Defining
the
binding
epitopes
of
antibodies
is
essential
for
understanding
how
they
bind
to
their
antigens
and
perform
molecular
functions.
However,
while
determining
linear
monoclonal
can
be
accomplished
utilizing
well-established
empirical
procedures,
these
approaches
are
generally
labor-and
time-intensive
costly.
To
take
advantage
recent
advances
in
protein
structure
prediction
algorithms
available
scientific
community,
we
developed
a
calculation
pipeline
based
on
localColabFold
implementation
AlphaFold2
that
predict
antibody
by
predicting
complex
between
heavy
light
chains
target
peptide
sequences
derived
from
antigens.
We
found
this
pipeline,
which
call
PAbFold,
was
able
accurately
flag
known
epitope
several
well-known
targets
(HA
/
Myc)
when
sequence
broken
into
small
overlapping
peptides
complementarity
regions
(CDRs)
were
grafted
onto
different
framework
single-chain
fragment
(scFv)
format.
determine
if
identify
novel
with
no
structural
information
publicly
available,
determined
anti-SARS-CoV-2
nucleocapsid
targeted
using
our
method
then
experimentally
validated
computational
results
competition
ELISA
assays.
These
indicate
AlphaFold2-based
PAbFold
capable
identifying
short
time
just
sequences.
This
emergent
capability
sensitive
methodological
details
such
as
length,
neural
network
versions,
multiple-sequence
alignment
database.
at
https://github.com/jbderoo/PAbFold.
Journal of Molecular Liquids,
Год журнала:
2023,
Номер
395, С. 123888 - 123888
Опубликована: Дек. 27, 2023
Efficient
drug
delivery
systems
(DDSs)
play
a
pivotal
role
in
ensuring
pharmaceuticals'
targeted
and
effective
administration.
However,
the
intricate
interplay
between
formulations
poses
challenges
their
design
optimization.
Simulations
have
emerged
as
indispensable
tools
for
comprehending
these
interactions
enhancing
DDS
performance
to
address
this
complexity.
This
comprehensive
review
explores
latest
advancements
simulation
techniques
provides
detailed
analysis.
The
encompasses
various
methodologies,
including
molecular
dynamics
(MD),
Monte
Carlo
(MC),
finite
element
analysis
(FEA),
computational
fluid
(CFD),
density
functional
theory
(DFT),
machine
learning
(ML),
dissipative
particle
(DPD).
These
are
critically
examined
context
of
research.
article
presents
illustrative
case
studies
involving
liposomal,
polymer-based,
nano-particulate,
implantable
DDSs,
demonstrating
influential
simulations
optimizing
systems.
Furthermore,
addresses
advantages
limitations
It
also
identifies
future
directions
research
development,
such
integrating
multiple
techniques,
refining
validating
models
greater
accuracy,
overcoming
limitations,
exploring
applications
personalized
medicine
innovative
DDSs.
employing
like
MD,
MC,
FEA,
CFD,
DFT,
ML,
DPD
offer
crucial
insights
into
behaviour,
aiding
Despite
advantages,
rapid
cost-effective
screening,
require
validation
addressing
limitations.
Future
should
focus
on
models,
enhance
outcomes.
paper
underscores
contribution
emphasizing
providing
valuable
facilitating
development
optimization
ultimately
patient
As
we
continue
explore
impact
advancing
discovery
improving
DDSs
is
expected
be
profound.
Biomarker Research,
Год журнала:
2025,
Номер
13(1)
Опубликована: Март 29, 2025
Antibodies
play
a
crucial
role
in
defending
the
human
body
against
diseases,
including
life-threatening
conditions
like
cancer.
They
mediate
immune
responses
foreign
antigens
and,
some
cases,
self-antigens.
Over
time,
antibody-based
technologies
have
evolved
from
monoclonal
antibodies
(mAbs)
to
chimeric
antigen
receptor
T
cells
(CAR-T
cells),
significantly
impacting
biotechnology,
diagnostics,
and
therapeutics.
Although
these
advancements
enhanced
therapeutic
interventions,
integration
of
artificial
intelligence
(AI)
is
revolutionizing
antibody
design
optimization.
This
review
explores
recent
AI
advancements,
large
language
models
(LLMs),
diffusion
models,
generative
AI-based
applications,
which
transformed
discovery
by
accelerating
de
novo
generation,
enhancing
response
precision,
optimizing
efficacy.
Through
advanced
data
analysis,
enables
prediction
sequences,
3D
structures,
complementarity-determining
regions
(CDRs),
paratopes,
epitopes,
antigen-antibody
interactions.
