Kyle Harrington

Hi all, I'm a computer scientist. Currently I'm focused on computational work that connects to bioimaging data. You can find more about me at my personal page kyleharrington.com

🏁 That's a wrap! The @biohub.org Cell Tracking machine learning challenge on @kaggle.com is over: 4,478 participants, 3,947 teams, 120 countries, 95,438 submissions, tracking every cell of zebrafish embryos. 🧪🔬🧵 kaggle.com/competition... #microscopy

*debates which torch monitor to use* docs.pytorch.org/docs/2.13/mo... or en.wikipedia.org/wiki/Sago_mo...

Congratulations to Ellen Zhong, Princeton University, for receiving the 2026 K.H. Kuo Award for Outstanding Young Scientist in Structural Biology www.bsc.org.cn/KuoSymposium...

Microscopy Nodes 3.1 is out for Blender 5.2! 🎉 This has cool new features for conditional masking, working with even larger data (regional upscaling), and data manipulation! Watch the new youtube tutorials that explain the features: www.youtube.com/playlist?lis...

📣 One of the best parts of #SciPy2026 is seeing the Scientific Python ecosystem evolve in real time. Today's Tools Plenary featured updates from the teams behind Zarr, Xarray, Tiled, Pangeo, scikit-image, Matplotlib, and napari, showcasing new features & future directions 🫶

📣 Tracking cells through time – including divisions – is a core problem in live-imaging microscopy. We built HOCT, an edge-centric Transformer that hits state-of-the-art on the Cell Tracking Challenge without a pretrained image encoder. Work led by @jookuma.bsky.social arxiv.org/abs/2607.11754 🧪🔬💻

Don't know how often @sethbullock.bsky.social visits here so I wanted to convey his message that our dear friend and ALIFE colleague INMAN HARVEY recently passed away. Follow the link below to Seth's touching post on LinkedIn. #ALIFE

Cool opportunity to help the community and get some cash 🤑

🧪

🚨Open call to the Cell Tracking crowd out there🚨! Loïc's team at @biohub.org opened our Kaggle Challenge for 3D cell tracking, with $60k of prize money💰. Spread the news, delve into our gigabytes of imaging (zarr3) and cell tracking (geff) data of developing zebrafish embryos, and start tracking 🤩

How do you track thousands of cells in complex systems, in 3D & over time? We are launching a Kaggle challenge to push the frontier of AI-powered cell tracking, building on advances like Ultrack & the DaXi lightsheet microscope from the @loicaroyer.bsky.social lab. bit.ly/4bfdzWE

Fantastic work by the team: Thibaut Goldsborough, Jordão Bragantini, Xiang Zhao, Gordon Leary, Teun Huijben, Ilan da Silva Theodoro, Kyle Harrington, Chi-Li Chiu, Walter Reade, María Cruz.

7/ 💰 $60K prize pool ($18K to 1st) · 🗓️ Final submission Sept 29, 2026 Build the next state of the art in cell tracking and help map life as it unfolds. 🔬🐟 👉 www.kaggle.com/competitions... #CellTracking #Kaggle

6/ 💻 You don't need to be a biologist. If you're into computer vision, object detection, segmentation, or graph optimization 📊, this is your problem. It's a code competition (notebooks, GPU/CPU ≤12h). Starter data and a sample submission are live now.

5/ 🧠 Why it matters: accurate single-cell lineages power developmental biology, immunology, and disease research 🩺, letting us ask where every cell comes from and where it ends up as a body takes shape. Better tracking = faster, more reproducible science.

4/ 🗺️ This is the problem behind Zebrahub (the Biohub's "Google Earth" of zebrafish development) and Ultrack 📄, our method in Nature Methods 2025 that topped the Cell Tracking Challenge on dense 3D embryos. Now it's your turn to push the state of the art!

3/ ⚠️ Why it's hard: high cell density, imaging noise, and irregular shapes break automated trackers, and small per-frame errors compound into broken lineages. 🪢 Today, scientists fix this by hand, with countless hours of manual tracking. That's the bottleneck.

2/ 🧫 The data: 3D+time light-sheet movies of fluorescently labeled zebrafish embryo cells (~88 GB training data, stored as Zarr). Thousands of similar-looking nuclei moving, deforming, and dividing. Biggest Dataset EVER! Your task: detect every cell, link it across time, and catch every division. ⏱️

1/ 🧬🔬 How does one cell become an entire animal? We can now film it in 3D 🐟, but turning those movies into accurate cell tracks is brutally hard. Enter our new #Kaggle challenge: $60K prize pool, to help crack 3D+time cell tracking at scale! 🧵👇 www.kaggle.com/competitions... @biohub.org

Cryo-ET is often framed as a tool for in situ protein structure. But what if the real revolution is contextualization? I explore how #teamtomo is redefining what "local" means in organelle biology, revealing membrane states rather than just protein structures. tinyurl.com/localmembrane

You can take a look at a demo tomogram acquired with the xLPP of apo-ferritin on the cryoET data portal here: cryoetdataportal.czscience.com/datasets/10496 Raw data is of course also available for download!

In a series of 3 papers and preprints, we’re thrilled to share with you the working laser phase plate. In collaboration with research led by Holger Müller at UC Berkeley, this is a huge innovation in imaging to make small and faint objects inside cells visible. bit.ly/4vK9LVn

Want to build some of the most advanced light-sheet microscopes in the world to watch life assemble itself cell by cell? The Royer Lab @ Biohub is hiring an Optical Engineer (Advanced Light Sheet Microscopy). 🧪🔬💻🔧 #Hardware + #Python + Advanced #Optics job-boards.greenhouse.io/biohub/jobs/...

