Molecules,
Год журнала:
2022,
Номер
27(19), С. 6453 - 6453
Опубликована: Сен. 30, 2022
Drug
repurposing
in
the
context
of
neuroimmunological
(NI)
investigations
is
still
its
primary
stages.
an
important
method
that
bypasses
lengthy
drug
discovery
procedures
and
focuses
on
discovering
new
usages
for
known
medications.
Neuroimmunological
diseases,
such
as
Alzheimer's,
Parkinson's,
multiple
sclerosis,
depression,
include
various
pathologies
result
from
interaction
between
central
nervous
system
immune
system.
However,
NI
medications
hindered
by
vast
amount
information
needs
mining.
We
previously
presented
Adera1.0,
which
was
capable
text
mining
PubMed
answering
query-based
questions.
Adera1.0
not
able
to
automatically
identify
chemical
compounds
within
relevant
sentences.
To
challenge
need
we
built
a
deep
neural
network
named
Adera2.0
perform
repurposing.
The
workflow
uses
three
learning
networks.
first
encoder
main
task
embed
into
matrices.
second
mean
squared
error
(MSE)
loss
function
predict
answers
form
embedded
third
network,
constitutes
novelty
our
updated
workflow,
also
MSE
function.
Its
usage
extract
compound
names
sentences
resulting
previous
network.
optimize
function,
compared
eight
different
designs.
found
consisting
RNN
leaky
ReLU
could
achieve
0.0001
67%
sensitivity.
Additionally,
validated
Adera2.0's
ability
against
DRUG
Repurposing
Hub
database.
These
results
establish
repurpose
candidates
can
shorten
development
cycle.
be
download
online.
Life,
Год журнала:
2024,
Номер
14(2), С. 233 - 233
Опубликована: Фев. 7, 2024
Drug
development
is
expensive,
time-consuming,
and
has
a
high
failure
rate.
In
recent
years,
artificial
intelligence
(AI)
emerged
as
transformative
tool
in
drug
discovery,
offering
innovative
solutions
to
complex
challenges
the
pharmaceutical
industry.
This
manuscript
covers
multifaceted
role
of
AI
encompassing
AI-assisted
delivery
design,
discovery
new
drugs,
novel
techniques.
We
explore
various
methodologies,
including
machine
learning
deep
learning,
their
applications
target
identification,
virtual
screening,
design.
paper
also
discusses
historical
medicine,
emphasizing
its
profound
impact
on
healthcare.
Furthermore,
it
addresses
AI’s
repositioning
existing
drugs
identification
combinations,
underscoring
potential
revolutionizing
systems.
The
provides
comprehensive
overview
programs
platforms
currently
used
illustrating
technological
advancements
future
directions
this
field.
study
not
only
presents
current
state
but
anticipates
trajectory,
highlighting
opportunities
that
lie
ahead.
Hepatology Communications,
Год журнала:
2023,
Номер
7(4)
Опубликована: Март 24, 2023
Since
its
release
as
a
“research
preview”
in
November
2022,
ChatGPT,
the
conversational
interface
to
Generative
Pretrained
Transformer
3
large
language
model
built
by
OpenAI,
has
garnered
significant
publicity
for
ability
generate
detailed
responses
variety
of
questions.
ChatGPT
and
other
models
sentences
paragraphs
response
word
patterns
training
data
that
they
have
previously
seen.
By
allowing
users
communicate
with
an
artificial
intelligence
human-like
way,
however,
crossed
technological
adoption
barrier
into
mainstream.
Existing
examples
use-cases,
such
negotiating
bills,
debugging
programing
code,
writing
essays,
indicate
similar
potential
profound
(and
yet
unknown)
impacts
on
clinical
research
practice
hepatology.
In
this
special
article,
we
discuss
general
background
pitfalls
associated
technologies—and
then
explore
uses
hepatology
specific
examples.
Artificial Intelligence Chemistry,
Год журнала:
2024,
Номер
2(2), С. 100071 - 100071
Опубликована: Июнь 12, 2024
Traditional
drug
discovery
struggles
to
keep
pace
with
the
ever-evolving
threat
of
infectious
diseases.
New
viruses
and
antibiotic-resistant
bacteria,
all
demand
rapid
solutions.
Artificial
Intelligence
(AI)
offers
a
promising
path
forward
through
accelerated
repurposing.
AI
allows
researchers
analyze
massive
datasets,
revealing
hidden
connections
between
existing
drugs,
disease
targets,
potential
treatments.
This
approach
boasts
several
advantages.
First,
repurposing
drugs
leverages
established
safety
data
reduces
development
time
costs.
Second,
can
broaden
search
for
effective
therapies
by
identifying
unexpected
new
targets.
Finally,
help
mitigate
limitations
predicting
minimizing
side
effects,
optimizing
repurposing,
navigating
intellectual
property
hurdles.
The
article
explores
specific
strategies
like
virtual
screening,
target
identification,
structure
base
design
natural
language
processing.
