Bioengineering,
Год журнала:
2024,
Номер
11(11), С. 1148 - 1148
Опубликована: Ноя. 15, 2024
Annually,
many
people
worldwide
lose
their
lives
due
to
breast
cancer,
making
it
one
of
the
most
prevalent
cancers
in
world.
Since
disease
is
becoming
more
common,
early
detection
cancer
essential
avoiding
serious
complications
and
possibly
death
as
well.
This
research
provides
a
novel
Breast
Cancer
Discovery
(BCD)
strategy
aid
patients
by
providing
prompt
sensitive
cancer.
The
two
primary
steps
that
form
BCD
are
Step
(BCDS)
Pre-processing
(P
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Янв. 17, 2025
Drug
discovery
and
development
is
a
challenging
time-consuming
process.
Laboratory
experiments
conducted
on
Vidarabine
showed
IC50
6.97
µg∕mL,
25.78
˃
100
µg∕mL
against
non-small
Lung
cancer
(A-549),
Human
Melanoma
(A-375),
epidermoid
Skin
carcinoma
(skin/epidermis)
(A-431)
respectively.
To
address
these
challenges,
this
paper
presents
an
Artificial
Intelligence
(AI)
model
that
combines
the
capabilities
of
Deep
Learning
(DL)
to
identify
potential
new
drug
candidates,
Fuzzy
Rough
Set
(FRS)
theory
determine
most
important
chemical
compound
features,
Explainable
(XAI)
explain
features'
importance
in
last
layer,
medicinal
chemistry
rediscover
anticancer
drugs
based
natural
products
like
Vidarabine.
The
proposed
aims
candidates.
By
analyzing
results
from
laboratory
Vidarabine,
identifies
Sulfur
magnesium
oxide
(MgO)
as
agents.
selected
MgO
Interpreting
their
promising
further
were
validate
model's
predictions.
demonstrated
that,
while
was
inactive
A-431
cell
line
(IC50
µg∕mL),
exhibited
significant
activity
4.55
17.29
µg/ml
respectively).
displayed
strong
A-549
A-375
lines
3.06
1.86
respectively)
better
than
However,
weaker
two
lines.
This
emphasizes
uncovering
hidden
features
may
not
be
discernible
without
assistance
AI.
highlights
ability
AI
discover
novel
compounds
with
therapeutic
potential,
which
can
significantly
impact
field
discovery.
by
warrants
preclinical
studies.
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Апрель 23, 2025
The
Gazelle
Optimization
Algorithm
(GOA)
is
a
recently
proposed
and
widely
recognized
metaheuristic
algorithm.
However,
it
suffers
from
slow
convergence,
low
precision,
tendency
to
fall
into
local
optima
when
addressing
practical
problems.
To
address
these
limitations,
we
propose
Multi-Strategy
Improved
(MIGOA).
Key
enhancements
include
population
initialization
based
on
an
optimal
point
set,
tangent
flight
search
strategy,
adaptive
step
size
factor,
novel
exploration
strategies.
These
improvements
collectively
enhance
GOA's
capability,
convergence
speed,
effectively
preventing
becoming
trapped
in
optima.
We
evaluated
MIGOA
using
the
CEC2017
CEC2020
benchmark
test
sets,
comparing
with
GOA
eight
other
algorithms.
results,
validated
by
Wilcoxon
rank-sum
Friedman
mean
rank
test,
demonstrate
that
achieves
average
rankings
of
1.80,
2.03,
2.70
(Dim
=
30/50/100)
20),
respectively,
outperforming
standard
high-performance
optimizers.
Furthermore,
application
three-dimensional
unmanned
aerial
vehicle
(UAV)
path
planning
problems
2
engineering
optimization
design
further
validates
its
potential
solving
constrained
Experimental
results
consistently
indicate
exhibits
strong
scalability
applicability.
Biomimetics,
Год журнала:
2024,
Номер
9(10), С. 632 - 632
Опубликована: Окт. 17, 2024
Feature
selection
(FS)
is
a
pivotal
technique
in
big
data
analytics,
aimed
at
mitigating
redundant
information
within
datasets
and
optimizing
computational
resource
utilization.
This
study
introduces
an
enhanced
zebra
optimization
algorithm
(ZOA),
termed
FTDZOA,
for
superior
feature
dimensionality
reduction.
To
address
the
challenges
of
ZOA,
such
as
susceptibility
to
local
optimal
subsets,
limited
global
search
capabilities,
sluggish
convergence
when
tackling
FS
problems,
three
strategies
are
integrated
into
original
ZOA
bolster
its
performance.
Firstly,
fractional
order
strategy
incorporated
preserve
from
preceding
generations,
thereby
enhancing
ZOA's
exploitation
capabilities.
Secondly,
triple
mean
point
guidance
introduced,
amalgamating
point,
random
current
effectively
augment
exploration
prowess.
Lastly,
capacity
further
elevated
through
introduction
differential
strategy,
which
integrates
disparities
among
different
individuals.
Subsequently,
FTDZOA-based
method
was
applied
solve
23
problems
spanning
low,
medium,
high
dimensions.
A
comparative
analysis
with
nine
advanced
methods
revealed
that
FTDZOA
achieved
higher
classification
accuracy
on
over
90%
secured
winning
rate
exceeding
83%
terms
execution
time.
These
findings
confirm
reliable,
high-performance,
practical,
robust
method.
