ot
e
in
a
r
e
c
ont
a
in
e
d
w
it
hi
n
th
e
s
e
c
om
pl
e
xe
s
.
S
e
que
n
c
e
r
-
ba
s
e
d
pr
ot
e
in
f
unc
ti
on
pr
e
di
c
ti
ons
ha
ve
be
e
n
th
e
s
ubj
e
c
t
of
m
uc
h
s
tu
dy
a
nd
ha
ve
f
ound
w
id
e
s
pr
e
a
d
us
e
in
th
e
s
c
ie
nt
if
ic
,
te
c
hnol
ogi
c
a
l,
a
nd me
di
c
a
l
f
ie
ld
s
[
28]
, [
29]
.
4.
D
A
T
A
S
O
U
R
C
E
O
m
ic
s
bi
om
a
r
ke
r
s
da
ta
s
e
t
is
a
c
ol
le
c
ti
on
of
da
ta
f
r
om
di
f
f
e
r
e
nt
bi
ol
ogi
c
a
l
le
ve
ls
,
s
u
c
h
a
s
g
e
nom
ic
s
,
tr
a
ns
c
r
ip
to
m
ic
s
,
pr
ot
e
om
ic
s
,
a
nd
m
e
ta
bol
om
ic
s
.
T
he
m
ol
e
c
ul
a
r
pr
ope
r
ti
e
s
of
B
C
c
a
n
be
th
or
oughly
vi
e
w
e
d
us
in
g
th
e
s
e
da
ta
b
a
s
e
s
,
w
hi
c
h
c
a
n
a
l
s
o
be
us
e
d
to
f
in
d
po
s
s
ib
le
bi
om
a
r
ke
r
s
or
tr
e
a
tm
e
nt
ta
r
ge
ts
.
T
he
pa
tt
e
r
ns
th
a
t
di
s
ti
ngui
s
h m
a
li
gna
nt
t
is
s
ue
f
r
om
he
a
lt
hy t
is
s
ue
c
a
n be
f
ound by e
xa
m
in
in
g omi
c
s
da
ta
f
r
om
B
C
pa
ti
e
nt
s
.
W
it
h t
hi
s
da
ta
, pr
e
di
c
ti
on mode
ls
c
a
n be
c
r
e
a
te
d t
o he
lp
i
de
nt
if
y i
ndi
vi
dua
ls
w
ho a
r
e
a
t
a
hi
gh r
is
k f
or
B
C
a
nd
to
gui
d
e
tr
e
a
tm
e
nt
c
hoi
c
e
s
.
O
m
ic
s
da
t
a
s
e
t
s
c
a
n
be
a
n
e
f
f
e
c
ti
v
e
to
ol
f
or
pr
e
di
c
ti
ng
th
e
de
ve
lo
pm
e
nt
of
B
C
ove
r
a
ll
,
a
nd
f
ur
th
e
r
s
tu
dy
is
e
xpe
c
te
d
to
f
in
d
f
ur
th
e
r
a
ppl
ic
a
ti
ons
f
or
th
e
s
e
da
ta
s
e
ts
th
a
t
w
il
l
e
nha
nc
e
pa
ti
e
nt
out
c
om
e
s
[
13]
.
T
he
da
ta
s
e
t
c
ont
a
in
s
1937
f
e
a
tu
r
e
s
a
nd
a
ta
r
ge
t
va
r
ia
bl
e
.
T
he
da
t
a
s
e
t
c
ont
a
in
s
in
s
ta
n
c
e
s
of
705
pa
ti
e
nt
s
(
611
pa
ti
e
nt
s
s
ur
vi
ve
d,
94
di
e
d)
.
E
a
c
h
f
e
a
tu
r
e
ha
s
a
pr
e
f
ix
a
c
c
or
di
ng
to
th
e
da
ta
ty
pe
:
m
u:
s
om
a
ti
c
m
ut
a
ti
on
(
ye
s
,
no)
[
s
om
a
ti
c
m
ut
a
ti
on:
a
pos
t
-
c
onc
e
p
ti
ona
l
c
ha
nge
in
D
N
A
.
S
om
a
ti
c
m
ut
a
ti
ons
c
a
n
ha
ppe
n
in
a
ny
ty
pe
of
c
e
ll
in
th
e
body,
e
xc
e
pt
f
o
r
ge
r
m
c
e
ll
s
(
e
gg
a
nd
s
pe
r
m
)
,
w
hi
c
h
a
r
e
not
tr
a
ns
f
e
r
r
e
d
to
pr
oge
ny]
.c
n:
c
opy
num
be
r
va
r
ia
ti
on
a
s
c
a
lc
ul
a
te
d
by
gi
s
ti
c
(
-
2,
-
1,
0,
1,
2)
,
r
s
:
R
N
A
(
R
ib
onuc
le
ic
a
c
id
)
s
e
que
nc
in
g
i.
e
ge
ne
e
xpr
e
s
s
io
n, pp: phos
phor
-
pr
ot
e
in
l
e
ve
ls
.
T
he
ove
r
a
ll
s
iz
e
of
da
ta
s
e
t
is
705 r
ow
s
*1941
c
ol
um
ns
.
5.
M
A
C
H
I
N
E
L
E
A
R
N
I
N
G
M
E
T
H
O
D
S
A
N
D
A
L
G
O
R
I
T
H
M
S
I
N
B
C
P
R
E
D
I
C
T
I
O
N
A
lg
or
it
hm
s
th
a
t
a
id
in
pr
e
di
c
ti
on
a
nd
c
la
s
s
if
ic
a
ti
on
c
a
n
be
c
r
e
a
te
d
a
nd
a
s
s
e
s
s
e
d
us
in
g
M
L
te
c
hni
que
s
.
F
our
pr
oc
e
s
s
e
s
f
or
m
th
e
f
ounda
ti
on
o
f
M
L
:
ga
th
e
r
in
g
da
ta
,
pr
oc
e
s
s
in
g
it
,
tr
a
in
in
g
th
e
m
ode
l,
a
nd
te
s
ti
ng
it
.
