Looking forward to your talk @jselkrig.bsky.social !!

Interesting data and analysis behind NeurIPS's new AI policy blog.neurips.cc/2026/06/02/a...

For those of you who've been hiding under a rock 😜 "From LLMs to scientific AI agents" #LLMs #AI #agents #science youtu.be/O658XYRmAqE

Come and start your group at @ki.se! ki.se/en/about-ki/...

I made a better one. My favorite kinase, Aurora A. Happy Pride! 🏳️‍🌈🏳️‍⚧️

A new perspective from IMSB's @nzamboni.bsky.social with Theodore Alexandrov. They map out how scaling up metabolomics, bridging single-cell resolution with large population cohorts, will have an impact on biology and medicine. www.nature.com/articles/s41...

The German National Academy of Sciences Leopoldina has elected Susana Coelho as a new member. Many congratulations! www.bio.mpg.de/523647/susan...

🛠️💉It's time for engineering contractile injection systems! @chipericson.bsky.social & @davidschaumann.bsky.social introduce programmable CIS - PROCIS, combining tail length control, non-native cargo loading, and cell retargeting all in one system! www.biorxiv.org/content/10.6... 🧵 1/5

Everything you wanted to know about the protein chemistry behind how amino-acid changes affect the cellular abundance of proteins from @tkschulze.bsky.social Effects of residue substitutions on the cellular abundance of proteins doi.org/10.7554/eLif...

Amazing work from the Kellogg lab!! I had this kind of project in my very first 2022 professorship proposal and but never actually did it, super glad to see it can work in reality!!!

Our aRES story is finally out 😀 Beyond what was reported in the preprint, we found that aRES is activated by direct binding of the phage DNA polymerase. Another NAD-degrading defense system — and multiple phage strategies to overcome it. www.sciencedirect.com/science/arti...

We built a joint experimental and computational platform for scalable multi-modal single-cell chemical screens — profiling RNA, protein (including phospho-signaling), and chromatin accessibility responses to thousands of small molecule perturbations in parallel. www.biorxiv.org/content/10.6...

I finally got around to trying to do a small research project with Claude code and wrote this up. The topic of general AI models is so polarizing in society at the moment. It would be more useful to try to have practical discussions about their uses. www.evocellnet.com/2026/05/ai-g...

Thermo Fisher has now made public the company line, which is ?!??!?!??!?!?! you really gotta read it. cen.acs.org/research-int...

Summary of Key Changes in OMB’s Proposed Federal Financial Assistance Rule. Russell Vought is going destroy American Science. elizabethginexi.substack.com/p/summary-of...

TL;DR: We've identified more than 100 cases of apparent manipulation in Thermo Fisher Scientific's antibody verification data. @sholtodavid.bsky.social @johanduchene.bsky.social reeserichardson.blog/2026/05/28/h...

Generative AI use and misuse call for assessment reform in higher education www.science.org/doi/10.1126/...

1/5 Cell identity is written in the proteome, not in the DNA, and not always in the RNA. Out on bioRxiv today: The first cell type-resolved, MS-based proteomic atlas of the human body. www.biorxiv.org/content/10.6...

Our kinase-based Phospho-Labeler approach for structural proteomics has now been published in Cell Reports Methods.

Connect Claude to PDBe in 3 steps: 1️⃣ Install uv 2️⃣ Run: uvx pdbe-mcp-server --server-type pdbe_api_server 3️⃣ Add config to Claude Desktop Now ask: “Find X-ray structures for UniProt P12345” 📦 github.com/PDBeurope/PDBe-MCP-Servers #PDBe #MCP #ClaudeAI #Bioinformatics

AI drug discovery has a data problem. We're fixing it. At ALLOX, we've spent the last few years building something that didn't exist before: a platform that systematically maps functional hotspots at scale, measuring the effects of mutations on protein-protein interactions across the proteome.

ESMfold2, claims increased accuracy and speed over AF3 and others. What does it have to do with the latest AI trend of "world models" is something I am sure I will find out when I read the manuscript. biohub.ai/esm/protein/...

1\ Excited to finally share some of my PhD work: OpenSplice! We measured how >590,000 mutations affect exon inclusion across 600 human exons, creating a resource to study splicing regulation, benchmark variant effect predictors, and support variant interpretation.

When I woke up this morning I didn't think I'd be spending a bunch of time today getting familiar with Catholic theology, but here we are. Notes on Pope Leo XIV's encyclical on AI. simonwillison.net/2026/May/25/...

new lab preprint - Protein function prediction is a well established problem but proteins exist in different post-translationally modified forms. Here, @julianvangerwen.bsky.social built a ML model to predict the biological process regulated by individual phosphosites www.biorxiv.org/content/10.6...

@johanduchene.bsky.social @sholtodavid.bsky.social Spent the last hour looking, found ten more apparently manipulated Western blots in Thermo Fisher's antibody verification data (across eight different catalogued products). Thread below. www.thermofisher.com/antibody/pro...