These
AI-powered
innovations
address
longstanding
challenges
development,
improving
speed,
specificity,
accuracy
design.
By
integrating
computational
with
biomedical
driving
next-generation
cancer
therapies,
transforming
precision
medicine,
patient
outcomes.
Defining
the
binding
epitopes
of
antibodies
is
essential
for
understanding
how
they
bind
to
their
antigens
and
perform
molecular
functions.
However,
while
determining
linear
monoclonal
can
be
accomplished
utilizing
well-established
empirical
procedures,
these
approaches
are
generally
labor-
time-intensive
costly.
To
take
advantage
recent
advances
in
protein
structure
prediction
algorithms
available
scientific
community,
we
developed
a
calculation
pipeline
based
on
localColabFold
implementation
AlphaFold2
that
predict
antibody
by
predicting
complex
between
heavy
light
chains
target
peptide
sequences
derived
from
antigens.
We
found
this
pipeline,
which
call
PAbFold,
was
able
accurately
flag
known
epitope
several
well-known
targets
(HA
/
Myc)
when
sequence
broken
into
small
overlapping
peptides
complementarity
regions
(CDRs)
were
grafted
onto
different
framework
single-chain
fragment
(scFv)
format.
determine
if
identify
novel
with
no
structural
information
publicly
available,
determined
anti-SARS-CoV-2
nucleocapsid
targeted
using
our
method
then
experimentally
validated
computational
results
competition
ELISA
assays.
These
indicate
AlphaFold2-based
PAbFold
capable
identifying
short
time
just
sequences.
This
emergent
capability
sensitive
methodological
details
such
as
length,
neural
network
versions,
multiple-sequence
alignment
database.
at
https://github.com/jbderoo/PAbFold.
Progress in Biomedical Engineering,
Год журнала:
2025,
Номер
7(2), С. 022004 - 022004
Опубликована: Фев. 5, 2025
Abstract
The
issue
of
antibiotic
resistance
is
increasing
with
time
because
the
quick
rise
microbial
strains.
Overuse
antibiotics
has
led
to
multidrug-resistant,
pan-drug-resistant,
and
extensively
drug-resistant
bacterial
strains,
which
have
worsened
situation.
Different
techniques
been
considered
applied
combat
this
issue,
such
as
developing
new
antibiotics,
practicing
stewardship,
improving
hygiene
levels,
controlling
overuse.
Vaccine
development
made
a
substantial
contribution
overcoming
although
it
underestimated.
In
recent
era,
reverse
vaccinology
contributed
different
kinds
vaccines
against
pathogens,
revolutionizing
vaccine
process.
Reverse
helps
prioritize
better
candidates
by
using
various
tools
filter
pathogen’s
complete
genome.
review,
we
will
shed
light
on
computational
designing,
immunoinformatic
tools,
genomic
proteomic
data,
challenges
success
stories
designing.
Briefings in Bioinformatics,
Год журнала:
2024,
Номер
25(4)
Опубликована: Май 23, 2024
Abstract
The
optimization
of
therapeutic
antibodies
through
traditional
techniques,
such
as
candidate
screening
via
hybridoma
or
phage
display,
is
resource-intensive
and
time-consuming.
In
recent
years,
computational
artificial
intelligence-based
methods
have
been
actively
developed
to
accelerate
improve
the
development
antibodies.
this
study,
we
an
end-to-end
sequence-based
deep
learning
model,
termed
AttABseq,
for
predictions
antigen–antibody
binding
affinity
changes
connected
with
antibody
mutations.
AttABseq
a
highly
efficient
generic
attention-based
model
by
utilizing
diverse
complex
sequences
input
predict
residue
assessment
on
three
benchmark
datasets
illustrates
that
120%
more
accurate
than
other
models
in
terms
Pearson
correlation
coefficient
between
predicted
experimental
changes.
Moreover,
also
either
outperforms
competes
favorably
structure-based
approaches.
Furthermore,
consistently
demonstrates
robust
predictive
capabilities
across
array
conditions,
underscoring
its
remarkable
capacity
generalization
wide
spectrum
antigen-antibody
complexes.
It
imposes
no
constraints
quantity
altered
residues,
rendering
it
particularly
applicable
scenarios
where
crystallographic
structures
remain
unavailable.
interpretability
analysis
indicates
causal
effects
point
mutations
antibody–antigen
can
be
visualized
at
level,
which
might
assist
automated
sequence
optimization.
We
believe
provides
fiercely
competitive
answer
