The One Click Wonder: a retrained automated segmentation pipeline that enables quantitative and modular analysis of C. elegans embryos
Bassett, P. C.; Verheijen, T. E.; Angonezi, A. L.; Andriollo, A.; Herbert, S.; Roth, G.; Chao, J.; Mango, S. E.
Show abstract
High-throughput approaches have transformed the study of gene regulation by enabling quantitative, genome-scale analyses in both genomics and imaging. However, applying these methods to intact organisms remains challenging, particularly for high-throughput, 3D imaging. In Caenorhabditis elegans, generalist segmentation models often perform poorly due to rapid changes in nuclear size, shape, and density. To overcome this obstacle, we developed One Click Wonder (OCW), an automated pipeline that pairs a retrained Cellpose model with stage-specific parameter selection to deliver accurate, high-throughput segmentation of embryos. We further introduce the Biological Annotation and Association Mapper (BAAM), which integrates segmentation with spot detection, to enable single-cell quantitation. Applied to the pioneer factor pha-4/FoxA, this pipeline revealed distinct cell populations with an eight-fold range in transcriptional burst frequency. These findings demonstrate that OCW and BAAM provide a modular, scalable pipeline for quantitative, single-cell analysis of gene expression in C. elegans embryos.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Deep Learning-Based High-Resolution Time Inference for Deciphering Dynamic Gene Regulation from Fixed Embryos 96%
- Mesmerize: a dynamically adaptable user-friendly analysis platform for 2D & 3D calcium imaging data. 96%
- Model-based prediction of spatial gene expression via generative linear mapping 95%
Similar papers in this journal
- ILoReg enables high-resolution cell population identification from single-cell RNA-seq data 94%
- Stitching and registering highly multiplexed whole slide images of tissues and tumors using ASHLAR 94%
- AFid: A tool for automated identification and exclusion of autofluorescent objects from microscopy images 94%
Similar papers in this journal
- Supervised and unsupervised deep learning-based approaches for studying DNA replication spatiotemporal dynamics 95%
- smiFISH and embryo segmentation for single-cell multi-gene RNA quantification in arthropods 95%
- UNSEG: unsupervised segmentation of cells and their nuclei in complex tissue samples 94%
Similar papers in this journal
- Interpretable trajectory inference with single-cell Linear Adaptive Negative-binomial Expression (scLANE) testing 95%
- Disentangling single-cell omics representation with a power spectral density-based feature extraction 95%
- Hybridization-based In Situ Sequencing (HybISS): spatial transcriptomic detection in human and mouse brain tissue 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.