Advances in innovative extraction techniques for polysaccharides, peptides, and polyphenols from distillery by-products: Common extraction techniques, emerging technologies, and AI-driven optimization
Food Chemistry,
Год журнала:
2025,
Номер
476, С. 143326 - 143326
Опубликована: Фев. 18, 2025
Язык: Английский
From pages to patterns: Towards extracting catalytic knowledge from structure and text for transition-metal complexes and metal-organic frameworks
Journal of Catalysis,
Год журнала:
2025,
Номер
unknown, С. 116174 - 116174
Опубликована: Май 1, 2025
Язык: Английский
Empowering Generalist Material Intelligence with Large Language Models
Advanced Materials,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 12, 2025
Abstract
Large
language
models
(LLMs)
are
steering
the
development
of
generalist
materials
intelligence
(GMI),
a
unified
framework
integrating
conceptual
reasoning,
computational
modeling,
and
experimental
validation.
Central
to
this
is
agent‐in‐the‐loop
paradigm,
where
LLM‐based
agents
function
as
dynamic
orchestrators,
synthesizing
multimodal
knowledge,
specialized
models,
robotics
enable
fully
autonomous
discovery.
Drawing
from
comprehensive
review
LLMs’
transformative
impact
across
representative
applications
in
science,
including
data
extraction,
property
prediction,
structure
generation,
synthesis
planning,
self‐driven
labs,
study
underscores
how
LLMs
revolutionizing
traditional
tasks,
catalyzing
bridging
ontology‐concept‐computation‐experiment
continuum.
Then
unique
challenges
scaling
up
LLM
adoption
discussed,
particularly
those
arising
misalignment
foundation
with
materials‐specific
emphasizing
need
enhance
adaptability,
efficiency,
sustainability,
interpretability,
trustworthiness
pursuit
GMI.
Nonetheless,
it
important
recognize
that
not
universally
efficient.
Their
substantial
resource
demands
inconsistent
performance
call
for
careful
deployment
based
on
demonstrated
task
suitability.
To
address
these
realities,
actionable
strategies
progressive
roadmap
equitably
democratically
implementing
materials‐aware
real‐world
practices
proposed.
Язык: Английский
A framework for evaluating the chemical knowledge and reasoning abilities of large language models against the expertise of chemists
Nature Chemistry,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 20, 2025
Язык: Английский
NMRExtractor: leveraging large language models to construct an experimental NMR database from open-source scientific publications
Chemical Science,
Год журнала:
2025,
Номер
unknown
Опубликована: Янв. 1, 2025
NMRExtractor
is
a
large
language
model-powered
pipeline
that
automatically
extracts
experimental
NMR
data
from
massive
open-access
publications,
resulting
in
the
construction
of
NMRBank—the
largest
dataset
available
to
date.
Язык: Английский
Rapid SERS Analysis: From Laboratory to Real Sample
ACS Applied Materials & Interfaces,
Год журнала:
2025,
Номер
unknown
Опубликована: Июнь 2, 2025
On
the
50th
anniversary
of
discovery
surface-enhanced
Raman
spectroscopy
(SERS),
numerous
reviews
highlighted
SERS
advancements
from
different
aspects,
such
as
historical
evolution,
enhancement
mechanisms,
quantitative
analysis,
and
medical
applications.
However,
how
to
develop
rapid
analysis
for
real
samples
has
rarely
been
summarized
yet.
This
review
highlights
following
three
pivotal
steps
in
this
direction:
(1)
establishing
reliable
highly
selectively
sensitive
laboratory;
(2)
developing
sample
pretreatment;
(3)
AI-enhanced
qualitative
analysis.
Язык: Английский
Unlocking deep eutectic solvent knowledge through a large language model-driven framework and an interactive AI agent
Green Chemical Engineering,
Год журнала:
2025,
Номер
unknown
Опубликована: Июнь 1, 2025
Язык: Английский
Primacy Effect or Recency Effect? The Interplay of Travel Duration and Hedonic Trends in Multi-Destination Tourism
Journal of Travel Research,
Год журнала:
2024,
Номер
unknown
Опубликована: Дек. 29, 2024
This
study
delves
into
the
under-explored
dynamics
of
Primacy
and
Recency
effects
in
multi-destination
tourism,
utilizing
data
from
online
travelogs.
Focusing
on
attraction
sequences
(hedonic
trends)
travel
duration,
our
analysis
reveals
key
relationships
between
duration
tourists’
emotional
experiences.
We
found
that
longer
durations
lead
to
a
effect,
where
later
parts
journey
significantly
impact
overall
experience.
In
contrast,
shorter
demonstrate
with
initial
attractions
having
more
pronounced
influence.
These
findings
not
only
highlight
“dynamic”
transition
based
but
also
offer
practical
insights
for
itinerary
design,
aiming
enhance
tourist
satisfaction.
research
contributes
new
understanding
temporal
sequencing
their
experiences,
enriching
both
theoretical
aspects
tourism
management.
Язык: Английский