Erik Maquoi
@erik-maquoi.bsky.social
Laboratory of Tumor & Development Biology - GIGA Institute - CIRM
University of Liège
Belgium
Cell biologist interested in #cancer #microenvironment - #fibroblasts - #ECM - #mechanobiology - #imaging - #drugscreening - #collagen
University of Liège
Belgium
Cell biologist interested in #cancer #microenvironment - #fibroblasts - #ECM - #mechanobiology - #imaging - #drugscreening - #collagen
Reposted by Erik Maquoi
Taking pictures of cells with a microscope, then extracting thousands of features from them is uncannily effective for quantifying cell state, esp. for genes and chemicals (e.g., Cell Painting). But we often average the rich single-cell data to simplify analysis. Can we do better?
#bioML 🧪
1/n
#bioML 🧪
1/n
![(a) Human U2OS cells treated with dimethyl sulfoxide (DMSO) and stained using the Cell Painting assay, which employs six dyes in five channels to label eight cellular compartments. The top row (from left to right) shows mitochondrial staining; actin, Golgi, and plasma membrane staining; and nucleolar and cytoplasmic RNA staining. The bottom row (from left to right) displays endoplasmic reticulum staining, DNA staining, and a montage of all five channels (from Cimini et al. [21]). (b) Thousands of features are extracted from each segmented cell in microscopy images of wells. A learned function f(x) (CytoSummaryNet) aggregates this data into a single feature vector: the sample’s profile. (c) An in-depth look at the model architecture used in this study. The model consists of three elements: a function φ(x), which maps the input data from ℝD to ℝL space, a summation, which collapses the cell dimension, and ρ(z), which maps the collapsed representation from ℝN to ℝL space. (d) During training, replicate compound profiles are forced to attract each other (green arrows) and simultaneously repel every other compound (red arrows) in the learned feature space. Here, all forces are drawn for a single profile of compound B.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:raswr6mjt7sbppdo6kcce4mz/bafkreicppuq2utmxkx5kpaggndigq7qcat6ppdqqajxhphpyi53ydlbbeq@jpeg)
December 19, 2024 at 11:31 PM
Taking pictures of cells with a microscope, then extracting thousands of features from them is uncannily effective for quantifying cell state, esp. for genes and chemicals (e.g., Cell Painting). But we often average the rich single-cell data to simplify analysis. Can we do better?
#bioML 🧪
1/n
#bioML 🧪
1/n
Reposted by Erik Maquoi
Just out! Exploring the Impact of Variability in Cell Segmentation and Tracking Approaches. Published in Microscopy Research and Technique. Thanks #BBSRC for funding.
see: doi.org/10.1002/jemt...
@laurawiggins13.bsky.social @globias.bsky.social @eurobioimaging.bsky.social
see: doi.org/10.1002/jemt...
@laurawiggins13.bsky.social @globias.bsky.social @eurobioimaging.bsky.social
Exploring the Impact of Variability in Cell Segmentation and Tracking Approaches
While manual segmentation and tracking of cells from microscopy images remain common practices in biological studies, our work demonstrates the inter- and intra-user variability that can arise from t...
doi.org
November 21, 2024 at 3:10 PM
Just out! Exploring the Impact of Variability in Cell Segmentation and Tracking Approaches. Published in Microscopy Research and Technique. Thanks #BBSRC for funding.
see: doi.org/10.1002/jemt...
@laurawiggins13.bsky.social @globias.bsky.social @eurobioimaging.bsky.social
see: doi.org/10.1002/jemt...
@laurawiggins13.bsky.social @globias.bsky.social @eurobioimaging.bsky.social
Reposted by Erik Maquoi
A forum for all things related to the cellular microenvironment and its role in health and disease. Spread the voice and drop a message if you want to join!
go.bsky.app/jhvVHF
November 19, 2024 at 4:18 PM
A forum for all things related to the cellular microenvironment and its role in health and disease. Spread the voice and drop a message if you want to join!
go.bsky.app/jhvVHF