Utilization of machine learning approach for production of optimized PLGA nanoparticles for drug delivery applications
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Март 14, 2025
This
study
investigates
utilization
of
machine
learning
for
the
regression
task
predicting
size
PLGA
(Poly
lactic-co-glycolic
acid)
nanoparticles.
Various
inputs
including
category
and
numeric
were
considered
building
model
to
predict
optimum
conditions
preparation
nanosized
particles
drug
delivery
applications.
The
proposed
methodology
employs
Leave-One-Out
(LOO)
categorical
feature
transformation,
Local
Outlier
Factor
(LOF)
outlier
detection,
Bat
Optimization
Algorithm
(BA)
hyperparameter
optimization.
A
comparative
analysis
compares
K-Nearest
Neighbors
(KNN),
ensemble
methods
such
as
Bagging
Adaptive
Boosting
(AdaBoost),
novel
Small-Size
Bat-Optimized
KNN
Regression
(SBNNR)
model,
which
uses
generative
adversarial
networks
deep
extraction
improve
performance
on
sparse
datasets.
Results
demonstrate
that
ADA-KNN
outperforms
other
models
Particle
Size
prediction
with
a
test
R²
0.94385,
while
SBNNR
achieves
superior
accuracy
in
Zeta
Potential
0.97674.
These
findings
underscore
efficacy
combining
advanced
preprocessing,
optimization,
techniques
robust
modeling.
contributions
this
work
include
development
validation
BA's
optimization
capabilities,
comprehensive
evaluation
methods.
method
provides
reliable
framework
using
material
science
applications,
particularly
nanoparticle
characterization.
Язык: Английский
Advances in Nanoparticles in Targeted Drug Delivery- A Review
Results in Surfaces and Interfaces,
Год журнала:
2025,
Номер
unknown, С. 100529 - 100529
Опубликована: Апрель 1, 2025
Язык: Английский
Intelligent Sensing Switches in Drug Delivery Systems: Mechanisms, Material Selection, and Future Perspectives
Journal of Biomedical Materials Research Part A,
Год журнала:
2025,
Номер
113(6)
Опубликована: Май 30, 2025
ABSTRACT
The
intelligence
and
controllability
of
drug
delivery
systems
(DDS)
are
crucial
for
enhancing
therapeutic
efficacy
minimizing
side
effects.
Among
these,
DDS
responsive
switches
play
a
pivotal
role
in
precisely
regulating
the
timing
spatial
distribution
release
response
to
specific
physiological
environments
within
body
or
external
stimuli.
Based
on
origin
stimuli,
they
can
be
categorized
into
endogenous
exogenous
This
paper
reviews
various
types
stimulus‐responsive
switches,
including
dual‐stimulus
elaborates
mechanisms
each
intelligent
switch.
It
summarizes
advantages
limitations
different
systems,
highlights
properties
commonly
used
temperature‐sensitive
materials,
discusses
applications
popular
nano‐engineered
materials
pH
electromagnetic‐responsive
switches.
Finally,
provides
an
outlook
future
DDS,
focusing
achieving
more
precise
control,
as
well
ensuring
clinical
stability
reliability.
Язык: Английский