Wiley Interdisciplinary Reviews Computational Molecular Science,
Год журнала:
2024,
Номер
14(3)
Опубликована: Май 1, 2024
Abstract
Structure‐based
drug
design
is
a
widely
applied
approach
in
the
discovery
of
new
lead
compounds
for
known
therapeutic
targets.
In
most
structure‐based
applications,
docking
procedure
considered
crucial
step.
Here,
potential
ligand
fitted
into
binding
site,
and
scoring
function
assesses
its
capability.
With
rise
modern
machine‐learning
discovery,
novel
functions
using
techniques
achieved
significant
performance
gains
virtual
screening
optimization
tasks
on
retrospective
data.
However,
real‐world
applications
these
methods
are
still
limited.
Missing
success
stories
prospective
one
reason
this.
Additionally,
fast‐evolving
nature
field
makes
it
challenging
to
assess
advantages
each
individual
method.
This
review
will
highlight
recent
strides
toward
improved
real
world
applicability
based
scoring,
enabling
better
understanding
benefits
pitfalls
project.
Furthermore,
systematic
way
classifying
that
facilitates
comparisons
be
presented.
article
categorized
under:
Data
Science
>
Chemoinformatics
Artificial
Intelligence/Machine
Learning
Software
Molecular
Modeling
Advances in media, entertainment and the arts (AMEA) book series,
Год журнала:
2024,
Номер
unknown, С. 1 - 63
Опубликована: Янв. 10, 2024
This
chapter
explores
AI's
influence
on
pharmaceutical
sciences,
highlighting
its
enhancement
of
traditional
design
methodologies.
It
transformational
role
in
key
sectors,
including
drug
discovery,
virtual
screening,
and
formulation
development.
ability
to
efficiently
identify
potential
candidates
from
large
chemical
libraries
use
optimization
algorithms
the
selection
suitable
excipients
dosage
forms
are
discussed.
The
also
emphasizes
significance
improving
manufacturing
processes
through
parameter
refinement,
quality
outcome
prediction,
real-time
anomaly
detection.
integration
methods
with
AI
ensures
robust,
reliable,
AI-driven
that
compliant
regulations.
In
conclusion,
highlights
sciences
importance
methods.
approach
empowers
scientists
innovate,
speed
up
development,
improve
patient
outcomes.
Future Journal of Pharmaceutical Sciences,
Год журнала:
2024,
Номер
10(1)
Опубликована: Апрель 7, 2024
Abstract
The
pharmaceutical
sector
has
recently
witnessed
a
transformative
improvement
and
shift
toward
artificial
intelligence
(AI)
in
its
drug
delivery
process
procedures.
Hence,
this
research
delves
into
the
benefits
obstacles
firms
face
utilizing
AI
China.
Globally,
China
is
recognized
as
dominant
pillar
development
industry.
country
incorporated
approaches
technologies
to
improve
industry’s
cost,
efficiency
development.
Therefore,
study
applies
case
method
evaluation
of
prior
studies
assess
AI’s
potential
challenges
enterprises.
provided
an
in-depth
various
phases
discovery
process.
outcome
indicated
that
include
repurposing,
target
identification,
clinical
trial
optimization,
quality
assurance,
control
efficient
distribution
method.
However,
analysis
revealed
faces
several
impact
pace
extent
integration
These
lack
standardized
data,
shortage
skilled
labor
or
professionals,
data
privacy
concerns.
In
addition,
provides
three
focused
on
f
XtalPi-AI-Enhanced
Drug
Discover,
BioMap:
Accelerating
Development
Through
iCarbonX:
AI-Driven
Precision
Medicine
comprehensive
how
these
have
used
stimulate
their
also
policies
can
help
Asian Journal of Pharmaceutical Sciences,
Год журнала:
2024,
Номер
19(4), С. 100943 - 100943
Опубликована: Июль 14, 2024
Inflammatory
bowel
diseases
(IBD)
significantly
contribute
to
high
mortality
globally
and
negatively
affect
patients'
qualifications
of
life.
The
gastrointestinal
tract
has
unique
anatomical
characteristics
physiological
environment
limitations.
Moreover,
certain
natural
or
synthetic
anti-inflammatory
drugs
are
associated
with
poor
targeting,
low
drug
accumulation
at
the
lesion
site,
other
side
effects,
hindering
them
from
exerting
their
therapeutic
effects.
Colon-targeted
delivery
systems
represent
attractive
alternatives
as
novel
carriers
for
IBD
treatment.
This
review
mainly
discusses
treatment
status
IBD,
obstacles
delivery,
design
strategies
colon-targeted
systems,
perspectives
on
existing
complementary
therapies.
based
recent
reports,
we
summarized
mechanism
delivery.
Finally,
addressed
challenges
future
directions
facilitate
exploitation
advanced
nanomedicine
therapy.
Archives of Gastroenterology Research,
Год журнала:
2024,
Номер
5(1), С. 1 - 10
Опубликована: Янв. 1, 2024
Background:
Liver
fibrosis
staging
is
critical
for
patient
selection
and
management
prior
to
transplantation,
but
biopsy
invasive
serum
biomarkers
lack
accuracy.
Near-infrared
spectroscopy
(NIRS)
an
emerging
non-invasive
technology
that
can
detect
liver
via
changes
in
tissue
composition.