F
our
c
a
te
gor
ie
s
of
a
lg
or
it
hm
s
w
e
r
e
us
e
d
in
th
is
in
ve
s
ti
ga
ti
o
n:
pr
ot
e
in
s
im
il
a
r
it
y
m
e
a
s
ur
e
d
us
in
g
P
e
a
r
s
on
c
or
r
e
la
ti
on t
e
c
hni
que
, f
e
a
tu
r
e
e
xt
r
a
c
ti
on, f
e
a
tu
r
e
s
e
le
c
ti
on, a
nd
c
lu
s
te
r
in
g s
how
n i
n F
ig
ur
e
1.
M
L
is
th
e
s
tu
dy
of
pr
ogr
a
m
m
in
g
c
om
put
e
r
s
to
a
ut
om
a
ti
c
a
ll
y
le
a
r
n
f
r
om
a
nd
a
da
pt
to
ne
w
s
it
ua
ti
ons
ba
s
e
d
on
a
va
il
a
bl
e
da
ta
.
B
y
ut
il
iz
in
g
s
ta
ti
s
ti
c
a
l
c
or
r
e
la
ti
ons
f
r
om
a
ny
da
ta
s
e
t,
pr
e
di
c
ti
ve
m
ode
ls
m
a
y
be
de
ve
lo
pe
d
th
a
t
c
a
n
be
tr
a
in
e
d
to
pr
e
di
c
t
a
va
r
ie
ty
of
e
ve
nt
s
[
30]
, [
31]
.
M
L
is
a
te
c
hni
que
f
o
r
opt
im
iz
in
g
s
e
ve
r
a
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024:
4344
-
4351
4348
m
e
ta
bol
ic
e
ngi
ne
e
r
in
g
c
om
pone
nt
s
,
in
c
lu
di
ng
ge
ne
c
ir
c
ui
t
s
tr
a
te
gy,
f
lu
x
pr
e
di
c
ti
on,
s
tr
a
in
ge
ne
r
a
ti
on,
ta
r
ge
t
pr
oduc
t
yi
e
ld
e
nha
nc
e
m
e
nt
,
r
out
e
pr
opos
a
l,
a
nd
opt
im
iz
a
ti
on.
T
hi
s
is
due
to
th
e
e
a
s
y
a
va
il
a
bi
li
ty
of
da
ta
on
m
ic
r
obi
a
l
m
e
ta
bol
is
m
in
va
r
io
us
c
e
ll
u
la
r
a
nd
phy
s
io
lo
gi
c
a
l
s
t
a
te
s
.
T
houghtf
ul
c
on
s
id
e
r
a
ti
on
of
th
e
pa
r
ti
c
ul
a
r
s
of
th
e
da
ta
,
th
e
na
tu
r
e
of
th
e
pr
obl
e
m
,
a
nd
th
e
s
tu
dy
obj
e
c
t
iv
e
s
goe
s
in
to
c
hoo
s
in
g
M
L
a
lg
or
it
hm
s
a
nd
e
va
lu
a
ti
on
c
r
it
e
r
ia
.
W
he
n
e
va
lu
a
ti
ng
a
nd
c
ont
r
a
s
ti
ng
th
e
pe
r
f
or
m
a
nc
e
of
va
r
io
us
a
lg
or
it
hm
s
,
c
r
os
s
-
va
li
da
ti
on,
r
e
le
va
nt
m
e
tr
ic
s
, a
nd doma
in
e
xpe
r
ti
s
e
a
r
e
e
s
s
e
nt
ia
l
c
om
pone
nt
s
.
M
e
th
odol
ogy
−
R
e
c
ove
r
a
ll
pos
s
ib
le
pr
ot
e
in
s
(
pr
ot
e
in
s
l
is
t)
f
r
om
m
ul
ti
om
ic
s
da
ta
s
e
t.
−
B
ui
ld
th
e
c
or
r
e
la
ti
on
in
te
r
a
c
ti
on
m
a
tr
ix
o
f
th
e
p
r
ot
e
in
s
to
id
e
nt
if
y
pr
ot
e
in
bi
o
m
a
r
ke
r
s
w
it
h
th
e
d
ir
e
c
t
a
s
s
oc
ia
ti
on t
o c
a
nc
e
r
ous
pa
ti
e
nt
s
.
−
S
e
le
c
te
d
be
s
t
pr
ot
e
in
by
us
in
g
f
e
a
tu
r
e
s
e
le
c
ti
on
a
lg
or
it
hm
(
g
e
ne
ti
c
a
lg
or
it
hm
)
,
P
C
A
,
a
nd
c
lu
s
te
r
in
g
a
lg
or
it
hm
.
−
T
he
m
a
in
obj
e
c
ti
ve
of
th
e
pr
oj
e
c
t
e
d
m
e
th
od
is
to
id
e
nt
if
y
th
e
s
u
bs
e
t
of
pr
ot
e
in
s
w
it
h
th
e
hi
ghe
s
t
r
e
le
va
nc
e
f
or
pr
e
di
c
ti
on of
B
C
.
−
C
ol
le
c
t
th
e
ge
ne
s
c
or
r
e
s
ponding t
o t
he
K
s
e
le
c
te
d pr
ot
e
in
s
f
r
om
om
ic
s
da
ta
s
e
t.
F
ig
ur
e
1. W
or
kf
lo
w
di
a
gr
a
m
f
o
r
B
C
pr
e
di
c
ti
on
6.
R
E
S
U
L
T
A
N
D
D
I
S
C
U
S
S
I
O
N
T
he
two
ke
y
p
a
r
ts
of
th
i
s
s
ugg
e
s
te
d
s
tr
a
te
gy
a
r
e
f
e
a
tu
r
e
s
e
le
c
ti
on
a
nd
c
lu
s
te
r
in
g.
T
h
e
be
s
t
f
e
a
tu
r
e
s
in
th
e
il
ln
e
s
s
pr
e
di
c
ti
on
da
ta
s
e
t
a
r
e
f
ound
in
th
e
f
ir
s
t
s
te
p
us
in
g
c
lu
s
te
r
in
g
a
lg
or
it
hm
a
nd
us
in
g
a
M
L
c
la
s
s
if
ie
r
.
O
ne
w
a
y
to
a
s
s
e
s
s
th
e
m
ode
l'
s
pe
r
f
or
m
a
n
c
e
is
us
in
g
th
e
c
onf
u
s
io
n
m
a
tr
ix
(
C
M
)
.