🔬 Tutorial Spotlight: Build custom image analysis tools without starting from scratch. Tim shows you napari's power for microscopy, satellite data, and everything between 🛰️ Extend, visualize, annotate like a pro! #SciPy2026 🔗 scipy2026.scipy.org

A newly released AI tool has generated an atlas of more than one billion predicted protein structures and billions more protein sequences. go.nature.com/4wS3Pen

Proteins are the machinery of life. Billions of their sequences have been cataloged—but the biology behind most is still unknown. Today we're releasing ESMFold2, ESMC and ESM Atlas to help change that. Open source, open to every scientist. biohub.ai/esm/protein

🎉 Announcing the naPLari hackathon in Kraków, Poland 🇵🇱, July 24–29 2026, after EuroSciPy! Hack on napari, join deep dives, meet the team. All experience levels welcome! 📝 Register by July 1: napari.typeform.com/naplari-hack #napari #ScientificPython #OpenSource #EuroSciPy #BioImageAnalysis

Grigory Solomatov, Derya Akkaynak: Conditions for well-posed color recovery in scattering media https://arxiv.org/abs/2605.03837 https://arxiv.org/pdf/2605.03837 https://arxiv.org/html/2605.03837

Today we're announcing the Virtual Biology Initiative—a major new commitment to build the data foundation biology needs to power the next generation of AI models. Next-gen imaging. Molecular engineering tools. Open data infrastructure for the entire scientific community. Read more: bit.ly/3ONTkHO

Also noting that copick is a great example of impactful work that is enabled here at @biohub.org!

Excited to share our paper about copick, a dataset API and toolkit for collaborative annotation and analysis of #cryoET data! Whether you're picking particles or curating segmentations, copick reduces friction and brings #OME-Zarr to cryoET without breaking pipelines. 🧵👇 doi.org/10.1002/pro.70578

Big thanks to all co-authors, collaborators, and early testers! @danielji.bsky.social @zhuowenzhao.bsky.social @kyleharrington.com @rahelwoldeyes.bsky.social

Done with annotation? Use copick-torch for PyTorch-compatible data loading to train your model! Docs, tutorials, and code at 👇 🔗 copick.github.io/copick/ 🐧 github.com/copick

copick includes an MCP-server and batch curation tools: describe your curation pipeline in plain language, let an AI agent compose a curation pipeline for you. No coding required.

copick works across storage backends: local filesystems, HPC, S3/cloud, or directly from the cryoET Data Portal. Plugins for @chimerax.ucsf.edu and @napari.org handle all the details, so multiple users can annotate the same data simultaneously. No overwriting, no headaches, easy import/export.

Woohoo, copick is out! Access to massive amounts of CryoET data, MCP for agentic, plus a @napari.org interface! We even used it when hosting the CZII CryoET Kaggle competition: www.kaggle.com/competitions... when we needed to support a large collaborative annotation event with humans + ML models.

A generative AI framework for disease-specific lung microtissue bioengineering https://www.biorxiv.org/content/10.64898/2026.04.15.718723v1

A generative AI framework for disease-specific lung microtissue bioengineering https://www.biorxiv.org/content/10.64898/2026.04.15.718723v1

A generative AI framework for disease-specific lung microtissue bioengineering [new] ...leverages 3D tissue imaging and diffusion models to design and bioprint anatomically detailed lung models for preclinical applications.

People interested in the VPP aspects should also see a recent paper (from the people at Biohub) showing that tilt-series alignments can be improved with phase plate usage. journals.iucr.org/m/issues/202...

Happy to share the heroic effort of @gaellel.bsky.social to reduce our segmentation pain through EpiCure (Epithelial Curation), a napari plugin easing the curation of epithelial segmentation developed with several groups of @devstempasteur.bsky.social. www.biorxiv.org/content/10.6... See more 👇

napari 0.7.0 is available now! 🚀🎉 It's a BIG release so read the full release notes, with highlights: napari.org/stable/relea... We want to thank everyone who has worked incredibly hard on this release including our 11 new brilliant contributors 🤩 and the community for their support and feedback!

Congratulations to Dr. Julia Mahamid on receiving the 2026 Gottfried Wilhelm Leibniz Prize! 🎉 Her pioneering work in cryo-ET is reshaping our understanding of how molecular architecture drives cellular processes and disease. #teamtomo #LeibnizPrize #StructuralBiology #LifeSciences #Innovation

This looks awesome! Some gifs would be super cool 😉

Hello, world! We are starting a worker cooperative to build, maintain, teach, and support open source scientific imaging software. image.coop/blog/posts/2...

🔬 Registration is open for our pilot Introduction to napari Workshop! napari is a powerful open-source image viewer for scientific data analysis in Python. This hands-on workshop will get you exploring multi-dimensional datasets fast. #napari #Python #ImageAnalysis #DataScience #OpenSource

Highly recommended!

New on the CryoET Data Portal: ~27,000 tomograms of affinity-captured lysosomes from HEK293T cells across 4 physiological states. Includes raw data, AreTomo3 reconstructions & Membrain-Seg annotations. Openly available for reuse! cryoetdataportal.czscience.com/depositions/...

Here's the other one: www.science.org/content/arti...

Thanks, Rita! I was pretty darn happy that the journalists at Nature (and Science) were kind enough to write up the story of Maria's discoveries. I appreciate y'all, it really helps our mission. www.nature.com/articles/d41...