Protein
sequence
design
in
the
context
of
small
molecules,
nucleotides
and
metals
is
critical
to
enzyme
small-molecule
binder
sensor
design,
but
current
state-of-the-art
deep-learning-based
methods
are
unable
model
nonprotein
atoms
molecules.
Here
we
describe
a
protein
method
called
LigandMPNN
that
explicitly
models
all
components
biomolecular
systems.
significantly
outperforms
Rosetta
ProteinMPNN
on
native
backbone
recovery
for
residues
interacting
with
molecules
(63.3%
versus
50.4%
50.5%),
(50.5%
35.2%
34.0%)
(77.5%
36.0%
40.6%).
generates
not
only
sequences
also
sidechain
conformations
allow
detailed
evaluation
binding
interactions.
has
been
used
over
100
experimentally
validated
DNA-binding
proteins
high
affinity
structural
accuracy
(as
indicated
by
four
X-ray
crystal
structures),
redesign
designs
increased
as
much
100-fold.
We
anticipate
will
be
widely
useful
designing
new
proteins,
sensors
enzymes.
Nature,
Год журнала:
2024,
Номер
630(8016), С. 493 - 500
Опубликована: Май 8, 2024
Abstract
The
introduction
of
AlphaFold
2
1
has
spurred
a
revolution
in
modelling
the
structure
proteins
and
their
interactions,
enabling
huge
range
applications
protein
design
2–6
.
Here
we
describe
our
3
model
with
substantially
updated
diffusion-based
architecture
that
is
capable
predicting
joint
complexes
including
proteins,
nucleic
acids,
small
molecules,
ions
modified
residues.
new
demonstrates
improved
accuracy
over
many
previous
specialized
tools:
far
greater
for
protein–ligand
interactions
compared
state-of-the-art
docking
tools,
much
higher
protein–nucleic
acid
nucleic-acid-specific
predictors
antibody–antigen
prediction
AlphaFold-Multimer
v.2.3
7,8
Together,
these
results
show
high-accuracy
across
biomolecular
space
possible
within
single
unified
deep-learning
framework.
Deep-learning
methods
have
revolutionized
protein
structure
prediction
and
design
but
are
presently
limited
to
protein-only
systems.
We
describe
RoseTTAFold
All-Atom
(RFAA),
which
combines
a
residue-based
representation
of
amino
acids
DNA
bases
with
an
atomic
all
other
groups
model
assemblies
that
contain
proteins,
nucleic
acids,
small
molecules,
metals,
covalent
modifications,
given
their
sequences
chemical
structures.
By
fine-tuning
on
denoising
tasks,
we
developed
RFdiffusion
(RFdiffusionAA),
builds
structures
around
molecules.
Starting
from
random
distributions
acid
residues
surrounding
target
designed
experimentally
validated,
through
crystallography
binding
measurements,
proteins
bind
the
cardiac
disease
therapeutic
digoxigenin,
enzymatic
cofactor
heme,
light-harvesting
molecule
bilin.
Cell,
Год журнала:
2024,
Номер
187(3), С. 526 - 544
Опубликована: Фев. 1, 2024
Methods
from
artificial
intelligence
(AI)
trained
on
large
datasets
of
sequences
and
structures
can
now
"write"
proteins
with
new
shapes
molecular
functions
de
novo,
without
starting
found
in
nature.
In
this
Perspective,
I
will
discuss
the
state
field
novo
protein
design
at
juncture
physics-based
modeling
approaches
AI.
New
folds
higher-order
assemblies
be
designed
considerable
experimental
success
rates,
difficult
problems
requiring
tunable
control
over
conformations
precise
shape
complementarity
for
recognition
are
coming
into
reach.
Emerging
incorporate
engineering
principles-tunability,
controllability,
modularity-into
process
beginning.
Exciting
frontiers
lie
deconstructing
cellular
and,
conversely,
constructing
synthetic
signaling
ground
up.
As
methods
improve,
many
more
challenges
unsolved.
bioRxiv (Cold Spring Harbor Laboratory),
Год журнала:
2024,
Номер
unknown
Опубликована: Март 18, 2024
Despite
the
central
role
that
antibodies
play
in
modern
medicine,
there
is
currently
no
way
to
rationally
design
novel
bind
a
specific
epitope
on
target.
