A semi-automated machine learning-aided approach to quantitative analysis of centrosomes and microtubule organization

“…We examined the distributions of centrosomal and centriolar satellite proteins whose splicing is affected by SON using a semi-automated radial intensity analysis algorithm in control and SON knockdown cells ( Figure 5A, B) (Sankaran et al, 2020). -tubulin, together withtubulin complex members, acts to nucleate microtubules and is concentrated at the centrosome (Stearns et al, 1991;Tovey & Conduit, 2018).…”

Section: Son Depletion Reduces Centriolar Satellites and Trafficking mentioning

confidence: 99%

“…For radial fluorescence intensity analyses, we utilized the algorithm described in Sankaran et al (Sankaran et al, 2020) using the PCM or microtubule analysis tool. Briefly, maximum intensity projected images were selected for analysis.…”

Section: Image Analysismentioning

confidence: 99%

“…Dysregulation of centrosome number can instigate cellular transformation to a cancerous state (Levine et al, 2017). More than two centrosomes results in chromosomal instability (Ganem et al, 2009;Silkworth et al, 2009;Zhang et al, 2015), altered cell migration (Godinho et al, 2014) and disruptions to the microtubule network (Godinho et al, 2014;Marteil et al, 2018;Sankaran et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The SON RNA splicing factor is required for intracellular trafficking that promotes centriole assembly

Stemm-Wolf

O’Toole

Sheridan

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Control of centrosome assembly is critical for cell division, intracellular trafficking and cilia. Regulation of centrosome number occurs through the precise duplication of centrioles that reside in centrosomes. Here we explored transcriptional control of centriole assembly and find that the RNA splicing factor SON is specifically required for completing procentriole assembly. Whole genome mRNA sequencing identified genes whose splicing and expression are affected by the reduction of SON, with an enrichment in genes involved in the microtubule cytoskeleton, centrosome and centriolar satellites. SON is required for the proper splicing and expression of CEP131 which encodes a major centriolar satellite protein and is required to organize the trafficking and microtubule network around the centrosomes. This study highlights the importance of the distinct microtubule trafficking network that is intimately associated with nascent centrioles and is responsible for procentriole development.

show abstract

“…Deep learning approaches represent an attractive alternative to alleviate these vulnerabilities, and such an approach has been in fact used to detect centrosomes [ 4 ]. Although both prior automated approaches use centriolar markers, they served to detect centrosomes, not centrioles and procentrioles per se .…”

Section: Introductionmentioning

confidence: 99%

CenFind: a deep-learning pipeline for efficient centriole detection in microscopy datasets

et al. 2023

View full text Add to dashboard Cite

Background High-throughput and selective detection of organelles in immunofluorescence images is an important but demanding task in cell biology. The centriole organelle is critical for fundamental cellular processes, and its accurate detection is key for analysing centriole function in health and disease. Centriole detection in human tissue culture cells has been achieved typically by manual determination of organelle number per cell. However, manual cell scoring of centrioles has a low throughput and is not reproducible. Published semi-automated methods tally the centrosome surrounding centrioles and not centrioles themselves. Furthermore, such methods rely on hard-coded parameters or require a multichannel input for cross-correlation. Therefore, there is a need for developing an efficient and versatile pipeline for the automatic detection of centrioles in single channel immunofluorescence datasets. Results We developed a deep-learning pipeline termed CenFind that automatically scores cells for centriole numbers in immunofluorescence images of human cells. CenFind relies on the multi-scale convolution neural network SpotNet, which allows the accurate detection of sparse and minute foci in high resolution images. We built a dataset using different experimental settings and used it to train the model and evaluate existing detection methods. The resulting average F1-score achieved by CenFind is > 90% across the test set, demonstrating the robustness of the pipeline. Moreover, using the StarDist-based nucleus detector, we link the centrioles and procentrioles detected with CenFind to the cell containing them, overall enabling automatic scoring of centriole numbers per cell. Conclusions Efficient, accurate, channel-intrinsic and reproducible detection of centrioles is an important unmet need in the field. Existing methods are either not discriminative enough or focus on a fixed multi-channel input. To fill this methodological gap, we developed CenFind, a command line interface pipeline that automates cell scoring of centrioles, thereby enabling channel-intrinsic, accurate and reproducible detection across experimental modalities. Moreover, the modular nature of CenFind enables its integration in other pipelines. Overall, we anticipate CenFind to prove critical for accelerating discoveries in the field.

show abstract

A semi-automated machine learning-aided approach to quantitative analysis of centrosomes and microtubule organization

Cited by 7 publications

References 64 publications

Trisomy 21 increases microtubules and disrupts centriolar satellite localization

Trisomy 21 increases microtubules and disrupts centriolar satellite localization

The SON RNA splicing factor is required for intracellular trafficking that promotes centriole assembly

CenFind: a deep-learning pipeline for efficient centriole detection in microscopy datasets

Contact Info

Product

Resources

About