International Journal of Molecular Sciences,
Journal Year:
2023,
Volume and Issue:
24(14), P. 11265 - 11265
Published: July 10, 2023
Natural
products
provide
valuable
starting
points
for
new
drugs
with
unique
chemical
structures.
Here,
we
retrieve
and
join
the
LOTUS
natural
product
database
ChEMBL
interaction
to
explore
relations
rhythm
between
features
of
biotarget
spaces.
Our
analysis
revealed
biogenic
pathways
species
taxonomy.
Nitrogen-containing
were
more
likely
achieve
high
activity
have
a
higher
potential
become
candidate
compounds.
An
apparent
trend
existed
in
target
space
originating
from
different
biological
sources.
Highly
active
alkaloids
related
targets
neurodegenerative
or
neural
diseases.
Oligopeptides
polyketides
mainly
associated
protein
phosphorylation
HDAC
receptors.
Fatty
acids
readily
intervened
various
physiological
processes
involving
prostanoids
leukotrienes.
We
also
used
FusionDTA,
deep
learning
model,
predict
affinity
all
622
therapeutic
drug
targets,
exploring
products.
data
exploration
provided
global
perspective
on
gaps
chemobiological
compounds
through
systematic
prediction
their
space,
which
can
be
design
repurposing.
Artificial Intelligence Chemistry,
Journal Year:
2024,
Volume and Issue:
2(2), P. 100077 - 100077
Published: Aug. 31, 2024
Molecular
similarity
pervades
much
of
our
understanding
and
rationalization
chemistry.
This
has
become
particularly
evident
in
the
current
data-intensive
era
chemical
research,
with
measures
serving
as
backbone
many
Machine
Learning
(ML)
supervised
unsupervised
procedures.
Here,
we
present
a
discussion
on
role
molecular
drug
design,
space
exploration,
"art"
generation,
representations,
more.
We
also
discuss
more
recent
topics
similarity,
like
ability
to
efficiently
compare
large
libraries.
Journal of Chemical Information and Modeling,
Journal Year:
2025,
Volume and Issue:
65(1), P. 201 - 213
Published: Jan. 2, 2025
The
design
of
drugs
and
nutraceutics
that
mimic
microbial
metabolites
is
an
emerging
drug
modality
in
medicinal
chemistry
attempts
to
modulate
the
myriad
interactions
these
molecules
establish
with
host
proteins.
Understanding
how
interact
their
target
proteins
key
perform
a
rational
metabolite
mimetic
for
therapeutic
usage.
In
present
work,
we
address
this
question
by
analyzing
functional
groups
they
display
set
more
than
71K
protein–metabolite
from
PDB.
Significant
differences
group
distributions,
chemical
features,
co-occurrences
are
observed
distinct
subsets
molecules.
same
true
distributions
interaction
types.
By
correlating
both
data
sets,
able
explain
patterns
terms
patterns.
These
results
will
shed
light
on
novel
purposes.
Journal of Chemical Information and Modeling,
Journal Year:
2024,
Volume and Issue:
64(4), P. 1229 - 1244
Published: Feb. 15, 2024
Food
chemicals
have
a
fundamental
role
in
our
lives,
with
an
extended
impact
on
nutrition,
disease
prevention,
and
marked
economic
implications
the
food
industry.
The
number
of
chemical
compounds
public
databases
has
substantially
increased
past
few
years,
which
can
be
characterized
using
chemoinformatics
approaches.
We
other
groups
explored
libraries
containing
up
to
26,500
compounds.
This
study
aimed
analyze
contents,
diversity,
coverage
space
additives
and,
from
here
on,
components.
approach
components
addressed
this
is
database
more
than
70,000
compounds,
including
those
predicted
via
Nutrients,
Journal Year:
2022,
Volume and Issue:
14(22), P. 4810 - 4810
Published: Nov. 14, 2022
Nature
may
have
the
answer
to
many
of
our
questions
about
human,
animal,
and
environmental
health.
Natural
bioactives,
especially
when
harvested
from
sustainable
plant
food
sources,
provide
a
plethora
molecular
solutions
nutritionally
actionable,
chronic
conditions.
The
spectrum
these
conditions,
such
as
metabolic,
immune,
gastrointestinal
disorders,
has
changed
with
prolonged
human
life
span,
which
should
be
matched
an
appropriately
extended
health
would
in
turn
favour
more
care:
“adding
years
adding
years”.
To
date,
bioactive
peptides
been
undervalued
underexploited
ingredients
drugs.
future
translational
science
on
peptides—and
natural
bioactives
general—is
being
built
(a)
systems-level
rather
than
reductionist
strategies
for
understanding
their
interdependent,
at
times
synergistic,
functions;
(b)
leverage
artificial
intelligence
prediction
discovery,
thereby
significantly
reducing
time
idea
concept
finished
consumers
patients.