Instead,
antibody
discovery
involves
time-consuming
immunization
of
an
animal
or
library
screening
approaches.
Here
we
demonstrate
fine-tuned
RFdiffusion
network
capable
designing
de
novo
variable
heavy
chains
(VHH's)
user-specified
epitopes.
We
experimentally
confirm
binders
four
disease-relevant
epitopes,
and
cryo-EM
structure
designed
VHH
bound
influenza
hemagglutinin
nearly
identical
model
both
configuration
CDR
loops
overall
binding
pose.
ACS Central Science,
Год журнала:
2024,
Номер
10(2), С. 226 - 241
Опубликована: Фев. 5, 2024
Enzymes
can
be
engineered
at
the
level
of
their
amino
acid
sequences
to
optimize
key
properties
such
as
expression,
stability,
substrate
range,
and
catalytic
efficiency-or
even
unlock
new
activities
not
found
in
nature.
Because
search
space
possible
proteins
is
vast,
enzyme
engineering
usually
involves
discovering
an
starting
point
that
has
some
desired
activity
followed
by
directed
evolution
improve
its
"fitness"
for
a
application.
Recently,
machine
learning
(ML)
emerged
powerful
tool
complement
this
empirical
process.
ML
models
contribute
(1)
discovery
functional
annotation
known
protein
or
generating
novel
with
functions
(2)
navigating
fitness
landscapes
optimization
mappings
between
associated
values.
In
Outlook,
we
explain
how
complements
discuss
future
potential
improved
outcomes.
AlphaFold2
(AF2)
models
have
had
wide
impact
but
mixed
success
in
retrospective
ligand
recognition.
We
prospectively
docked
large
libraries
against
unrefined
AF2
of
the
σ
Biomolecules,
Год журнала:
2024,
Номер
14(3), С. 339 - 339
Опубликована: Март 12, 2024
Recent
advancements
in
AI-driven
technologies,
particularly
protein
structure
prediction,
are
significantly
reshaping
the
landscape
of
drug
discovery
and
development.
This
review
focuses
on
question
how
these
technological
breakthroughs,
exemplified
by
AlphaFold2,
revolutionizing
our
understanding
function
changes
underlying
cancer
improve
approaches
to
counter
them.
By
enhancing
precision
speed
at
which
targets
identified
candidates
can
be
designed
optimized,
technologies
streamlining
entire
development
process.
We
explore
use
AlphaFold2
development,
scrutinizing
its
efficacy,
limitations,
potential
challenges.
also
compare
with
other
algorithms
like
ESMFold,
explaining
diverse
methodologies
employed
this
field
practical
effects
differences
for
application
specific
algorithms.
Additionally,
we
discuss
broader
applications
including
prediction
complex
structures
generative
design
novel
proteins.
Diagnostics,
Год журнала:
2024,
Номер
14(11), С. 1100 - 1100
Опубликована: Май 25, 2024
The
integration
of
artificial
intelligence
(AI)
into
point-of-care
(POC)
biosensing
has
the
potential
to
revolutionize
diagnostic
methodologies
by
offering
rapid,
accurate,
and
accessible
health
assessment
directly
at
patient
level.
This
review
paper
explores
transformative
impact
AI
technologies
on
POC
biosensing,
emphasizing
recent
computational
advancements,
ongoing
challenges,
future
prospects
in
field.
We
provide
an
overview
core
their
use
POC,
highlighting
issues
challenges
that
may
be
solved
with
AI.
follow
can
applied
including
machine
learning
algorithms,
neural
networks,
data
processing
frameworks
facilitate
real-time
analytical
decision-making.
explore
applications
each
stage
biosensor
development
process,
diverse
opportunities
beyond
simple
analysis
procedures.
include
a
thorough
outstanding
field
AI-assisted
focusing
technical
ethical
regarding
widespread
adoption
these
technologies,
such
as
security,
algorithmic
bias,
regulatory
compliance.
Through
this
review,
we
aim
emphasize
role
advancing
inform
researchers,
clinicians,
policymakers
about
reshaping
global
healthcare
landscapes.