My current AI stack: - Codex Pro Max - Base-spec Mac mini with SSH, Screen Sharing, and Continuity enabled, obviously - Hermes as the main agent runtime with OpenClaw, and OMX still around for comparisons / fallback 1/3

Science has a weird habit: we still treat the PDF as the atomic unit of trust. But a paper is not one thing. It is a bundle of datasets, tools, models, protocols, results, assumptions, proofs, bugs, caveats, and human story. AI makes this harder to ignore. 1/3

I made a map of gene regulation as one integrated control system, from DNA → RNA → protein. 🧬 It contains 38 mechanisms grouped into 7 layers. It has a few recurring principles, such as: 🔓 accessibility 🏷️ reversible marks ⏱️ and kinetic coupling. 1/2

This morning I had the chance to present my research at the Cancéropôle IDF "AI & Cancer" day. Talking single-cell foundation models to cancer researchers and clinicians was a great exercise! 😅 1/2

We trained 42 models so we didn't have to guess. Before building scPRINT-2, we ran a systematic ablation study — one design choice changed at a time. The results shaped every architectural decision. Now it's out. 🧵 1/3

Built two @openclaw skills: E2EE messaging across all major platforms via Matrix/Beeper, and cross-platform social scheduling. My online presence is now 100% interfaced through my agents.

Unbridled — ClawHub

Send and read messages on Facebook Messenger, WhatsApp, Instagram, LinkedIn, Twitter/X, Signal, Telegram, Discord and other networks through a Beeper account...

clawhub.ai

In fall 2023, I met Alex in CZI's CellXGene Slack channel when we were both trying to figure out how to best manage metadata of thousands of scRNA-seq datasets. Alex for his work on LaminDB, and I for my work on scRNA-seq foundation models. 1/3

🚨 2026 Lilly x Nucleate Grand Challenge: Aging Reimagined 🔬 $100K non-dilutive 🏛️ Pitch at Lilly HQ 🤝 Lilly's science + venture teams Focus: mobility, cognition, immune resilience, regenerative medicine — the frontiers of healthspan. 📅 May 15 👉 linktr.ee/lillygrand...

The biggest bottleneck in building cell foundation models isn't the architecture. It's the data. For scPRINT-2 we assembled what is, to our knowledge, the largest pre-training corpus for any cell foundation model. www.biorxiv.org/cont... 🧵 1/3

Self-attention changed everything in deep learning. But it comes with a tax: O(n²) complexity. For long sequences, that's not just slow — it's a wall. There's a cleaner way to think about it, which I introduced in my recent preprint: scPRINT-2, it is called Criss-Cross Attention: 🧵 1/2

Did you know that likely most cases of multiple sclerosis (MS) are driven by the EBV virus (herpes/mononucleosis disease)? >90% of us get infected in our teens, and some will go on to develop many diseases later in life because of it. 1/6

And then lucky to pursue through an atlas of cells of many types and species, with a focus on quality and diversity mattering more than quantity with @jkobject.com

🧑‍🎄🎄 Christmas Foundation Model Release: scPRINT-2 **One-liner:** a **20M-active-param** single-cell foundation model trained on **350M cells / 16 species / 300 tissues / 500 cell types**. 1/6

It was a blast hosting our Nucleate Inside AI roundtable at the France Techbio 2025 event.

🌐🧬I am excited to present you a round table I am doing together with Matteo Marengo Gabriel Michaux as part of our emerging Nucleate Parisian chapter led by Clara Brouaux 🔥. Title: **Inside AI: Choosing the Right Path to Value Creation** 1/3

Next week we will see the first conference where both the main authors and reviewers are LLM Agents! This might be fun to follow: agents4science.stanf... 👀 🤖

I am presenting my PhD work today at the conference on immuno oncology in Toulouse's CRCT Oncopole! Happy to talk about how we can use foundation models in the real world 🧬 🧑‍⚕️

Proud to be a Nucleate Leader! 🚀 Being a Nucleate Leader means joining a community of peers who step up to shape the future of biotech — leading teams, driving programs, and building ventures that make real impact.

