Cell Genomics,
Journal Year:
2024,
Volume and Issue:
4(6), P. 100581 - 100581
Published: May 31, 2024
Cell
atlases
serve
as
vital
references
for
automating
cell
labeling
in
new
samples,
yet
existing
classification
algorithms
struggle
with
accuracy.
Here
we
introduce
SIMS
(scalable,
interpretable
machine
learning
single
cell),
a
low-code
data-efficient
pipeline
single-cell
RNA
classification.
We
benchmark
against
datasets
from
different
tissues
and
species.
demonstrate
SIMS's
efficacy
classifying
cells
the
brain,
achieving
high
accuracy
even
small
training
sets
(<3,500
cells)
across
samples.
accurately
predicts
neuronal
subtypes
developing
shedding
light
on
genetic
changes
during
differentiation
postmitotic
fate
refinement.
Finally,
apply
to
of
cortical
organoids
predict
identities
uncover
variations
between
lines.
identifies
cell-line
differences
misannotated
lineages
human
derived
pluripotent
stem
Altogether,
show
that
is
versatile
robust
tool
cell-type
datasets.
Nature Neuroscience,
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 21, 2025
Human
brain
development
requires
generating
diverse
cell
types,
a
process
explored
by
single-cell
transcriptomics.
Through
parallel
meta-analyses
of
the
human
cortex
in
(seven
datasets)
and
adulthood
(16
datasets),
we
generated
over
500
gene
co-expression
networks
that
can
describe
mechanisms
cortical
development,
centering
on
peak
stages
neurogenesis.
These
meta-modules
show
dynamic
subtype
specificities
throughout
with
several
developmental
displaying
spatiotemporal
expression
patterns
allude
to
potential
roles
fate
specification.
We
validated
these
modules
primary
tissues.
include
meta-module
20,
module
elevated
FEZF2+
deep
layer
neurons
includes
TSHZ3,
transcription
factor
associated
neurodevelopmental
disorders.
chimeroid
experiments
both
FEZF2
TSHZ3
are
required
drive
20
activity
neuron
specification
but
through
distinct
modalities.
studies
demonstrate
how
meta-atlases
engender
further
mechanistic
analyses
Development,
Journal Year:
2024,
Volume and Issue:
151(4)
Published: Feb. 15, 2024
ABSTRACT
The
generation
of
neurons
in
the
developing
neocortex
is
a
major
determinant
size.
Crucially,
increase
cortical
neuron
numbers
primate
lineage,
notably
upper-layer
neurons,
contributes
to
increased
cognitive
abilities.
Here,
we
review
evolutionary
changes
affecting
apical
progenitors
ventricular
zone
and
focus
on
key
germinal
constituting
foundation
neocortical
neurogenesis
primates,
outer
subventricular
(OSVZ).
We
summarize
characteristic
features
OSVZ
its
stem
cell
type,
basal
(or
outer)
radial
glia.
Next,
concentrate
primate-specific
human-specific
genes,
expressed
OSVZ-progenitors,
ability
which
amplify
these
by
targeting
regulation
cycle
ultimately
underlies
neurons.
Finally,
address
likely
differences
development
between
present-day
humans
Neanderthals
that
are
based
amino
acid
substitutions
proteins
operating
progenitors.
Cell Genomics,
Journal Year:
2024,
Volume and Issue:
4(6), P. 100581 - 100581
Published: May 31, 2024
Cell
atlases
serve
as
vital
references
for
automating
cell
labeling
in
new
samples,
yet
existing
classification
algorithms
struggle
with
accuracy.
Here
we
introduce
SIMS
(scalable,
interpretable
machine
learning
single
cell),
a
low-code
data-efficient
pipeline
single-cell
RNA
classification.
We
benchmark
against
datasets
from
different
tissues
and
species.
demonstrate
SIMS's
efficacy
classifying
cells
the
brain,
achieving
high
accuracy
even
small
training
sets
(<3,500
cells)
across
samples.
accurately
predicts
neuronal
subtypes
developing
shedding
light
on
genetic
changes
during
differentiation
postmitotic
fate
refinement.
Finally,
apply
to
of
cortical
organoids
predict
identities
uncover
variations
between
lines.
identifies
cell-line
differences
misannotated
lineages
human
derived
pluripotent
stem
Altogether,
show
that
is
versatile
robust
tool
cell-type
datasets.
