Natural
products
are
an
important
source
of
molecules
with
therapeutic
and
biotechnological
applications.However,
the
inherent
complexity
biological
matrices
increasing
rediscovery
rates
challenge
search
for
new
bioactive
compounds.Exploring
specimens
biodiversity
applying
computational
tools
imperative
identifying
promising
chemical
entities.In
this
study,
we
proposed
to
catalyze
prospecting
process
demonstrate
potential
Brazilian
cyanobacteria
as
a
molecules.Nine
strains
freshwater
were
cultivated,
extracted,
fractionated.Extracts
fractions
tested
cytotoxic
against
microcrustacean
Artemia
salina,
antiproliferative
human
melanoma
cell
lines,
Leishmania
(L.)
amazonensis
promastigotes.Samples
analyzed
in
parallel
via
UPLC-HRMS/MS.A
molecular
network
was
created
using
GNPS
platform.Dereplication
guided
by
DAFdiscovery,
tool
that,
through
fusion
information
from
LC-MS/MS
data
metadata
containing
obtained
bioassays,
indexed
which
features
correlate
activity.Annotation
followed
database
performed
SIRIUS
software.Brasilonema
octagenarum,
Anagnostidinema
amphibium,
Nostoc
sp.,
Komarekiella
atlantica
selected
following
approach
due
their
novelty
bioactivity.
Nature Machine Intelligence,
Journal Year:
2024,
Volume and Issue:
6(4), P. 437 - 448
Published: March 29, 2024
Abstract
Generative
machine
learning
models
have
attracted
intense
interest
for
their
ability
to
sample
novel
molecules
with
desired
chemical
or
biological
properties.
Among
these,
language
trained
on
SMILES
(Simplified
Molecular-Input
Line-Entry
System)
representations
been
subject
the
most
extensive
experimental
validation
and
widely
adopted.
However,
these
what
is
perceived
be
a
major
limitation:
some
fraction
of
strings
that
they
generate
are
invalid,
meaning
cannot
decoded
structure.
This
shortcoming
has
motivated
remarkably
broad
spectrum
work
designed
mitigate
generation
invalid
correct
them
post
hoc.
Here
I
provide
causal
evidence
produce
outputs
not
harmful
but
instead
beneficial
models.
show
provides
self-corrective
mechanism
filters
low-likelihood
samples
from
model
output.
Conversely,
enforcing
valid
produces
structural
biases
in
generated
molecules,
impairing
distribution
limiting
generalization
unseen
space.
Together,
results
refute
prevailing
assumption
reframe
as
feature,
bug.
Pharmaceuticals,
Journal Year:
2024,
Volume and Issue:
17(3), P. 283 - 283
Published: Feb. 22, 2024
Natural
products
(NPs)
have
played
a
vital
role
in
human
survival
for
millennia,
particularly
their
medicinal
properties.
Many
traditional
medicine
practices
continue
to
utilise
crude
plants
and
animal
treating
various
diseases,
including
inflammation.
In
contrast,
contemporary
focuses
more
on
isolating
drug-lead
compounds
from
NPs
develop
new
better
treatment
drugs
inflammatory
disorders
such
as
bowel
diseases.
There
is
an
ongoing
search
drug
leads
there
still
no
cure
many
conditions.
Various
approaches
technologies
are
used
discoveries
NPs.
This
review
comprehensively
anti-inflammatory
small
molecules
describes
the
key
strategies
identifying,
extracting,
fractionating
small-molecule
leads.
also
discusses
(i)
most
recently
available
techniques,
artificial
intelligence
(AI),
(ii)
machine
learning,
computational
discovery;
(iii)
provides
models
cell
lines
in-vitro
in-vivo
assessment
of
potential
Communications Chemistry,
Journal Year:
2024,
Volume and Issue:
7(1)
Published: April 18, 2024
Abstract
Natural
products
are
small
molecules
synthesized
by
fungi,
bacteria
and
plants,
which
historically
have
had
a
profound
effect
on
human
health
quality
of
life.
