JCO Clinical Cancer Informatics,
Journal Year:
2021,
Volume and Issue:
5, P. 709 - 718
Published: July 1, 2021
Early
discontinuation
affects
more
than
one
third
of
patients
enrolled
in
early-phase
oncology
clinical
trials.
is
deleterious
both
for
the
patient
and
study,
by
inflating
its
duration
associated
costs.
We
aimed
at
predicting
successful
screening
dose-limiting
toxicity
period
completion
(SSD)
from
automatic
analysis
consultation
reports.We
retrieved
reports
included
phase
I
and/or
II
trials
any
tumor
type
Gustave
Roussy,
France.
designed
a
preprocessing
pipeline
that
transformed
free
text
into
numerical
vectors
gathered
them
semantic
clusters.
These
document-based
were
then
fed
machine
learning
model
we
trained
to
output
binary
prediction
SSD
status.Between
September
2012
July
2020,
56,924
used
build
dictionary
1,858
or
inclusion
train
(72%),
validate
(14%),
test
(14%)
random
forest
model.
Preprocessing
could
efficiently
cluster
words
with
proximity.
On
unseen
cohort
264
reports,
performances
reached:
F1
score
0.80,
recall
0.81,
area
under
curve
0.88.
Using
this
model,
have
reduced
screen
fail
rate
(including
period)
39.8%
12.8%
(relative
risk,
0.322;
95%
CI,
0.209
0.498;
P
<
.0001)
within
cohort.
Most
important
clusters
predictions
comprised
related
hematologic
malignancies,
anatomopathologic
features,
laboratory
imaging
interpretation.Machine
conservation
promising
tool
assist
physicians
selecting
prone
achieve
Exploration of Targeted Anti-tumor Therapy,
Journal Year:
2024,
Volume and Issue:
5(2), P. 409 - 431
Published: April 25, 2024
Colorectal
cancer
(CRC)
is
a
heterogeneous
disease.
Conventional
two-dimensional
(2D)
culture
employing
cell
lines
was
developed
to
study
the
molecular
properties
of
CRC
in
vitro.
Although
these
which
are
isolated
from
tumor
niche
develop,
translation
human
model
such
as
studying
drug
response
often
hindered
by
inability
recapture
original
features
and
lack
clinical
tumors
represented
this
2D
model,
differed
vivo
condition.
These
limitations
may
be
overcome
utilizing
three-dimensional
(3D)
consisting
spheroids
organoids.
Over
past
decade,
great
advancements
have
been
made
optimizing
method
establish
organoids
solid
including
for
multiple
purposes
screening
establishing
personalized
medicine.
structures
proven
versatile
robust
models
progression
deciphering
its
heterogeneity.
This
review
will
describe
on
advances
3D
technology
application
well
challenges
CRC-derived
mode
screen
anticancer
drugs.
bioRxiv (Cold Spring Harbor Laboratory),
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 2, 2025
ABSTRACT
Proteolysis-targeting
chimeras
(PROTACs),
a
pioneering
class
of
heterobifunctional
ligands,
have
emerged
as
transformative
tools
in
combating
cancer
and
immune-related
diseases
due
to
their
ability
target
previously
undruggable
proteins
overcome
drug
resistance.
Accurate
assessment
the
degradation
potential
PROTACs
is
essential
for
advancing
therapeutic
applications.
However,
development
robust
predictive
models
hindered
by
scarcity
large-scale
datasets
domain-specific
tools,
well
underutilization
existing
unlabeled
data.
To
address
these
challenges,
we
developed
an
innovative
method
called
AiPROTAC
predict
capacity
PROTACs.
In
particular,
integrates
graph
augmentation,
message-passing
enhanced
encoders
cross-attention
mechanisms
within
contrastive
learning
framework.
Moreover,
leverages
curated
specialized
dataset
combined
with
PROTAC-DB
enhance
prediction
accuracy.
Experimental
results
across
two
six
evaluation
metrics
demonstrate
that
consistently
outperforms
state-of-the-art
models.
Further
case
studies
underline
its
superior
sensitivity
reliability.
Notably,
facilitated
design
novel
androgen
receptor
(AR)
degrader,
PROTAC
GT19,
which
achieved
vitro
compared
Bavdegalutamide
(ARV-110).
This
advancement
highlights
our
AiPROTAC’s
accelerate
PROTAC-based
optimization.