The first 1 million prime numbers vizualized in 2D according to their prime factors (Umap) Source: johnhw.github.io/uma...

what they sell you, what you get...

If you are launching your biotech / techbio startup in Paris or anywhere else in the world actually, think about applying to Nucleate's Global Activator Program! 🚀 🧬 Many people to meet and things to learn from Researchers, Investors, CEOs and more!

Main

Made with Softr, the easiest way to turn your data into portals and internal tools.

gateway.nucleate.org

In 2025, deciding to have a child without full genome sequencing of both parents is borderline reckless. It costs under €400. Takes 2 minutes. Could save your child’s life. Yet >200 million people live with rare genetic diseases—many preventable by this simple test. 1/2

I am at ISMB ECCB this week 🧬👨‍💻Do reach out if you are in Liverpool and want to chat about AI, target discovery and disease modelling 😊

If you are at ICML, I would be happy to meet to talk about AI, bio, and drug discovery!

Very happy to share that my new paper got accepted at the ICML workshop for Foundation model for Life Sciences!! www.biorxiv.org/cont... Foundation Models are being trained from atoms to molecules ⚛️, molecule chains 🧬, entire cells 🦠, and even groups of cell across tissue slices 🫁

scPRINT is now finally on the Chan Zuckerberg Institute's Model Hub! 🎉 🧬 🌈 It is one more way you can use this cell foundation model to embed, denoise, predict cell type, get gene networks from your data from scratch, or fine-tune it on your own application / usecase: virtualcellmodels.cz...

scPRINT | v1.0 | Virtual Cells Platform

scPRINT is a cell foundation model, also called a Large Cell Model (LCM), trained on single-cell RNA sequence (scRNAseq) data from more than 50M human and mouse cells available through CZ CELLxGENE. Based on the transformer architecture, the model is fully open source and reproducible, with multiple checkpoint sizes available from 2M to 100M parameters. scPRINT demonstrated high performance for genome-wide cell-specific gene network inference when benchmarked against state-of-the-art models (e.g., scGPT, Geneformer v2, GENIE3). In addition, scPRINT has various zero-shot capabilities, including cell embedding, cell label prediction (e.g., cell type, sex, disease), and gene expression imputation, highlighting its potential as a versatile tool for single-cell analysis.

virtualcellmodels.cziscience.com

Thanks to @GenBioAI to let me present my work on scPRINT and to have synthetised it so expertly in their blog post: genbio.ai/scprint-ge... Watch the full presentation here: www.youtube.com/watc...

scPRINT: Gene Network Inference from 50M Cells by Jérémie Kalfon - Genbio AI

TL;DR In this talk, Jérémie Kalfon presents his paper “scPRINT: pre-training on 50 million cells allows robust gene network predictions” at the Foundation Models for Biology Seminar Series by GenBio AI. He introduces scPRINT, a transformer-based foundation model trained on over 50 million single-cell RNA-seq profiles to infer gene networks. scPRINT enables scientists to predict

genbio.ai

I see people want to compete with scDataLoader... arxiv.org/abs/2506.0...

scDataset: Scalable Data Loading for Deep Learning on Large-Scale...

Modern single-cell datasets now comprise hundreds of millions of cells, presenting significant challenges for training deep learning models that require shuffled, memory-efficient data loading....

arxiv.org

The first convincing example I saw of why one would want to map across species: www.biorxiv.org/cont... 1/2

cool cryoEM+ML talk Showing the future of the protein structure data modality and by doing-so, where structural models like AF3 will go next and how they might be trained www.youtube.com/watc...

MIA: Ellen Zhong, ML for reconstructing structural landscapes from cryoEM; Primer, Rishwanth Raghu

Models, Inference and Algorithms March 11, 2025 Broad Institute of MIT and Harvard Primer: Heterogeneous reconstruction in cryo-EM Rishwanth Raghu Princeton University Department of Computer Science Meeting: Machine learning for visualizing structural landscapes inside the cell Ellen Zhong Princ

youtube.com