ChemCatChem,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 23, 2024
Abstract
The
advent
of
machine
learning
(ML)
has
significantly
advanced
enzyme
engineering,
particularly
through
zero‐shot
(ZS)
predictors
that
forecast
the
effects
amino
acid
mutations
on
properties
without
requiring
additional
labeled
data
for
target
enzyme.
This
review
comprehensively
summarizes
ZS
developed
over
past
decade,
categorizing
them
into
kinetic
parameters,
stability,
solubility/aggregation,
and
fitness.
It
details
algorithms
used,
encompassing
traditional
ML
approaches
deep
models,
emphasizing
their
predictive
performance.
Practical
applications
in
engineering
specific
enzymes
are
discussed.
Despite
notable
advancements,
challenges
persist,
including
limited
training
necessity
to
incorporate
environmental
factors
(e.g.,
pH,
temperature)
dynamics
these
models.
Future
directions
proposed
advance
prediction‐guided
thereby
enhancing
practical
utility
predictors.
Synthetic Communications,
Journal Year:
2025,
Volume and Issue:
unknown, P. 1 - 22
Published: Jan. 9, 2025
Biocatalysis
is
an
essential
tool
in
the
green
synthesis
of
compounds.
These
catalysts
exhibit
regioselectivity
and
stereoselectivity
toward
specific
products,
enabling
nontoxic
eco-friendly
synthetic
routes
with
high-yield
biotransformation
enantioselectivity,
resulting
enantiopure
products.
Moreover,
E-factor,
which
measures
efficiency
a
process
by
calculating
ratio
waste
generated
to
product
formed,
significantly
lower
biocatalytic
organic
than
traditional
methods.
The
reusability
biocatalysts
allows
for
economically
advantageous
designs,
reproducibility
products
better
yields
energy
route.
In
this
context,
enzymes
their
modified
counterparts
have
been
emphasized
as
asymmetric
bio-reduction
various
ketones,
aldehydes,
esters,
alcohols,
other
substrates.
Research Square (Research Square),
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 19, 2025
Abstract
Enzyme
catalytic
efficiency
(kcat
/
Km)
is
a
key
parameter
for
identifying
high-activity
enzymes.
Recently
deep
learning
techniques
have
demonstrated
the
potential
fast
and
accurate
kcatKm
prediction.
However,
three
challenges
remain:
(i)
limited
size
of
available
dataset
hinders
development
models;
(ii)
model
predictions
lacked
reliable
confidence
estimates;
(iii)
models
interpretable
insights
into
enzyme-catalyzed
reactions.
To
address
these
challenges,
we
proposed
IECata,
prediction
that
provides
uncertainty
estimation
interpretability.
IECata
collected
two
datasets
from
databases
literatures.
By
introducing
evidential
learning,
an
predictions.
Moreover,
it
uses
bilinear
attention
mechanism
to
focused
on
crucial
local
interactions
interpret
residues
substrate
atoms
in
Testing
results
indicate
performance
exceeds
state-of-the-art
benchmark
models.
Case
studies
further
highlight
incorporation
screening
highly
active
enzymes
can
effectively
reduce
false
positives,
thereby
improving
experimental
validation
accelerating
directed
enzyme
evolution.
public
usage
developed
online
platform:
http://mathtc.nscc-tj.cn/cataai/.
Microorganisms,
Journal Year:
2025,
Volume and Issue:
13(4), P. 820 - 820
Published: April 3, 2025
ω-Transaminases
are
biocatalysts
capable
of
asymmetrically
synthesizing
high-value
chiral
amines
through
the
reductive
amination
carbonyl
compounds,
and
they
ubiquitously
distributed
across
diverse
microorganisms.
Despite
their
broad
natural
occurrence,
industrial
utility
naturally
occurring
ω-transaminases
remains
constrained
by
limited
catalytic
efficiency
toward
sterically
bulky
substrates.
Over
recent
decades,
use
structure-guided
molecular
modifications,
leveraging
three-dimensional
structures,
mechanisms,
machine
learning-driven
predictions,
has
emerged
as
a
transformative
strategy
to
address
this
limitation.
Notably,
these
advancements
have
unlocked
unprecedented
progress
in
asymmetric
synthesis
amines,
which
is
exemplified
industrial-scale
production
sitagliptin
using
engineered
ω-transaminases.
This
review
systematically
explores
structural
mechanistic
foundations
ω-transaminase
engineering.
We
first
delineate
substrate
binding
regions
enzymes,
focusing
on
defining
features
such
tunnels
dual
pockets.
These
elements
serve
critical
targets
for
rational
design
enhance
promiscuity.
Next,
we
dissect
recognition
mechanisms
(S)-
(R)-ω-transaminases.
Drawing
insights,
consolidate
advances
engineering
highlight
performance
aim
guide
future
research
implementation
tailored
Abstract
A
(S)-selective
amine
transaminase
from
a
Streptomyces
strain,
Sbv333-ATA
is
biocatalyst
showing
both
high
thermostability
with
melting
temperature
of
85oC
and
broad
substrate
specificity
for
the
amino
acceptor.
This
enzyme
has
been
further
characterised
biochemically
structurally.
The
stable
in
presence
up
to
20%
(v/v)
water-miscible
cosolvents
methanol,
ethanol,
acetonitrile,
dimethyl
sulfoxide,
biphasic
systems
petroleum
ether,
toluene
ethyl
acetate
as
an
organic
phase.
showed
also
good
activity
towards
different
donors,
such
(S)-methylbenzylamine
2-phenylethylamine,
aliphatic
mono-
or
di-amines
like
propylamine,
cadaverine,
putrescine,
selected
acids.
However,
more
sterically
hindered
aromatic
amines
are
not
accepted.
Based
on
knowledge
three-dimensional
structures
obtained
rational
approach
site
specific
mutagenesis
carried
out
broaden
Sbv333-ATA.
mutant
W89A
highest
bulky
substrates,
diaromatic
compound
1,2-diphenylethylamine.
high-resolution
holo
inhibitor
gabaculine
bound
forms
native
Sbv333-ATA,
F61C
mutants
have
determined
at
resolutions
1.49,
1.24
1.31
(both
mutants)
Å
respectively.
These
important
revealing
details
active
binding
pockets
its
mechanism.