Frontiers in Pharmacology,
Journal Year:
2025,
Volume and Issue:
16
Published: March 25, 2025
Purpose
Bayesian
approaches
may
improve
the
efficiency
of
trials
and
accelerate
decision-making,
but
reluctance
to
depart
from
traditional
frequentist
statistics
limit
their
use.
Because
oncology
generally
involve
severe
conditions
with
no
or
limited
therapeutic
options,
they
are
well-suited
applying
methodologies
perceived
as
using
these
methods
often
in
early
phases.
Objectives
In
this
study,
we
aim
describe
use
designs
clinical
last
20
years.
Method
A
cross-sectional
observational
study
was
conducted
identify
registered
clinicaltrials.gov
between
2004
2024.
Trials
were
searched
,
PubMed,
through
manual
search
cross-references.
Results
retrieved,
main
characteristics
extracted
R
verified
manually.
Between
2024,
384,298
;
identified
84,850
(22%),
which
640
(0.75%)
used
approaches.
The
adoption
increased
significantly
after
2011,
while
half
all
studies
started
5
years,
paralleled
overall
increase
research
rather
than
an
proportion
trials.
majority
phase
1
2
studies,
two-thirds
efficacy
objectives
had
single-arm
designs,
utilizing
binary
endpoints,
such
response,
primary
measure.
Conclusion
uptake
has
flattened
is
still
scarce,
mostly
applied
analysis
treatment
endpoints.
There
room
for
further
potential
advantages
settings
small
populations
unmet
needs.
Clinical Pharmacology & Therapeutics,
Journal Year:
2021,
Volume and Issue:
110(1), P. 200 - 209
Published: Jan. 19, 2021
Despite
numerous
publications
emphasizing
the
value
of
dose
finding,
drug
development
in
oncology
is
dominated
by
mindset
that
higher
provides
efficacy.
Examples
finding
implemented
biopharmaceutical
firms
can
change
this
mindset.
The
purpose
article
to
outline
a
pragmatic
selection
strategy
for
immuno-oncology
(IO)
and
other
targeted
monoclonal
antibodies
(mAbs).
approach
was
pembrolizumab.
Selecting
recommended
phase
II
(RP2D)
with
novel
mechanism
action
often
challenging
due
uncertain
relationships
between
pharmacodynamics
measurements
clinical
end
points.
Additionally,
I
efficacy
safety
data
are
generally
inadequate
RP2D
IO
mAbs.
Here,
estimated
based
on
(clinical
study
KN001
A
A2)
pharmacokinetics
as
required
target
saturation,
which
represents
surrogate
maximal
pharmacological
effect
antagonist
Due
limitations
associated
collecting
analyzing
tumor
biopsies,
characterizing
intratumoral
engagement
(TE)
challenging.
To
overcome
gap,
physiologically-based
pharmacokinetic
model
predict
TE.
As
tumors
spatially
heterogeneous,
TE
predicted
well-vascularized
poorly
vascularized
regions.
impact
differences
expression,
example,
interindividual
variability
cancer
type,
simulated.
Simulations
showed
200
mg
every
3
weeks
achieve
≥
90%
clinically
relevant
scenarios,
resulting
recommendation
RP2D.
Randomized
comparison
studies
(KN001
B2
D)
showing
similar
over
fivefold
dose/exposure
range
confirmed
pivotal
dose.
Chinese Medical Journal,
Journal Year:
2021,
Volume and Issue:
134(11), P. 1267 - 1275
Published: May 19, 2021
Immunotherapy
has
opened
a
new
era
in
cancer
treatment.
Drugs
represented
by
immune
checkpoint
inhibitors
have
led
to
important
breakthroughs
the
treatment
of
various
solid
tumors,
greatly
improving
survival
rate
patients.
Many
types
immunotherapeutic
drugs
become
widely
available;
however,
their
efficacy
is
variable,
and
relatively
few
patients
with
advanced
experience
life-altering
durable
survival,
reflecting
complex
highly
regulated
nature
system.
The
research
field
immunotherapy
(CIT)
still
faces
many
challenges
pursuing
broader
social
goal
"curing
cancer."
Increasing
attention
been
paid
strengthening
understanding
molecular
or
cellular
drivers
resistance
immunotherapy,
actively
exploring
more
effective
therapeutic
targets,
developing
combination
therapy
strategies.