Machine
learning
(ML)
enables
analysis
of
NIRS
data
diagnostic
modeling.
Purpose:
To
review
the
potential
NIRS-ML
approaches
rapid,
point-of-care
detection,
including
technological
principles,
promising
applications,
current
limitations,
future
directions.
Main
body
abstract:
leverages
unique
near-infrared
absorbance
patterns
reflecting
collagen
accumulation,
lipid
reduction,
other
chemical
alterations
fibrotic
liver.
Handheld/hyperspectral
systems
acquire
spectroscopic
minutes.
Multiple
human
studies
correlate
with
histological
scores.
ML
techniques
like
partial
least
squares
regression,
neural
networks,
support
vector
machines,
random
forests
analyze
spectra
develop
optimized
algorithms.
Initial
models
differentiate
mild
versus
advanced
stage
cirrhosis
high
accuracy,
outperforming
traditional
biomarkers.
Recent
advances
include
smartphone-based
scanning,
cloud
computing,
integrated
user-friendly
platforms.
However,
further
large
validation
trials,
standardization,
assessment
confounding
factors,
improved
methodology,
cost-effectiveness
are
required
before
widespread
clinical
implementation.
Conclusion:
With
ongoing
research
address
remaining
barriers,
hold
great
disruptive
quantification
fibrosis,
optimizing
transplant
surgery
planning
management.
Journal of Medicinal Chemistry,
Год журнала:
2024,
Номер
67(9), С. 7260 - 7275
Опубликована: Апрель 23, 2024
Artificial
intelligence
(AI)
de
novo
molecular
generation
is
a
highly
promising
strategy
in
the
drug
discovery,
with
deep
reinforcement
learning
(RL)
models
emerging
as
powerful
tools.
This
study
introduces
fragment-by-fragment
growth
RL
forward
and
optimization
based
on
low
activity
lead
compound.
process
integrates
fragment
growth-based
reaction
templates,
while
target
docking
drug-likeness
prediction
were
simultaneously
performed.
comprehensive
approach
considers
similarity,
internal
diversity,
synthesizability,
effectiveness,
thereby
enhancing
quality
efficiency
of
generation.
Finally,
series
tyrosinase
inhibitors
generated
synthesized.
Most
compounds
exhibited
more
improved
than
lead,
an
optimal
candidate
compound
surpassing
effects
kojic
acid
demonstrating
significant
antipigmentation
zebrafish
model.
Furthermore,
metabolic
stability
studies
indicated
susceptibility
to
hepatic
metabolism.
The
proposed
AI
structural
strategies
will
play
role
accelerating
discovery
improving
traditional
efficiency.
Advances in medical technologies and clinical practice book series,
Год журнала:
2024,
Номер
unknown, С. 42 - 86
Опубликована: Апрель 26, 2024
Addressing
the
critical
challenge
of
lengthy
and
costly
drug
development,
this
chapter
illuminates
transformative
role
advanced
artificial
intelligence
(AI)
in
discovery.
It
aims
to
dissect
impact
AI
methodologies
streamlining
these
traditionally
complex
processes.
This
begins
by
highlighting
inefficiencies
conventional
discovery
methods,
emphasizing
their
resource-intensive
nature.
An
in-depth
discussion
how
technologies
are
revolutionizing
identification
novel
targets,
optimizing
molecular
structures
candidates,
accurately
predicting
efficacy
toxicity
is
needed.
exploration
underscores
AI's
dual
advantages:
significantly
reducing
development
timelines
expenses
while
simultaneously
enhancing
precision
predictions,
leading
safer
more
effective
drugs.
concludes
with
a
vision
future
where
AI-driven
methods
fully
integrated
personalized
medicine
genomics,
signaling
onset
new
era
healthcare
therapeutic
innovation.
Expert Opinion on Drug Metabolism & Toxicology,
Год журнала:
2024,
Номер
20(7), С. 621 - 628
Опубликована: Май 14, 2024
This
review
explores
the
transformative
impact
of
machine
learning
(ML)
on
carcinogenicity
prediction
within
drug
development.
It
discusses
historical
context
and
recent
advancements,
emphasizing
significance
ML
methodologies
in
overcoming
challenges
related
to
data
interpretation,
ethical
considerations,
regulatory
acceptance.
Expert Opinion on Drug Discovery,
Год журнала:
2024,
Номер
19(8), С. 933 - 948
Опубликована: Июнь 18, 2024
Introduction
The
transition
from
conventional
cytotoxic
chemotherapy
to
targeted
cancer
therapy
with
small-molecule
anticancer
drugs
has
enhanced
treatment
outcomes.
This
approach,
which
now
dominates
treatment,
its
advantages.
Despite
the
regulatory
approval
of
several
molecules
for
clinical
use,
challenges
such
as
low
response
rates
and
drug
resistance
still
persist.
Conventional
discovery
methods
are
costly
time-consuming,
necessitating
more
efficient
approaches.
rise
artificial
intelligence
(AI)
access
large-scale
datasets
have
revolutionized
field
discovery.
Machine
learning
(ML),
particularly
deep
(DL)
techniques,
enables
rapid
identification
development
novel
agents
by
analyzing
vast
amounts
genomic,
proteomic,
imaging
data
uncover
hidden
patterns
relationships.