S
om
e
c
om
m
on
m
e
a
s
ur
e
s
us
e
d
in
M
L
s
tu
di
e
s
to
a
s
s
e
s
s
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
m
ode
ls
c
ont
a
in
in
g
c
onf
us
io
n
m
a
tr
ic
e
s
a
r
e
:
r
e
c
a
ll
or
s
e
ns
it
iv
it
y,
s
pe
c
if
ic
it
y,
F
1
-
s
c
or
e
,
a
r
e
a
unde
r
th
e
c
ur
ve
(
A
U
C
)
c
ur
ve
,
a
c
c
ur
a
c
y,
pr
e
c
is
io
n,
a
nd
r
e
c
e
iv
e
r
ope
r
a
ti
ng
c
ha
r
a
c
te
r
is
ti
c
s
(
R
O
C
)
c
ur
ve
.
C
lu
s
te
r
in
g
us
in
g
m
ul
ti
om
ic
s
da
ta
s
e
t:
I
t
is
im
por
ta
nt
to
c
on
s
id
e
r
s
ta
ti
s
ti
c
a
l
s
ig
ni
f
ic
a
nc
e
in
a
ddi
ti
on
to
c
or
r
e
la
ti
on
m
a
gni
tu
de
.
I
f
th
e
s
a
m
pl
e
s
iz
e
is
la
r
ge
e
nough,
a
m
ode
s
t
c
onne
c
ti
on
c
oul
d
n
e
ve
r
th
e
le
s
s
be
s
ta
ti
s
ti
c
a
ll
y
s
ig
ni
f
ic
a
nt
.
T
o
a
s
c
e
r
ta
in
w
he
th
e
r
a
c
onne
c
ti
on
de
vi
a
te
s
s
ig
ni
f
ic
a
nt
ly
f
r
o
m
z
e
r
o,
s
ta
ti
s
ti
c
a
l
te
s
ts
li
ke
p
-
va
lu
e
s
a
r
e
us
ua
ll
y
e
m
pl
oye
d.
T
a
bl
e
2
s
how
s
th
e
hi
gh
e
s
t
c
or
r
e
la
ti
on
be
twe
e
n
c
opy
num
be
r
a
nd
phos
phopr
ot
e
in
e
xpr
e
s
s
io
n
in
B
C
.
T
hi
s
c
a
n
pr
ovi
de
va
lu
a
bl
e
in
s
ig
ht
s
in
to
th
e
m
ol
e
c
ul
a
r
m
e
c
ha
ni
s
m
s
unde
r
ly
in
g
th
e
di
s
e
a
s
e
.
S
uc
h
c
or
r
e
la
ti
ons
c
a
n
he
lp
to
unde
r
s
ta
nd
how
ge
ne
ti
c
a
lt
e
r
a
ti
ons
(
C
N
A
s
)
m
a
y
in
f
lu
e
nc
e
th
e
a
c
ti
va
ti
on or
i
na
c
ti
va
ti
on of
s
pe
c
if
ic
s
ig
na
li
ng pa
th
w
a
ys
r
e
pr
e
s
e
nt
e
d by phos
phopr
ot
e
in
e
xpr
e
s
s
io
n. T
he
s
e
f
in
di
ngs
c
a
n
pot
e
nt
ia
ll
y
le
a
d
to
th
e
id
e
nt
if
ic
a
ti
on
of
bi
om
a
r
ke
r
s
a
nd
th
e
r
a
pe
ut
ic
ta
r
ge
ts
f
or
m
or
e
pe
r
s
ona
li
z
e
d
B
C
tr
e
a
tm
e
nt
s
.
T
a
bl
e
3
c
om
pa
r
e
s
th
e
a
c
c
ur
a
c
y
of
th
e
v
a
r
io
us
m
ode
ls
/m
e
th
ods
,
pr
ovi
di
ng
a
vi
s
ua
l
r
e
pr
e
s
e
nt
a
ti
on of
t
he
ir
pe
r
f
o
r
m
a
nc
e
. T
he
a
c
c
ur
a
c
y pe
r
f
or
m
a
nc
e
of
e
a
c
h m
e
th
od i
s
s
how
n i
n t
he
gr
a
ph or
c
ha
r
t
e
it
he
r
s
id
e
by
s
id
e
or
s
upe
r
im
pos
e
d.
T
hi
s
c
om
pa
r
is
on
s
how
s
t
ha
t
va
r
io
us
m
ode
ls
us
e
d
in
th
e
s
tu
dy
di
f
f
e
r
in
th
e
ir
pr
e
di
c
ti
ve
a
bi
li
ty
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
m
ac
hi
ne
l
e
ar
ni
ng bas
e
d f
r
am
e
w
o
r
k
f
or
b
r
e
as
t
c
an
c
e
r
p
r
e
di
c
ti
on us
in
g bi
om
ar
k
e
r
s
(
A
pur
v
a V
as
hi
s
t)
4349
T
a
bl
e
2. C
or
r
e
la
ti
on ma
tr
ix
P
hos
phor
-
pr
ot
e
i
n (
P
P
)
R
i
bonuc
l
e
i
c
a
c
i
d (
R
S
)
M
ut
a
t
i
on (
M
u)
C
opy num
be
r
(
C
N
)
P
hos
phor
-
pr
ot
e
i
n (
P
P
)
1
-
0.004
0.013
0.014
R
i
bonuc
l
e
i
c
a
c
i
d (
R
S
)
-
0.004
1
-
0.036
-
0.136
M
ut
a
t
i
on (
M
u)
0.013
-
0.036
1
-
0.076
C
opy num
be
r
(
CN
)
0.014
-
0.136
-
0.076
1
T
a
bl
e
3. F
e
a
tu
r
e
s
e
le
c
ti
on a
ppr
oa
c
he
s
A
l
gor
i
t
hm
N
a
m
e
D
a
t
a
s
e
t
A
c
c
ur
a
c
y
(%)
C
l
us
t
e
r
ba
s
e
d gr
e
y w
ol
f
opt
i
m
i
z
a
t
i
on a
l
gor
i
t
hm
M
ul
t
i
om
i
c
s
(
B
R
C
A
)
91
G
e
ne
t
i
c
a
l
gor
i
t
hm
M
ul
t
i
om
i
c
s
(
B
R
C
A
)
93.5
A
P
C
A
a
n
a
ly
s
is
of
in
te
gr
a
te
d
c
opy
num
be
r
,
pr
ot
e
in
e
xpr
e
s
s
io
n,
a
nd
s
om
a
ti
c
m
ut
a
ti
on
da
ta
is
pr
oba
bl
y
de
pi
c
te
d
in
F
ig
ur
e
2(
a
)
,
w
hi
c
h
pr
ovi
de
s
a
vi
s
ua
l
de
pi
c
ti
on
of
t
he
m
ol
e
c
ul
a
r
la
nds
c
a
p
e
of
B
C
s
a
m
pl
e
s
.
