Here it is, PhenoMe in action! 🎬
Load, process and explore your data in seconds. Spot outliers, patterns, and relationships, even among the metadata you have (dose, time, temperature).
Analyze faster, test smarter, and build your next hypothesis with confidence.
1
6
Ready to try it? 👇
💻 GitHub: github.com/PhenoMe-Ecosystem…
📄 Preprint: doi.org/10.64898/2026.10.29.…
1
Aitor González-Marfil retweeted
Replying to @gomez_mariscal @AAitorG
PhenoMe is model-agnostic, supporting the use of Foundation Models and representation learning in life sciences research. It integrates ready-to-use pretrained DINOv2 and STED-FM, and functionality to process images with any PyTorch model
Aitor González-Marfil retweeted
Replying to @gomez_mariscal @AAitorG
♥️ Connecting all these features, it is then possible to run cluster analysis, cross-correlation analysis (supporting interpretation of the results), analysis of dynamic processes, and retrieve image prototypes that represent conditions, replicas, clusters or detected phenotypes!
Aitor González-Marfil retweeted
Replying to @gomez_mariscal @AAitorG
PhenoMe #standards also facilitate the integration of additional biological readouts into the image datasets, allowing a joint (multimodal😉) analysis
Aitor González-Marfil retweeted
Replying to @gomez_mariscal @AAitorG
#PhenoMe processes🔬 images (2D, multichannel, time-lapse, with/without masks) with a pretrained vision model (e.g. DINOv2) and displays the latent space representation interactively (Jupyter&Napari). This lets you explore new data acquisitions and identify existing phenotypes😎
Aitor González-Marfil retweeted
🚀Our latest work on AI embeddings and phenotyping is out! #PhenoMe is a new interactive tool bridging image representations derived from #FoundationModels with explainable features and biological readouts🕸️ Congrats to @AAitorG on this exciting work!🥳 biorxiv.org/content/10.64898…
What if you could explore thousands of microscopy images as an interactive map, without training a single model? 🔬
I'm really excited to share our new framework and preprint:
"PhenoMe: An interactive AI framework for interpretable, microscopy-driven phenotyping" 🧵👇
Together we built a tool I feel very proud of, and I hope the bioimaging community finds it useful! 😊
try it out:
pip install phenome
or using @napari_imaging:
pip install phenome-gui
Aitor González-Marfil retweeted
Introducing LeVJEPA 1.5 Large, the first step in scaling our method.
It closes the gap to V-JEPA on both image and video benchmarks, trained with 5.6x less compute and over an order of magnitude less data.
Here is DINOSim in @napari_imaging! 🎬
Click a few points on the object you care about and the mask shows up right away. Drop in more images, and segment them in seconds. No background clicks, no training set, and no fine-tuning needed.
1
9
Available now on the napari hub and PyPI:
pip install napari-dinosim
📄 doi.org/10.1002/jemt.70194
💻 github.com/AAitorG/napari-DI…
7
Aitor González-Marfil retweeted
Our method #DINOSim for #zeroshotsegmentation leveraging #foundationmodel's embeddings has been published in Microscopy and Research Technique🔥Big congratulations to @AAitorG for leading this beautiful work 🚀
📝analyticalsciencejournals.on… – at Oeiras, Portugal
🎉 It's out!
After a long journey, I'm happy to announce that my first paper as first author is now published in Microscopy Research and Technique! 😊
"DINOSim: Training-Free Semantic Segmentation on Microscopy Images" 🧵👇
We packaged the workflow as an interactive @napari_imaging plugin so you can use it right away in the lab!
Huge thanks to my supervisors & coauthors @gomez_mariscal and Ignacio Arganda-Carreras. 🤗🤗🤗
Give it a try 👇
pip install napari-dinosim
📄 doi.org/10.1002/jemt.70194
💻 github.com/AAitorG/napari-DI…