This
new
strategy
follows
path
benefit
definition
via
design
and,
eventually,
validation
production.
Journal of Chemical Information and Modeling,
Journal Year:
2024,
Volume and Issue:
64(17), P. 6778 - 6798
Published: Aug. 21, 2024
Human
gut
microbial
metabolites
are
currently
undergoing
much
research
due
to
their
involvement
in
multiple
biological
processes
that
important
for
health,
including
immunity,
metabolism,
nutrition,
and
the
nervous
system.
Metabolites
exert
effect
through
interaction
with
host
bacterial
proteins,
suggesting
use
of
"metabolite-mimetic"
molecules
as
drugs
nutraceutics.
In
present
work,
we
retrieve
analyze
full
set
published
interactions
these
compounds
human
microbiome-relevant
proteins
find
patterns
structure,
chemical
class,
target
origins.
addition,
virtual
screening
expand
(more
than
4-fold)
interactions,
validate
them
retrospective
analyses,
bioinformatic
tools
prioritize
based
on
relevance.
this
way,
fill
many
chemobiological
gaps
observed
data.
By
providing
expect
speed
up
clarification
space
by
reliable
predictions
fast,
focused
experimental
testing.
Journal of Cheminformatics,
Journal Year:
2023,
Volume and Issue:
15(1)
Published: Oct. 13, 2023
Abstract
Gut-targeted
drugs
provide
a
new
drug
modality
besides
that
of
oral,
systemic
molecules,
could
tap
into
the
growing
knowledge
gut
metabolites
bacterial
or
host
origin
and
their
involvement
in
biological
processes
health
through
interaction
with
targets
(bacterial
host,
too).
Understanding
properties
can
guidance
for
design
gut-targeted
drugs.
In
present
work
we
analyze
large
set
metabolites,
both
shared
serum
only
gut,
compare
them
oral
We
find
patterns
specific
these
two
subsets
be
used
to
targeting
gut.
addition,
develop
openly
share
Super
Learner
model
predict
permanence,
order
aid
molecules
appropriate
profiles
remain
resulting
putatively
reduced
secondary
effects
better
pharmacokinetics.
Human
gut
microbial
metabolites
are
currently
undergoing
much
research
due
to
their
involvement
in
multiple
biological
processes
important
for
health,
including
immunity,
metabolism,
nutrition,
and
the
nervous
system.
Metabolites
exert
effect
through
interaction
with
host
bacterial
proteins,
suggesting
use
of
“metabolite-mimetic”
molecules
as
drugs
nutraceutics.
In
present
work,
we
retrieve
analyze
full
set
published
interactions
these
compounds
human
microbiome-relevant
find
patterns
structure,
chemical
class,
target
origins.
addition,
virtual
screening
expand
(>
4-fold)
interactions,
validate
them
retrospective
analyses,
bioinformatic
tools
prioritize
based
on
relevance.
this
way,
fill
many
chemobiological
gaps
observed
data.
By
providing
expect
speed
up
clarification
space
compounds,
by
reliable
predictions
fast,
focused
experimental
testing.
Deleted Journal,
Journal Year:
2024,
Volume and Issue:
27
Published: June 12, 2024
La
Quimioinformática
y
la
Inteligencia
Artificial
(IA)
son
disciplinas
con
métodos
que,
actualmente,
contribuyen
al
desarrollo
de
varias
áreas
del
conocimiento
Química,
por
medio
almacenamiento,
organización,
búsqueda
datos
químicos,
el
procesamiento
modelado,
para
generar
información
a
nivel
molecular
las
relaciones
estructura-propiedad
los
compuestos
químicos
existentes
determinar
propiedades
nuevos,
partir
diseño
base
en
un
perfil
deseado.
Todas
estas
técnicas
se
han
utilizado
Química
Alimentos,
lo
que
objetivo
este
artículo
es
analizar
bases
Quimioinformáticos
IA
su
aplicación
estudio
alimentos.
Gut-targeted
drugs
provide
a
new
drug
modality
besides
that
of
oral,
systemic
molecules,
could
tap
from
the
growing
knowledge
gut
metabolites
bacterial
or
host
origin
and
their
involvement
in
biological
processes
health
through
interaction
with
targets
(bacterial
host,
too).
Understanding
properties
can
hints
for
design
gut-targeted
drugs.
In
present
work
we
analyze
large
set
metabolites,
both
shared
serum
only
gut,
compare
them
oral
We
find
patterns
specific
these
two
subsets
be
used
to
targeting
gut.
addition,
develop
openly
share
Super
Learner
model
predict
permanence,
order
aid
molecules
appropriate
profiles
remain
resulting
putatively
reduced
secondary
effects
distribution
issues.