Some thoughts on where AI in genomics stands right now, building on a symposium we recently hosted at UChicago. Seven points, ranging from why scaling DNA models hasn't delivered, to why metadata is the real bottleneck, to the weird backlash against AI in academia open.substack.com/pub/blekhman...

Thread coming later but I think people will like this!! 2 million stability measurements plus a predictive model for deltaG (not ddG)

Accurate protein stability prediction for small domains using mega-scale experiments https://www.biorxiv.org/content/10.64898/2026.05.19.726285v1

We are looking for a new colleague to join us in Galway. The position is in Biochemistry and if research focus lines up we hope the successful person will join us in the Centre for Chromosome biology (chromosome.ie). Reach out if you are interested in applying! tinyurl.com/2jy4rj3r

Honored to celebrate Paola Picotti at yesterday’s Otto Naegeli Prize 2026 ceremony — recognizing her groundbreaking contributions to proteomics and systems biology. An inspiring evening dedicated to scientific excellence and the future of biomedical research... and a great presentation by Paola!

I tried the same prompt for generating of a high impact fake Cell paper about kinase signaling on 4 different AI models. One refused to do it (yay Claude), the other 3 did without any issues being raised and funnily enough all 3 were about a kinase that forms condensates :)

Former president of the Helmholtz Association joins @champalimaudf.bsky.social as the new Director of Champalimaud Science www.fchampalimaud.org/news/welcome...

Screen 1M random protein sequences to discover that biology-like folds are accessible from random sequences with surprising frequency www.biorxiv.org/content/10.6...

We are implementing a similar policy at @arxiv.bsky.social. If there is incontrovertible evidence of LLM slop in a paper, this means the authors did not take the time to read the LLM output and we can't trust anything else in the paper. Penalty is 1 year ban from arXiv followed by...

The final version of our @annualreviews.bsky.social article is now published OA: www.annualreviews.org/content/jour...

Benvinguda, bienvenida y bem-vinda @monicabettencourt.bsky.social, who completes her first week as Director of the Centre for Genomic Regulation. She takes the relay from Luis Serrano after fifteen years. We look forward to the next chapter! @eu-life.bsky.social @prbb.org @cerca.cat

It's finally out!

TranscriptFormer: A generative cell atlas across 1.5 billion years of evolution www.science.org/doi/10.1126/... - this looks cool! 👀

Equivariance is dead! 😢 Or is it? 😈 Genie 3 is out! Our latest protein design model achieves SoTA results for binder design and motif scaffolding, greatly improving on BindCraft and Proteina-Complexa. It does so using all-atom SE(3)-equivariance based on a branched polymer representation👇

A transformer model is used to construct the DreaMS Atlas—a molecular network of 201 million MS/MS spectra go.nature.com/4k1n5iC rdcu.be/feuB9

Super excited to see this out! Fantastic collaboration with Luke O'Connor and trainees Amber Shen and Xinran Wang. Thread with details will come soon, but linear ARG provide a HIGHLY efficient representation of genotype data that can be treated as a linear operator www.biorxiv.org/content/10.6...

Our findings from the largest systematic analysis of complex trait associations is out now on bioRxiv! 🧬🖥️ www.biorxiv.org/content/10.6...

#OpenBind announces its first data drop marking a major milestone for AI‑Enabled #DrugDiscovery! It’s the first initiative to generate open, AI‑ready datasets for protein–drug complexes, produced continuously & at industrial scale to enable the next generation of #AI models. https://loom.ly/eIrsqqg#OpenBind

Systems modeling identifies phenotype-determining signaling pathways controlled by phosphatase PTPRJ in diverse receptor tyrosine kinase activation settings https://www.biorxiv.org/content/10.64898/2026.04.30.721884v1

I am happy to share a review I recently wrote on the design of peptide binders. It gives an overview of experimentally validated tools and discusses the challenges of why peptide design is more difficult than the design of classical protein binders. www.chimia.ch/chimia/artic...

Enjoyed this recent review/perspective: many somatic mutations are already present in normal tissues, shifting attention from driver mutations to non-mutagenic promoters of oncogenesis. Also wild that it took 3 years from submission to publication. nature.com/articles/s41586-026-10386-x

I am deeply honoured to be awarded the NVBMB Prize 2026! I feel very grateful for this recognition, and especially for the many colleagues, mentors, and team members who have supported me scientifically and helped me get to this point. A big thank you to the NVBMB for this award.

Could agentic AI topple grant-funding systems? New article in @nature.com by @profgeraintrees.bsky.social & me, with data from 12 funders showing a 57% increase in grant applications since 2022 (& the launch of LLMs) rdcu.be/ffApn @rorinstitute.bsky.social @magdalenaskipper.bsky.social

📜The final version of our paper on eCIS firing is out: www.nature.com/articles/s41... Congrats to @xujwet.bsky.social @chipericson.bsky.social #cryoEM #CIS