Morphi: AI-driven phenotypic profiling for organoid screening

bioRxiv (preprint)

Overview

Morphi is an AI-driven framework that infers organoid viability and phenotypic states directly from label-free bright-field microscopy. By combining viability scores with unsupervised morphology and texture features, the system enables high-content, mechanism-aware drug screening across multiple tissue types.

In Depth

Key Findings

Morphi provides a unified, quantitative readout of organoid viability and phenotypic response. The framework can segment individual organoids from images to output a percentage viability score and a spatial death map, which identifies dead sub-organoid regions. These capabilities allow for the capture of graded cytotoxic responses at a single-organoid resolution.

Technical Details

The system utilizes an AI-driven approach to bypass the need for dense manual annotation by using fluorescence-based viability signals as weak supervision to train a pixel-level viability model. Beyond viability, Morphi integrates unsupervised morphology and texture features to embed each organoid into a high-dimensional phenotypic space.

These resulting “phenotypic fingerprints” provide several analytical capabilities:

• Capture of the dense phenotypic state of individual organoids.
• Analysis of population-level distributions across different perturbation conditions.
• Clustering of drugs based on their mechanism of action.
• Resolution of differences between mechanistically related drugs.
• Identification of phenotypic convergence across distinct perturbagens.

Background & Context

While organoids have improved in vitro modeling by more faithfully recapitulating native tissue architecture and providing physiological drug response readouts, the visualization and quantitative analysis of their phenotypes have remained underdeveloped. Morphi addresses this gap by offering a scalable, label-free strategy for profiling.

Significance & Outlook

The framework performs robustly across multiple tissue types, making it a viable tool for large-scale drug screening. By providing a mechanism-aware readout, Morphi enables researchers to move toward high-content screening that can distinguish between subtle drug effects and identify convergent phenotypic responses in organoid models.

Get our weekly technology intelligence — free

Receive an infographic that lets you judge at a glance whether each field’s analysis report is worth reading.

Subscribe Free — Weekly Tech Intelligence

By subscribing, you’ll receive Troy-Technical’s weekly technology intelligence newsletter.

• Your email and selected fields are used only to deliver the newsletter.
• We never share your information with third parties.
• You can unsubscribe anytime via the link in each email.

See our Privacy Policy for details.

Agree & Continue ▶

Takes about a minute · Unsubscribe anytime