Here,
we
review
key
that
emerged
CIT
possible
solutions
development
directions
overcome
these
difficulties,
providing
relevant
references
for
basic
modified
clinical
regimens.
Pharmaceutical Statistics,
Journal Year:
2021,
Volume and Issue:
20(4), P. 783 - 792
Published: March 2, 2021
When
a
sponsor
carries
out
single-arm
trial
of
novel
oncology
compound,
it
may
wish
to
assess
the
efficacy
compound
via
comparison
overall
survival
an
external
control
arm,
constructed
using
patients
included
in
some
retrospective
registry.
If
is
compared
physician's
choice
chemotherapy,
registry
might
qualify
for
inclusion
arm
at
multiple
different
points
time,
when
they
receive
chemotherapy
treatments.
For
example,
patient
start
their
second,
third
and
fourth
lines
therapy.
From
which
line
therapy
should
this
patient's
be
participants
trial?
Some
sponsors
have
elected
include
from
last
available
database.
Another
possibility
randomly
select
each
among
those
available.
In
paper,
we
show,
probabilistic
arguments
also
simulation
based
on
real
data,
that
both
these
methods
give
rise
bias
favor
trial.
We
further
show
can
avoided
by
instead
including
times
once
time
qualifying
treatment.
Cells,
Journal Year:
2021,
Volume and Issue:
10(7), P. 1657 - 1657
Published: July 1, 2021
Cancer
is
a
disorder
characterized
by
an
uncontrollable
overgrowth
and
fast-moving
spread
of
cells
from
localized
tissue
to
multiple
organs
the
body,
reaching
metastatic
state.
Throughout
years,
complexity
cancer
progression
invasion,
high
prevalence
incidence,
as
well
rise
in
treatment
failure
cases
leading
poor
patient
prognosis
accounted
for
continuous
experimental
investigations
on
animals
cellular
models,
mainly
with
2D-
3D-cell
culture.
Nowadays,
these
research
models
are
considered
main
asset
reflect
physiological
events
many
types
terms
characteristics
features,
replication
mechanisms,
metabolic
pathways,
biomarkers
expression,
chemotherapeutic
agent
resistance.
In
practice,
based
perspective
hypothesis,
scientists
aim
choose
best
model
approach
their
understanding
prove
hypothesis.
Recently,
seen
be
highly
incorporated
crucial
tool
reflecting
true
cell
microenvironment
pharmacokinetic
pharmacodynamics
studies,
addition
intensity
anticancer
drug
response
pharmacogenomics
trials.
Hence,
this
review,
we
shed
light
unique
3D
favoring
its
promising
usage
through
comparative
other
specifically
2D-cell
Plus,
will
discuss
importance
direct
reflector
intrinsic
environment
newest
methods
available
3D-cells
implementation.
OMICS A Journal of Integrative Biology,
Journal Year:
2019,
Volume and Issue:
23(11), P. 517 - 538
Published: Oct. 15, 2019
This
expert
review
offers
a
critical
synthesis
of
the
latest
insights
and
approaches
at
targeting
Wnt/β-catenin
pathway
in
various
cancers
such
as
colorectal
cancer,
melanoma,
leukemia,
breast
lung
cancers.
Notably,
from
organogenesis
to
signaling
displays
varied
highly
versatile
biological
functions
animals,
with
virtually
all
tissues
requiring
one
way
or
other.
Aberrant
expression
members
has
been
implicated
many
pathological
conditions,
particularly
human
Mutations
genes
have
noted
diverse
Biochemical
genetic
data
support
idea
that
inhibition
is
beneficial
cancer
therapeutics.
The
interaction
this
important
other
systems
also
noteworthy,
but
remains
an
area
for
further
research
discovery.
In
addition,
formation
different
complexes
by
components
precise
roles
these
cytoplasmic
milieu
are
yet
be
fully
elucidated.
article
highlights
medical
technologies
imaging,
single-cell
omics,
use
artificial
intelligence
(e.g.,
machine
learning
techniques),
genome
sequencing,
quantum
computing,
molecular
docking,
computational
softwares
modeling
interactions
between
molecules
predicting
protein–protein
compound–protein
pertinent
biology
therapeutic
value
pathway.
We
discuss
emerging
relationship
what
currently
needed
move
concept
actionable
strategies
translating
laboratory
discoveries
Wnt-targeted
therapies
diagnostics
clinic.