B
a
s
e
d
on
th
e
c
om
bi
ne
d
m
ol
e
c
ul
a
r
c
h
a
r
a
c
te
r
is
ti
c
s
of
c
opy
num
be
r
va
r
ia
ti
ons
a
nd
pr
ot
e
in
e
xpr
e
s
s
io
n
le
ve
ls
,
F
ig
ur
e
s
2(
b)
-
2
(
d)
pr
oba
bl
y
of
f
e
r
s
a
th
o
r
ough
vi
s
ua
li
z
a
ti
on
of
B
C
s
a
m
pl
e
s
,
us
in
g
th
e
knowle
dge
f
r
om
P
C
A
a
nd
K
-
M
e
a
ns
c
lu
s
te
r
in
g a
na
ly
s
i
s
. I
n t
he
c
ont
e
xt
of
B
C
r
e
s
e
a
r
c
h, t
hi
s
m
e
th
od he
lp
s
t
o unc
ove
r
pa
tt
e
r
ns
,
s
ubgr
oups
,
a
nd pos
s
ib
le
t
he
r
a
pe
ut
ic
i
m
pl
ic
a
ti
on
s
.
(
a
)
(
b)
(
c
)
(
d)
F
ig
ur
e
2. P
C
A
of
(
a
)
c
om
bi
ne
d c
opy number
, pr
ot
e
in
, a
nd s
om
a
ti
c
m
ut
a
ti
on, (
b)
c
om
bi
ne
d c
opy number
a
nd
pr
ot
e
in
l
e
ve
l
w
it
h k
-
m
e
a
ns
c
lu
s
te
r
in
g, (
c
)
c
om
bi
ne
d c
opy numb
e
r
a
nd r
na
-
s
e
q da
ta
w
it
h k
-
m
e
a
ns
c
lu
s
te
r
in
g,
a
nd (
d)
c
om
bi
ne
d c
opy number
a
nd r
na
-
s
e
q da
ta
w
it
h k
-
m
e
a
ns
c
lu
s
te
r
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024:
4344
-
4351
4350
7.
C
O
N
C
L
U
S
I
O
N
A
N
D
F
U
T
U
R
E
WORK
T
he
pr
e
s
e
nt
e
d
om
ic
s
da
ta
m
us
t
b
e
s
ta
nd
a
r
di
z
e
d
u
s
in
g
a
n
a
ppr
opr
ia
te
knowle
dge
e
ngi
ne
e
r
in
g
te
c
hni
que
to
pr
oduc
e
c
om
pl
e
te
tr
a
in
in
g
da
ta
s
e
ts
f
or
M
L
.
H
e
n
c
e
,
c
om
bi
n
in
g
knowle
dge
e
ngi
ne
e
r
in
g
w
it
h
M
L
of
f
e
r
s
a
s
e
tt
in
g t
ha
t
pr
om
ot
e
s
ongoing l
e
a
r
ni
ng f
or
de
ve
lo
pi
ng
im
pr
ove
d e
xpl
a
na
ti
ons
f
or
B
C
pr
obl
e
m
pr
e
di
c
ti
on.
T
hi
s
r
e
vi
e
w
e
m
pha
s
iz
e
s
th
e
br
oa
d
r
a
nge
of
M
L
a
ppl
ic
a
ti
ons
in
s
e
ve
r
a
l
bi
ol
ogi
c
a
l
f
ie
ld
s
th
a
t
ha
ve
pr
ove
n
to
be
e
xt
r
e
m
e
ly
he
lp
f
ul
.
E
ve
n
th
e
pos
s
ib
il
it
y
of
a
ut
om
a
te
d
pr
oc
e
dur
e
s
in
vol
vi
ng
r
obot
s
be
in
g
us
e
d
in
M
L
ha
s
be
e
n
th
e
or
iz
e
d.
W
he
n
c
om
pa
r
e
d
to
m
a
nua
l
a
n
a
ly
s
is
,
M
L
ha
s
s
ho
w
n
to
be
e
f
f
e
c
ti
ve
a
t
s
ubs
t
a
nt
ia
ll
y
r
e
duc
in
g
pr
oc
e
s
s
in
g
ti
m
e
a
nd
im
pr
ovi
ng
th
e
a
c
c
ur
a
c
y
of
e
xpe
c
te
d
r
e
s
ul
ts
.
T
he
be
s
t
c
or
r
e
la
ti
on,
a
s
de
t
e
r
m
in
e
d
by
P
e
a
r
s
on
c
or
r
e
la
ti
on, be
twe
e
n c
opy number
a
nd pr
o
te
in
i
s
0.014, a
nd t
he
a
c
c
ur
a
c
y a
c
hi
e
ve
d by the
ge
ne
ti
c
a
lg
or
it
hm
i
s
93.5%
us
in
g
m
ul
ti
-
om
ic
s
da
ta
s
e
ts
.
I
n
th
e
f
ut
ur
e
,
va
r
io
us
f
e
a
tu
r
e
s
e
le
c
ti
on
te
c
hni
que
s
,
s
u
c
h
a
s
va
r
ia
nc
e
th
r
e
s
hol
d
a
nd w
ha
le
opt
i
m
iz
a
ti
on a
lg
or
it
hm
c
a
n be
e
m
pl
oye
d t
o f
ur
th
e
r
s
tu
dy t
he
e
f
f
e
c
t
on pr
e
di
c
ti
ons
.