Real-world
examples
highlight
AI-driven
in
discovering
treatments
Journal of Global Health,
Год журнала:
2025,
Номер
15
Опубликована: Янв. 10, 2025
The
emergence
of
artificial
intelligence
(AI)
in
drug
discovery
represents
a
transformative
development
addressing
neglected
diseases,
particularly
the
context
developing
world.
Neglected
often
overlooked
by
traditional
pharmaceutical
research
due
to
limited
commercial
profitability,
pose
significant
public
health
challenges
low-
and
middle-income
countries.
AI-powered
offers
promising
solution
accelerating
identification
potential
candidates,
optimising
process,
reducing
time
cost
associated
with
bringing
new
treatments
market.
However,
while
AI
shows
promise,
many
its
applications
are
still
their
early
stages
require
human
validation
ensure
accuracy
reliability
predictions.
Additionally,
models
availability
high-quality
data,
which
is
sparse
regions
where
diseases
most
prevalent.
This
viewpoint
explores
application
for
examining
current
impact,
related
ethical
considerations,
broader
implications
It
also
highlights
opportunities
presented
this
context,
emphasising
need
ongoing
research,
oversight,
collaboration
between
stakeholders
fully
realise
transforming
global
outcomes.
Meta-analysis
of
randomized
clinical
trials
(RCTs)
plays
a
crucial
role
in
evidence-based
medicine
but
can
be
labor-intensive
and
error-prone.
This
study
explores
the
use
large
language
models
to
enhance
efficiency
aggregating
results
from
at
scale.
We
perform
detailed
comparison
performance
these
zero-shot
prompt-based
information
extraction
diverse
set
RCTs
traditional
manual
annotation
methods.
analyze
for
two
different
meta-analyses
aimed
drug
repurposing
cancer
therapy
pharmacovigilience
chronic
myeloid
leukemia.
Our
findings
reveal
that
best
model
demonstrated
tasks,
ChatGPT
generally
extract
correct
identify
when
desired
is
missing
an
article.
additionally
conduct
systematic
error
analysis,
documenting
prevalence
types
encountered
during
process
extraction.
Journal of Cheminformatics,
Год журнала:
2025,
Номер
17(1)
Опубликована: Янв. 29, 2025
G
protein-coupled
receptors
(GPCRs)
play
vital
roles
in
various
physiological
processes,
making
them
attractive
drug
discovery
targets.
Meanwhile,
deep
learning
techniques
have
revolutionized
by
facilitating
efficient
tools
for
expediting
the
identification
and
optimization
of
ligands.
However,
existing
models
GPCRs
often
focus
on
single-target
or
a
small
subset
employ
binary
classification,
constraining
their
applicability
high
throughput
virtual
screening.
To
address
these
issues,
we
introduce
AiGPro,
novel
multitask
model
designed
to
predict
molecule
agonists
(EC50)
antagonists
(IC50)
across
231
human
GPCRs,
it
first-in-class
solution
large-scale
GPCR
profiling.
Leveraging
multi-scale
context
aggregation
bidirectional
multi-head
cross-attention
mechanisms,
our
approach
demonstrates
that
ensemble
may
not
be
necessary
predicting
complex
states
interactions.
Through
extensive
validation
using
stratified
tenfold
cross-validation,
AiGPro
achieves
robust
performance
with
Pearson's
correlation
coefficient
0.91,
indicating
broad
generalizability.
This
breakthrough
sets
new
standard
studies,
outperforming
previous
studies.
Moreover,
multi-tasking
can
agonist
antagonist
activities
wide
range
offering
comprehensive
perspective
ligand
bioactivity
within
this
diverse
superfamily.
facilitate
easy
accessibility,
deployed
web-based
platform
access
at
https://aicadd.ssu.ac.kr/AiGPro
.
Scientific
Contribution
We
learning-based
multi-task
generalize
prediction
accurately.
The
is
implemented
user-friendly
web
server
rapid
screening
small-molecule
libraries,
GPCR-targeted
discovery.
Covering
set
targets,
delivers
robust,
scalable
advancing
GPCR-focused
therapeutic
development.
proposed
framework
incorporates
an
innovative
dual-label
strategy,
enabling
simultaneous
classification
molecules
as
agonists,
antagonists,
both.
Each
further
accompanied
confidence
score,
quantitative
measure
activity
likelihood.
advancement
moves
beyond
conventional
focusing
solely
binding
affinity,
providing
more
understanding
ligand-receptor
At
core
lies
Bi-Directional
Multi-Head
Cross-Attention
(BMCA)
module,
architecture
captures
forward
backward
contextual
embeddings
protein
features.
By
leveraging
BMCA,
effectively
integrates
structural
sequence-level
information,
ensuring
precise
representation
molecular
Results
show
highly
accurate
affinity
predictions
consistent
families.
unifying
into
single
architecture,
bridge
critical
gap
modeling.
enhances
accuracy
accelerates
workflows,
valuable
