PhenoMe: An interactive AI framework for interpretable, microscopy-driven phenotyping
Abstract
Extracting meaningful biological patterns from microscopy image datasets requires tools that quantitatively connect visual similarities and experimental context. Deep learning models, and in particular novel foundation models, have the capacity to translate images into high-dimensional embeddings that can better represent complex visual patterns. Using these complex representations analytically and linking them to experimental information, it is possible to build advanced exploratory and phenotyping capabilities. Here, we present PhenoMe, an open-source, model-agnostic framework to handle pretrained foundation model-derived image representations alongside quantitative image properties and experimental metadata. PhenoMe integrates multiple scriptable and interactive workflows for embedding space visualisation, dimensionality reduction and clustering, similarity-based comparison and retrieval of representative images for each phenotype, among others. It also supports correlation analyses that link the embedding structure to interpretable image properties. We demonstrate PhenoMe's capabilities on seven public microscopy datasets, ranging from cell painting assays, nanoscale synaptic images, drug-response analyses and dynamic cell-phenotyping. These case studies show how readily available image representations can support data contextualisation, curation and analysis. Through guided notebooks, reproducible configurations, extensible model wrappers and a napari plugin, PhenoMe makes representation-based microscopy exploration accessible to researchers without dedicated technical expertise. PhenoMe lays the groundwork for applying foundation models and representation learning to microscopy data analysis.
Related
- Interpretable computational SHG microscopy enables quantitative tissue phenotyping of cardiac remodeling in nonischemic heart failure
- Luxar: Gaussian splatting for microscopy and scalable interactive web visualisation of multidimensional scientific data
- Pan Genome to Pan Phenome provides a mechanistic framework for translating hidden genetic diversity into predictive wheat breeding
- FaceKit: a Toolkit for Interpretable Facial Phenotyping, Synthetic Image Generation and Privacy Analysis in Rare Diseases
- AltraFlowSOM: A Semi-Supervised Framework for Imaging Mass Cytometry Phenotyping
BibTeX
@misc{gonzalezmarfil2026phenome,
title = {{PhenoMe: An interactive AI framework for interpretable, microscopy-driven phenotyping}},
author = {A. Gonzalez-Marfil and L. Backova and R. Bernatchez and I. Hidalgo-Cenalmor and A. Dufour and G. Jacquemet and F. Lavoie-Cardinal and I. Arganda-Carreras and E. Gomez-de-Mariscal},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.29.762637},
url = {https://www.biorxiv.org/content/10.64898/2026.10.29.762637v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - PhenoMe: An interactive AI framework for interpretable, microscopy-driven phenotyping
AU - A. Gonzalez-Marfil
AU - L. Backova
AU - R. Bernatchez
AU - I. Hidalgo-Cenalmor
AU - A. Dufour
AU - G. Jacquemet
AU - F. Lavoie-Cardinal
AU - I. Arganda-Carreras
AU - E. Gomez-de-Mariscal
PY - 2026
DA - 2026/10/29
PB - bioRxiv
DO - 10.64898/2026.10.29.762637
UR - https://www.biorxiv.org/content/10.64898/2026.10.29.762637v1
AB - Extracting meaningful biological patterns from microscopy image datasets requires tools that quantitatively connect visual similarities and experimental context. Deep learning models, and in particular novel foundation models, have the capacity to translate images into high-dimensional embeddings that can better represent complex visual patterns. Using these complex representations analytically and linking them to experimental information, it is possible to build advanced exploratory and phenotyping capabilities. Here, we present PhenoMe, an open-source, model-agnostic framework to handle pretrained foundation model-derived image representations alongside quantitative image properties and experimental metadata. PhenoMe integrates multiple scriptable and interactive workflows for embedding space visualisation, dimensionality reduction and clustering, similarity-based comparison and retrieval of representative images for each phenotype, among others. It also supports correlation analyses that link the embedding structure to interpretable image properties. We demonstrate PhenoMe's capabilities on seven public microscopy datasets, ranging from cell painting assays, nanoscale synaptic images, drug-response analyses and dynamic cell-phenotyping. These case studies show how readily available image representations can support data contextualisation, curation and analysis. Through guided notebooks, reproducible configurations, extensible model wrappers and a napari plugin, PhenoMe makes representation-based microscopy exploration accessible to researchers without dedicated technical expertise. PhenoMe lays the groundwork for applying foundation models and representation learning to microscopy data analysis.
ER -