R
E
F
E
R
E
N
C
E
S
[
1]
S
. Y
e
r
uka
l
a
a
nd S
. Y
. H
o, “
I
de
nt
i
f
yi
ng a
m
i
R
N
A
s
i
gn
a
t
ur
e
f
or
pr
e
di
c
t
i
ng t
he
s
t
a
ge
of
br
e
a
s
t
c
a
nc
e
r
,”
Sc
i
e
nt
i
f
i
c
R
e
por
t
s
, vol
. 8, no
.
1, 2018, doi
:
10.1038/
s
41598
-
018
-
34604
-
3.
[
2]
C
.
E
.
D
e
S
a
nt
i
s
,
J
.
M
a
,
A
.
G
.
S
a
ue
r
,
L
.
A
.
N
e
w
m
a
n,
a
nd
A
.
J
e
m
a
l
,
“
B
r
e
a
s
t
c
a
n
c
e
r
s
t
a
t
i
s
t
i
c
s
,
2017,
r
a
c
i
a
l
di
s
pa
r
i
t
y
i
n
m
or
t
a
l
i
t
y
b
y
s
t
a
t
e
,”
C
A
:
A
C
anc
e
r
J
ou
r
nal
f
or
C
l
i
ni
c
i
an
s
, vol
. 67, no. 6, pp. 439
–
448, 2017, doi
:
10.3322/
c
a
a
c
.21412.
[
3]
J
.
T
a
ng,
W
.
M
a
,
Q
.
Z
e
ng,
J
.
T
a
n,
K
.
C
a
o,
a
nd
L
.
L
uo,
“
I
de
nt
i
f
i
c
a
t
i
on
of
m
i
R
N
A
-
ba
s
e
d
s
i
gna
t
ur
e
a
s
a
nove
l
pot
e
nt
i
a
l
pr
ognos
t
i
c
bi
om
a
r
ke
r
i
n pa
t
i
e
nt
s
w
i
t
h br
e
a
s
t
c
a
nc
e
r
,”
D
i
s
e
as
e
M
ar
k
e
r
s
, vol
. 2019, 2019, d
oi
:
10.1155/
2019/
3815952.
[
4]
J
. K
. S
a
ndhu, A
. K
a
ur
, a
nd
C
. K
a
us
ha
l
,
“
A
na
l
ys
i
s
of
br
e
a
s
t
c
a
nc
e
r
i
n
e
a
r
l
y s
t
a
g
e
by us
i
ng m
a
c
hi
ne
l
e
a
r
ni
ng a
l
gor
i
t
hm
s
:
a
r
e
vi
e
w
,
”
P
r
oc
e
e
di
ngs
of
2022
I
E
E
E
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on C
u
r
r
e
nt
D
e
v
e
l
opm
e
nt
i
n E
ngi
ne
e
r
i
ng and T
e
c
hnol
ogy
,
C
C
E
T
2022
, 2022,
doi
:
10.1109/
C
C
E
T
56606.2022.10080757.
[
5]
E
.
T
a
g
hi
z
a
de
h
, S
.
H
e
yda
r
he
yda
r
i
,
A
.
S
a
be
r
i
, S
.
J
. N
e
s
he
l
i
,
a
nd
S
.
M
.
R
e
z
a
e
i
j
o,
“
B
r
e
a
s
t
c
a
nc
e
r
p
r
e
d
i
c
t
i
o
n
w
i
t
h t
r
a
ns
c
r
i
pt
om
e
p
r
o
f
i
l
i
n
g
us
i
n
g
f
e
a
t
u
r
e
s
e
l
e
c
t
i
on
a
n
d
m
a
c
h
i
n
e
l
e
a
r
ni
ng
m
e
t
h
ods
,
”
B
M
C
B
i
oi
nf
or
m
a
t
i
c
s
,
vo
l
.
23
, n
o.
1,
2
022
,
do
i
:
10
.11
86
/
s
12
85
9
-
02
2
-
04
965
-
8.
[
6]
A
.
Y
ur
ye
v,
“
G
e
ne
e
xpr
e
s
s
i
on
pr
of
i
l
i
ng
f
or
t
a
r
ge
t
e
d
c
a
nc
e
r
t
r
e
a
t
m
e
nt
,”
E
x
pe
r
t
O
pi
ni
on
on
D
r
ug
D
i
s
c
ov
e
r
y
,
vol
.
10,
no.
1,
pp.
91
–
99, 2015, doi
:
10.1517/
17460441.2015.971007.
[
7]
J
.
L
i
,
R
.
L
i
a
ng,
C
.
S
ong,
Y
.
X
i
a
ng,
a
nd
Y
.
L
i
u,
“
P
r
ognos
t
i
c
va
l
ue
of
K
i
-
67/
M
I
B
-
1
e
xpr
e
s
s
i
on
i
n
m
e
ni
ngi
om
a
pa
t
i
e
nt
s
:
A
m
e
t
a
-
a
na
l
ys
i
s
,”
C
r
i
t
i
c
al
R
e
v
i
e
w
s
i
n
E
uk
ar
y
ot
i
c
G
e
ne
E
x
pr
e
s
s
i
on
,
vol
.
29,
no.
2,
pp.
141
–
150,
2019,
do
i
:
10.1615/
C
r
i
t
R
e
vE
uka
r
yot
G
e
ne
E
xpr
.2019025430.
[
8]
A
.
D
.
M
.
G
ut
i
e
r
r
e
z
e
t
al
.
,
“
I
de
nt
i
f
i
c
a
t
i
on
of
m
i
r
na
m
a
s
t
e
r
r
e
gul
a
t
or
s
i
n
br
e
a
s
t
c
a
nc
e
r
,”
C
e
l
l
s
,
vol
.
9,
no.
7,
pp.
1
–
20,
2020,
doi
:
10.3390/
c
e
l
l
s
9071610.
[
9]
J
.
A
yool
a
a
nd
T
.
O
gunf
unm
i
,
“
A
c
om
pa
r
a
t
i
ve
a
na
l
ys
i
s
of
r
e
gr
e
s
s
i
on
a
l
gor
i
t
hm
s
w
i
t
h
ge
ne
t
i
c
a
l
gor
i
t
hm
i
n
t
he
pr
e
di
c
t
i
on
of
br
e
a
s
t
c
a
nc
e
r
t
um
or
s
,”
2022
I
E
E
E
G
l
obal
H
um
ani
t
ar
i
an
T
e
c
hnol
ogy
C
onf
e
r
e
nc
e
,
G
H
T
C
2022
,
pp.