These
natural
evolved
over
millions
years
resulting
in
specific
biological
functions
that
may
be
interest
for
pharmaceutical,
agricultural,
or
nutraceutical
use.
Often
need
to
structurally
modified
make
them
suitable
applications.
Combinatorial
biosynthesis
is
method
alter
the
composition
enzymes
needed
synthesize
product
diversified
molecules.
In
this
review
we
discuss
different
approaches
combinatorial
via
engineering
fungal
biosynthetic
pathways.
We
highlight
knowledge
gained
from
these
studies
provide
examples
new-to-nature
bioactive
molecules,
including
using
combinations
non-fungal
enzymes.
Advanced Agrochem,
Journal Year:
2024,
Volume and Issue:
3(3), P. 185 - 187
Published: June 25, 2024
The
latest
review
published
in
Nature
Reviews
Drug
Discovery
by
Michael
W.
Mullowney
and
co-authors
focuses
on
the
use
of
artificial
intelligence
techniques,
specifically
machine
learning,
natural
product
drug
discovery.
authors
discussed
various
applications
AI
this
field,
such
as
genome
metabolome
mining,
structural
characterization
products,
predicting
targets
biological
activities
these
compounds.
They
also
highlighted
challenges
associated
with
creating
managing
large
datasets
for
training
algorithms,
well
strategies
to
address
obstacles.
Additionally,
examine
common
pitfalls
algorithm
offer
suggestions
avoiding
them.
Advanced Science,
Journal Year:
2024,
Volume and Issue:
11(39)
Published: Aug. 19, 2024
Abstract
Tuberculosis
(TB)
stands
as
the
second
most
fatal
infectious
disease
after
COVID‐19,
effective
treatment
of
which
depends
on
accurate
diagnosis
and
phenotyping.
Metabolomics
provides
valuable
insights
into
identification
differential
metabolites
for
However,
TB
phenotyping
remain
great
challenges
due
to
lack
a
satisfactory
metabolic
approach.
Here,
metabolomics‐based
diagnostic
method
rapid
detection
is
reported.
Serum
fingerprints
are
examined
via
an
automated
nanoparticle‐enhanced
laser
desorption/ionization
mass
spectrometry
platform
outstanding
by
its
speed
(measured
in
seconds),
minimal
sample
consumption
(in
nanoliters),
cost‐effectiveness
(approximately
$3).
A
panel
14
m
z
−1
features
identified
biomarkers
4
Based
acquired
biomarkers,
models
constructed
through
advanced
machine
learning
algorithms.
The
robust
model
yields
97.8%
(95%
confidence
interval
(CI),
0.964‐0.986)
area
under
curve
(AUC)
85.7%
CI,
0.806‐0.891)
AUC
In
this
study,
serum
biomarker
panels
revealed
develop
tool
with
desirable
performance
phenotyping,
may
expedite
implementation
end‐TB
strategy.
Pharmaceutics,
Journal Year:
2025,
Volume and Issue:
17(3), P. 315 - 315
Published: March 1, 2025
Chinese
materia
medica
(CMM)
refers
to
the
medicinal
substances
used
in
traditional
medicine.
In
recent
years,
CMM
has
become
globally
prevalent,
and
scientific
research
on
increasingly
garnered
attention.
Computer-aided
drug
design
(CADD)
been
employed
Western
medicine
for
many
contributing
significantly
its
progress.
However,
role
of
CADD
not
systematically
reviewed.
This
review
briefly
introduces
methods
from
perspectives
computational
chemistry
(including
quantum
chemistry,
molecular
mechanics,
mechanics/molecular
mechanics)
informatics
cheminformatics,
bioinformatics,
data
mining).
Then,
it
provides
an
exhaustive
discussion
applications
these
through
rich
cases.
Finally,
outlines
advantages
challenges
research.
conclusion,
despite
current
challenges,
still
offers
unique
over
experiments.
With
development
industry
computer
science,
especially
driven
by
artificial
intelligence,
is
poised
play
pivotal
advancing
