CAJAL enables analysis and integration of single-cell morphological data using metric geometry.

Area of Science:

• Computational Biology
• Single-Cell Analysis
• Morphological Data Analysis

Background:

• High-resolution imaging enables studying single cells in spatial context.
• Analyzing diverse cell shapes and integrating morphological data with other single-cell data presents challenges.

Purpose of the Study:

• To present CAJAL, a computational framework for analyzing and integrating single-cell morphological data.
• To infer cell morphology latent spaces using metric geometry.
• To facilitate integration of morphological data across technologies and infer relations with other data types.

Main Methods:

• Developed CAJAL, a computational framework based on metric geometry.
• Inferred cell morphology latent spaces where distances represent physical deformation.
• Integrated single-cell morphological data with transcriptomic data.

Main Results:

• CAJAL successfully infers cell morphology latent spaces.
• Demonstrated utility with neuronal and glial datasets.
• Identified genes associated with neuronal plasticity in C. elegans.

Conclusions:

• CAJAL provides a general framework for single-cell morphology analysis and integration.
• The framework effectively integrates cell morphology into single-cell omics analyses.
• Facilitates discovery of relationships between cell shape and other biological data.