143
–
149,
2022,
doi
:
10.1109/
G
H
T
C
55712.2022.9911033.
[
10]
K
.
N
oui
r
a
,
Z
.
M
a
a
l
e
j
,
F
.
B
.
R
e
j
a
b, L
.
O
ue
r
f
e
l
l
y,
a
nd
A
.
F
e
r
c
hi
c
hi
, “
A
na
l
ys
i
s
of
br
e
a
s
t
c
a
nc
e
r
da
t
a
:
A
c
om
pa
r
a
t
i
ve
s
t
udy
on
di
f
f
e
r
e
nt
f
e
a
t
ur
e
s
e
l
e
c
t
i
on t
e
c
hni
que
s
,”
P
r
oc
e
e
di
ng
s
of
2020
I
nt
e
r
nat
i
onal
M
ul
t
i
-
C
onf
e
r
e
nc
e
on:
O
r
gani
z
at
i
on of
K
now
l
e
dge
and A
dv
anc
e
d
T
e
c
hnol
ogi
e
s
, O
C
T
A
2020
, 2020, doi
:
10.1109/
O
C
T
A
49274.2020.9151824.
[
11]
V
.
C
.
A
l
c
udi
a
a
nd
M
.
A
.
V
.
R
odr
í
gue
z
,
“
A
r
t
i
f
i
c
i
a
l
be
e
c
ol
ony
a
l
go
r
i
t
hm
ba
s
e
d on
dom
i
na
nc
e
(
A
B
C
D
)
f
or
a
hybr
i
d
ge
ne
s
e
l
e
c
t
i
on
m
e
t
hod,”
K
now
l
e
dge
-
B
as
e
d Sy
s
t
e
m
s
, vol
. 205, 2020, doi
:
10.1016/
j
.knos
y
s
.202
0.106323.
[
12]
I
.
Z
e
nbout
,
A
.
B
our
a
m
oul
,
S
.
M
e
s
houl
,
a
nd
M
.
A
m
r
a
ne
,
“
E
f
f
i
c
i
e
nt
bi
oi
ns
pi
r
e
d
f
e
a
t
ur
e
s
e
l
e
c
t
i
on
a
nd
m
a
c
hi
ne
l
e
a
r
ni
ng
ba
s
e
d
f
r
a
m
e
w
or
k us
i
ng om
i
c
s
da
t
a
a
nd
bi
ol
ogi
c
a
l
know
l
e
dge
da
t
a
ba
s
e
s
i
n c
a
nc
e
r
c
l
i
n
i
c
a
l
e
ndpoi
nt
pr
e
di
c
t
i
on,”
I
E
E
E
A
c
c
e
s
s
, vol
. 11, pp.
2674
–
2699, 2023, doi
:
10.1109/
A
C
C
E
S
S
.2023.3234294.
[
13]
Z
.
I
s
i
k
a
nd
M
.
E
.
E
r
c
a
n,
“
I
n
t
e
gr
a
t
i
on
of
R
N
A
-
S
e
q
a
nd
R
P
P
A
da
t
a
f
o
r
s
ur
vi
va
l
t
i
m
e
pr
e
di
c
t
i
on
i
n
c
a
nc
e
r
pa
t
i
e
nt
s
,”
C
om
put
e
r
s
i
n
B
i
ol
ogy
and M
e
di
c
i
ne
, vol
. 89, pp. 397
–
404, 2017, doi
:
10.1016/
j
.c
om
pbi
om
e
d.
2017.08.028.
[
14]
M
. K
i
m
a
nd
I
. T
a
gkopoul
os
,
“
D
a
t
a
i
nt
e
gr
a
t
i
on a
nd pr
e
di
c
t
i
ve
m
ode
l
i
ng m
e
t
hod
s
f
or
m
ul
t
i
-
om
i
c
s
da
t
a
s
e
t
s
,”
M
ol
e
c
ul
ar
O
m
i
c
s
,
vol
.
14, no. 1, pp. 8
–
25, 2018, doi
:
10.1039/
c
7m
o00051k.
[
15]
Q
. X
i
a
o
e
t
al
.
, “
H
i
gh
-
t
hr
oughput
pr
ot
e
om
i
c
s
a
nd A
I
f
or
c
a
nc
e
r
bi
om
a
r
ke
r
di
s
c
o
ve
r
y,”
A
dv
anc
e
d D
r
ug D
e
l
i
v
e
r
y
R
e
v
i
e
w
s
,
vol
. 176
,
2021, doi
:
10.1016/
j
.a
ddr
.2021.113844.
[
16]
N
.
B
i
s
w
a
s
a
nd
S
.
C
ha
kr
a
ba
r
t
i
,
“
A
r
t
i
f
i
c
i
a
l
I
nt
e
l
l
i
ge
nc
e
(
A
I
)
-
ba
s
e
d
s
ys
t
e
m
s
bi
ol
ogy
a
ppr
oa
c
he
s
i
n
m
ul
t
i
-
om
i
c
s
da
t
a
a
na
l
ys
i
s
of
c
a
nc
e
r
,”
F
r
ont
i
e
r
s
i
n O
nc
ol
ogy
, vol
. 10, 2020, doi
:
10.3389/
f
onc
.2020.588221.
[
17]
M
.
A
gr
a
w
a
l
a
nd
V
.
J
a
i
n,
“
A
m
a
c
hi
ne
l
e
a
r
ni
ng
ba
s
e
d
a
ppr
oa
c
h
f
or
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
t
i
on,”
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
A
ut
om
at
i
on, C
om
put
i
ng and R
e
ne
w
abl
e
Sy
s
t
e
m
s
, I
C
A
C
R
S 2022
, pp. 623
–
626,
2022, doi
:
10.1109/
I
C
A
C
R
S
55517.2022.10029256.
[
18]
J
a
m
a
l
,
J
.
H
.
A
nt
or
,
R
.
K
um
a
r
,
a
nd
P
.
