Artificial Intelligence Approaches to Assessing Primary Cilia

Abstract

Cilia are microtubule based cellular appendages that function as signaling centers for a diversity of signaling pathways in many mammalian cell types. Cilia length is highly conserved, tightly regulated, and varies between different cell types and tissues and has been implicated in directly impacting their signaling capacity. For example, cilia have been shown to alter their lengths in response to activation of ciliary G protein-coupled receptors. However, accurately and reproducibly measuring the lengths of numerous cilia is a time-consuming and labor-intensive procedure. Current approaches are also error and bias prone. Artificial intelligence (Ai) programs can be utilized to overcome many of these challenges due to capabilities that permit assimilation, manipulation, and optimization of extensive data sets. Here, we demonstrate that an Ai module can be trained to recognize neuronal cilia in images from both in vivo and in vitro samples. After using our trained Ai to identify cilia, we are able to design and rapidly utilize applications that analyze hundreds of cilia in a single sample for length, fluorescence intensity and co-localization. This unbiased approach increased our confidence and rigor when comparing samples from different primary neuronal preps in vitro as well as across different brain regions within an animal and between animals. Moreover, this technique can be used to reliably analyze cilia dynamics from any cell type and tissue in a high-throughput manner across multiple samples and treatment groups. Ultimately, Ai-based approaches will likely become standard as most fields move toward less biased and more reproducible approaches for image acquisition and analysis.

Physiological Condition Dependent Changes in Ciliary GPCR Localization in the Brain

“…We confirmed our MCHR1 antibody immunofluorescence specificity by observing the loss of ciliary staining in a Mchr1 knockout allele mouse brain and colocalization with a Mchr1-mCherry knock-in fusion allele mouse ( Supplemental Figure 1A and B ) (Jasso, Kamba et al 2021). For our broader analysis of cilia localization, we utilized our recently reported computer-assisted approach for measuring cilia frequency, length, and fluorescence intensity (Bansal, Engle et al 2021). This approach offers the advantages of being less biased and higher throughput.…”

“…We chose an antibody staining approach combined with a computer assisted analysis as this combination was the best way to detect endogenous ciliary MCHR1 in an unbiased and high throughput manner allowing us to observe hundreds of cilia per animal (Bansal, Engle et al 2021, Jasso, Kamba et al 2021).…”

“…Image Analysis: Cilia analysis was performed as previously described (Bansal, Engle et al 2021). Briefly, sum projection images from captured z-stacks were analyzed using the artificial intelligence (Ai) module, which had been trained to recognize cilia in brain section images.…”

Regulation of the mouse ventral tegmental area by melanin-concentrating hormone

“…Our MCHR1 antibody (1:1,000; PA5-24182, Invitrogen, Carlsbad, CA) labeled MCHR1 immunoreactivity at the primary cilium of neurons (Diniz et al, 2020). Only cilia, identified by their long spindle-like appearance greater than 1 μm (Bansal et al, 2021;Diniz et al, 2020), associated with a NeuroTrace-labeled somata was counted as a MCHR1-expressing cell. Only TH staining at the somata that colocalized with DAPI-, NeuroTrace-, or EGFP-labeled cell was considered.…”