Kinase-substrate prediction using an autoregressive model
Farzaneh Esmaili,
No information about this author
Yongfang Qin,
No information about this author
Duolin Wang
No information about this author
et al.
Computational and Structural Biotechnology Journal,
Journal Year:
2025,
Volume and Issue:
27, P. 1103 - 1111
Published: Jan. 1, 2025
Kinase-specific
phosphorylation
plays
a
critical
role
in
cellular
signaling
and
various
diseases.
However,
even
model
organisms,
the
substrates
of
most
kinases
remain
unidentified.
Currently,
there
is
no
reliable
method
to
predict
kinase-substrate
relationships.
In
this
study,
we
introduce
an
innovative
approach
leveraging
autoregressive
pairs.
Unlike
traditional
methods
focused
on
predicting
site-specific
phosphorylation,
our
addresses
kinase-specific
protein
substrate
prediction
at
level.
We
redefine
problem
as
special
type
protein-protein
interaction
task.
Our
integrates
large
language
ESM-2
encoder
employs
decoder
classify
protein-kinase
interactions
binary
fashion.
adopted
hard
negative
strategy,
based
kinase
embedding
distances
generated
from
ESM-2,
compel
effectively
distinguish
positive
data.
conducted
top‑k
analysis
assess
how
well
can
prioritize
likely
candidates.
also
capable
zero-shot
prediction,
meaning
it
for
case
known
substrates,
which
cannot
be
achieved
by
methods.
model's
robust
generalization
novel
underrepresented
groups
showcases
its
versatility
broad
utility.
Code
data
are
available
https://github.com/farz1995/substrate_kinase_prediction.
Language: Английский
Targeting senescence in Amyotrophic Lateral Sclerosis: senolytic treatment improves neuromuscular function and preserves cortical excitability in a TDP-43Q331K mouse model.
Research Square (Research Square),
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 26, 2025
Amyotrophic
lateral
sclerosis
(ALS)
is
a
fatal
neurodegenerative
disorder
marked
by
progressive
motor
neuron
degeneration
in
the
primary
cortex
(PMC)
and
spinal
cord.
Aging
key
factor
ALS
onset
progression,
with
evidence
suggesting
that
biological
aging-a
process
involving
cellular
decline-
far
outpaces
chronological
aging
ALS.
This
promotes
senescent
cell
accumulation-marked
irreversible
cell-cycle
arrest,
impaired
apoptosis,
chronic
inflammation-disrupting
tissue
homeostasis
impairing
neuronal
support
functions.
Thus,
targeting
senescence
presents
novel
therapeutic
strategy
for
Here,
we
investigated
senolytic
combination
Dasatinib
Quercetin
(D&Q)
TDP-43
Q331K
mice.
D&Q
improved
neuromuscular
function
reduced
plasma
neurofilament
light
chain,
biomarker
of
axonal
damage.
The
most
pronounced
improvement
was
cortical
excitability,
accompanied
reductions
PMC.
These
findings
highlight
potential
senolytics
to
mitigate
ALS-related
dysfunction,
supporting
their
viability
as
strategy.
*Jose
A.
Viteriab,
Nathan
R.
Kerrab,
Charles
D.
Brennana
are
co-first
authors.
Language: Английский