R
a
ni
,
“
B
r
e
a
s
t
c
a
nc
e
r
pr
e
di
c
t
i
on
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
c
l
a
s
s
i
f
i
e
r
s
,”
5t
h
I
E
E
E
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on A
dv
anc
e
s
i
n Sc
i
e
nc
e
and T
e
c
hnol
ogy
, I
C
A
ST
2022
, pp. 456
–
459, 2022, doi
:
10.1109/
I
C
A
S
T
55766.2022.10039656.
[
19]
V
. N
. G
opa
l
, F
. A
.
-
T
ur
j
m
a
n, R
. K
um
a
r
, L
. A
na
nd, a
nd M
. R
a
j
e
s
h, “
F
e
a
t
ur
e
s
e
l
e
c
t
i
on a
nd c
l
a
s
s
i
f
i
c
a
t
i
on i
n br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
t
i
on
us
i
ng
I
oT
a
nd
m
a
c
hi
ne
l
e
a
r
ni
ng,”
M
e
as
ur
e
m
e
nt
:
J
our
nal
of
t
he
I
nt
e
r
nat
i
onal
M
e
as
ur
e
m
e
nt
C
onf
e
de
r
at
i
on
,
vol
.
178,
2021,
doi
:
10.1016/
j
.m
e
a
s
ur
e
m
e
nt
.2021.109442.
[
20]
S
.
T
onm
oy,
H
.
K
.
H
i
ya
,
M
.
Z
.
H
a
s
a
n,
K
.
M
.
Z
.
H
a
s
a
n,
a
nd
N
.
Z
a
ha
n,
“
B
r
e
a
s
t
c
a
nc
e
r
pr
e
di
c
t
i
on
w
i
t
h
ga
us
s
i
a
n
pr
oc
e
s
s
us
i
n
g
a
nt
hr
opom
e
t
r
i
c
pa
r
a
m
e
t
e
r
s
,”
2021
12t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
C
om
put
i
ng
C
om
m
uni
c
at
i
on
and
N
e
t
w
or
k
i
ng
T
e
c
hnol
ogi
e
s
,
I
C
C
C
N
T
2021
, 2021, doi
:
10.1109/
I
C
C
C
N
T
51525.2021.9579704.
[
21]
Y
.
J
.
T
s
e
ng
e
t
al
.
,
“
P
r
e
di
c
t
i
ng
br
e
a
s
t
c
a
nc
e
r
m
e
t
a
s
t
a
s
i
s
by
u
s
i
ng
s
e
r
um
bi
om
a
r
ke
r
s
a
nd
c
l
i
ni
c
opa
t
hol
ogi
c
a
l
d
a
t
a
w
i
t
h
m
a
c
hi
n
e
l
e
a
r
ni
ng
t
e
c
hnol
ogi
e
s
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
M
e
di
c
al
I
nf
or
m
at
i
c
s
,
vol
.
128,
pp.
79
–
86,
2019,
doi
:
10.1016/
j
.i
j
m
e
di
nf
.2019.05.003.
[
22]
W
.
S
he
ng
e
t
al
.
,
“
I
nva
s
i
ve
duc
t
a
l
br
e
a
s
t
c
a
nc
e
r
m
ol
e
c
ul
a
r
s
ubt
ype
pr
e
di
c
t
i
on
by
M
R
I
r
a
di
om
i
c
a
nd
c
l
i
ni
c
a
l
f
e
a
t
ur
e
s
ba
s
e
d
o
n
m
a
c
hi
ne
l
e
a
r
ni
ng,”
F
r
ont
i
e
r
s
i
n O
n
c
ol
ogy
, vol
. 12, 2022, doi
:
10.3389/
f
onc
.2022.964605.
[
23]
K
.
A
t
hi
r
a
a
nd
G
.
G
opa
kum
a
r
,
“
B
r
e
a
s
t
c
a
nc
e
r
s
t
a
ge
pr
e
di
c
t
i
on:
a
c
om
put
a
t
i
ona
l
a
ppr
oa
c
h
gui
de
d
by
t
r
a
ns
c
r
i
pt
om
e
a
na
l
ys
i
s
,”
M
ol
e
c
ul
ar
G
e
ne
t
i
c
s
and G
e
nom
i
c
s
, vol
. 297, no. 6, pp. 1467
–
1479, 2022, doi
:
10.1007/
s
00438
-
022
-
01932
-
z.
[
24]
J
. M
i
t
c
he
l
, K
. C
h
a
t
l
i
n, L
. T
ong, a
nd
M
.
D
. W
a
ng,
“
A
t
r
a
n
s
l
a
t
i
ona
l
pi
pe
l
i
ne
f
or
ove
r
a
l
l
s
ur
vi
va
l
pr
e
di
c
t
i
on of
br
e
a
s
t
c
a
nc
e
r
p
a
t
i
e
nt
s
by
de
c
i
s
i
on
-
l
e
ve
l
i
nt
e
gr
a
t
i
on
of
m
ul
t
i
-
om
i
c
s
da
t
a
,”
2019
I
E
E
E
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
B
i
oi
nf
or
m
at
i
c
s
and
B
i
om
e
di
c
i
ne
,
B
I
B
M
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
m
ac
hi
ne
l
e
ar
ni
ng bas
e
d f
r
am
e
w
o
r
k
f
or
b
r
e
as
t
c
an
c
e
r
p
r
e
di
c
ti
on us
in
g bi
om
ar
k
e
r
s
(
A
pur
v
a V
as
hi
s
t)
4351
2019
, pp. 1573
–
1580, 2019, doi
:
10.1109/
B
I
B
M
47256.2019.8983243.
[
25]
M
.
K
a
ne
hi
s
a
,
Y
.
S
a
t
o,
M
.
K
a
w
a
s
hi
m
a
,
M
.
F
ur
um
i
c
hi
,
a
nd
M
.
T
a
na
b
e
,
“
K
E
G
G
a
s
a
r
e
f
e
r
e
nc
e
r
e
s
our
c
e
f
or
ge
ne
a
nd
pr
ot
e
i
n
a
nnot
a
t
i
on,”
N
uc
l
e
i
c
A
c
i
ds
R
e
s
e
ar
c
h
, vol
. 44, no. D
1, pp. D
457
–
D
462, 2016, d
oi
:
10.1093/
na
r
/
gkv1070.
[
26]
N
.
A
.
A
buj
a
ba
l
a
nd
A
.
B
.
N
a
s
s
i
f
,
“
M
e
t
a
-
he
ur
i
s
t
i
c
a
l
gor
i
t
hm
s
-
ba
s
e
d
f
e
a
t
ur
e
s
e
l
e
c
t
i
on
f
or
br
e
a
s
t
c
a
nc
e
r
di
a
gnos
i
s
:
A
s
ys
t
e
m
a
t
i
c
r
e
vi
e
w
,”
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
l
e
c
t
r
i
c
al
,
C
om
put
e
r
,
C
o
m
m
uni
c
at
i
ons
and
M
e
c
hat
r
oni
c
s
E
ngi
ne
e
r
i
ng,
I
C
E
C
C
M
E
2022
,
2022, doi
:
10.1109/
I
C
E
C
C
M
E
55909.2022.9988285.
[
27]
D
.
M
.
C
a
m
a
c
ho,
K
.
M
.
C
ol
l
i
ns
,
R
.
K
.
P
ow
e
r
s
,
J
.
C
.
C
os
t
e
l
l
o,
a
nd
J
.
J
.
C
ol
l
i
ns
,
“
N
e
xt
-
ge
ne
r
a
t
i
on
m
a
c
hi
ne
l
e
a
r
ni
ng
f
o
r
bi
ol
og
i
c
a
l
ne
t
w
or
ks
,”
C
e
l
l
, vol
. 173, no. 7, pp. 1581
–
1592, J
un. 2018, doi
:
10.1016/
j
.c
e
l
l
.2018.05.015.
[
28]
M
. H
os
s
e
i
nz
a
d
e
h, A
. G
or
j
i
, A
.
F
.
J
ouz
da
ni
, S
.
M
. R
e
z
a
e
i
j
o, A
. R
a
hm
i
m
, a
nd M
.
R
. S
a
l
m
a
npour
,
“
P
r
e
di
c
t
i
on o
f
c
ogni
t
i
ve
de
c
l
i
ne
i
n
pa
r
ki
ns
on’
s
di
s
e
a
s
e
us
i
ng c
l
i
ni
c
a
l
a
nd D
A
T
S
P
E
C
T
i
m
a
gi
ng f
e
a
t
ur
e
s
, a
nd hybr
i
d m
a
c
hi
ne
l
e
a
r
ni
ng s
ys
t
e
m
s
,”
D
i
agnos
t
i
c
s
, vol
. 13,
no. 10, 2023, doi
:
10.3390/
di
a
gnos
t
i
c
s
13101691.
[
29]
S
.
H
e
yda
r
he
yda
r
i
,
M
.
J
.
T
.
B
i
r
ga
ni
,
a
nd
S
.
M
.
R
e
z
a
e
i
j
o,
“
A
ut
o
-
s
e
gm
e
nt
a
t
i
on
of
he
a
d
a
nd
ne
c
k
t
um
o
r
s
i
n
pos
i
t
r
on
e
m
i
s
s
i
on
t
om
ogr
a
phy i
m
a
ge
s
us
i
ng non
-
l
oc
a
l
m
e
a
ns
a
nd m
or
phol
ogi
c
a
l
f
r
a
m
e
w
or
ks
,”
P
o
l
i
s
h J
our
nal
of
R
adi
ol
ogy
, vol
.
88,
no. 1,
pp. e
364
–
e
369, 2023, doi
:
10.5114/
pj
r
.2023.130815.
[
30]
S
.
M
.
R
e
z
a
e
i
j
o,
N
.
C
he
ge
ni
,
F
.
B
.
N
a
e
i
ni
,
D
.
M
a
kr
i
s
,
a
nd
S
.
B
a
k
a
s
,
“
W
i
t
hi
n
-
m
oda
l
i
t
y
s
ynt
he
s
i
s
a
nd
nove
l
r
a
di
om
i
c
e
va
l
ua
t
i
on
of
br
a
i
n M
R
I
s
c
a
n
s
,”
C
anc
e
r
s
, vol
. 15, no. 14, 2023, doi
:
10.3390/
c
a
n
c
e
r
s
151435
65.
[
31]
H
. K
ha
nf
a
r
i
e
t
al
.
,
“
E
xpl
or
i
ng
t
he
e
f
f
i
c
a
c
y o
f
m
ul
t
i
-
f
l
a
vor
e
d
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
w
i
t
h r
a
di
om
i
c
s
a
nd de
e
p f
e
a
t
ur
e
s
f
or
pr
os
t
a
t
e
c
a
nc
e
r
gr
a
di
ng on m
pM
R
I
,”
B
M
C
M
e
di
c
al
I
m
agi
ng
, vol
. 23, no. 1, 2023, doi
:
10.1186
/
s
12880
-
023
-
01140
-
0.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
Apurva
Vashist
is
a
p
ostgraduate
student
in
Department
of
Comput
er
Science
an
d
Engineering, Sharda University. She has research interests in
the appli
cation of ML in medical
domain. She can be contacted a
t email: apurva
.vashist@
gmail.com
.
Anil Kumar S
agar
is curren
tly
working a
s Professor
in Depar
tmen
t of Compute
r
Scienc
e
and
Engine
ering
in
School
of
Engine
ering
and
Techn
ology,
S
harda
Univer
sity,
India.
He
obtained
his
doctorate
from
JNU,
New
Delhi
in
Ad
-
hoc
Networks.
He
obtained
his
B.E
.
in
Computer
Science
&
Enginee
ring
from
G
.
B
.
Pant
Engineering
Coll
ege
Pauri
Garhwal,
and
M.Tech
.
from JSS
ATE Noida. He
can be contacted at
email:
aksagar22@
gmail.co
m
.
Anjali
Goyal
is
an
Assistant
Professor
in
the
Department
of
Comput
er
Science
and
Engineering
at
School
of
Engineering
and
Technology,
Sharda
Univer
sity,
Greater
Noida.
She
possesses 7 years of teaching a
nd
research expe
rience. Her
research int
erests are in the are
as o
f
mining
software
repositories,
text
analytics,
and
machine
learning
.
S
he
has
published
several
research
papers
in
various
internatio
nal
conferences
and
journals
of
repute.
She
can
be
contacted
at email
:
anjali1@
sharda.ac.i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.