1/28 How do you optimize a dynamic protein property that emerges from multiple states? Our finally published paper in @NatureComms takes on one of the hardest problems in protein engineering with phage assisted evolution: evolving allosteric switches🧵
Added a JAX translation of the excellent Proteina-Complexa (from nvidia, @kdidi.bsky.social , @karstenkreis.bsky.social ) to mosaic. You can do beam search with any mosaic loss (e.g. protenix + mpnn) and JAX with generate efficient GPU/TPU code.
🚨🚨🚨Job alert
We are looking for postdoc joining our lab. If you are interested in subcellular distribution of proteins using iPSC and animal models in combination with leading genome engineering tools, check this add out!!
🧠🧬🔬🧫💊
www.linkedin.com/posts/karl-c...
ZeroFold: Protein-RNA Binding Affinity Predictions from Pre-Structural Embeddings
Figure 1
Figure 2
Figure 3
ZeroFold: Protein-RNA Binding Affinity Predictions from Pre-Structural Embeddings [new]
Leverages pre-structural embeddings that capture RNA flexibility for direct, sequence-based affinity prediction via cross-modal attention, bypassing structural data.
New OpenFold3 preview out! (OF3p2)
It closes the gap to AlphaFold3 for most modalities.
Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9
New post: blog.escalante.bio/teaching-gen.... You can massively improve in silico metrics for BoltzGen using standard post-training techniques (with a structure model as your reward function). If this holds up (no wetlab testing yet!) you could get binders in seconds rather than hours...
Interested in gaining research experience, and curious about genome editing tool development and their application to treat human diseases? 🧬 🧫
We are hiring!! Join us at Mass General Hospital in Boston! 📣
massgeneralbrigham.wd1.myworkdayjobs.com/MGBExternal/...
I wrote a blog post about the future of structural bioinformatics.
Where to go after AlphaFold? How do we avoid the field becoming a load of half-baked LLMs?
Let me know what you think.
jgreener64.github.io/posts/struct...
We built DNA scaffold crystals that can be reprogrammed to host different guest proteins for X-ray structure determination — no new crystallization screen required. This animation shows a guest protein (glowing) seeking its designed binding site inside the crystal lattice. shorturl.at/DANdc
First preprint of the @pollyfordyce.bsky.social and @dunnlab.bsky.social collaboration! We used high-throughput microfluidics for sequence-strength mapping at the single-molecule level. Our new tech allowed us to discover a fundamental nonequilibrium property of multivalent systems. 1/13
🧬 RNAMed is hiring!
Apply for one of 11 fully funded PhD positions in RNA medicine and work with leading RNA experts in an international, interdisciplinary environment.
📅 Deadline: 24 March 2026
More info & apply:
lnkd.in/eX7fQcJi
Wow congrats to the authors this is truly impressive
Looking for a truly unique PhD programme on RNA drugs and therapeutics? We have just opened the call for the second cohort of RNAmed-Future leaders in RNA-based medicine. More details under www.rnamed.de Please spread the word.
A detailed comparison of de novo designed proteins by NMR finally puts to rest the idea that structure prediction confidence metrics have any correlation with local flexibility
Figure 2
AlphaFast: High-throughput AlphaFold 3 via GPU-accelerated MSA construction [new]
...is a drop-in framework integrating GPU-accelerated MMseqs2 to overcome the CPU-bound MSA generation bottleneck in AlphaFold 3.
if you don't like the huge extended helices or alpha solenoid proteins you're getting from hallucination-based protein design methods (bindcraft, mosaic, etc), increasing the scale of the initial sequence noise (typically Gumbel) increases funkiness without hurting final metrics like ipTM
The fitness landscapes of binders targeting protein surfaces that are evolutionarily predisposed to engage in PPIs is much narrower and deeper than those that target surfaces with no known interacting proteins. This might be b/c random binding events is bad, and selected against
🎉🎉 Our paper on temperature-dependent protein control using AsLOV2 variants is now published at @natchembio.nature.com: www.nature.com/articles/s41... including some new insights from extend variant characterizations.
How could a simple self-replicating system emerge at the origins of life? RNA polymerase ribozymes can replicate RNA, but existing ones are so large that their self-replication seems impossible. Could they be smaller?
Excited to share our latest work in @science.org on a new small polymerase.
1/n
I made a map of 3.4 million Bluesky users - see if you can find yourself!
bluesky-map.theo.io
I've seen some similar projects, but IMO this seems to better capture some of the fine-grained detail
Introducing The Structural History of Eukarya (SHE): The first proteome-scale phylogeny constructed entirely from 3D structure.
We computed 300 trillion alignments across 1,542 species to map the tree of life. 🧵👇 (1/5)
🧬🌉Online @science.org Programmable genome editing in human cells using RNA-guided bridge recombinases | Science www.science.org/doi/10.1126/...
🗓️ Save the Date!
The 5th European RosettaCon – Crossing Boundaries with Protein Design will take place in Lisbon, Portugal 🇵🇹
🗓️ October 28–30, 2026
Join the protein design community for an inspiring scientific meeting at the intersection of innovation and design.
Does the noncoding genome actually carry more genetic information than coding seqs? Motivated by this question we mutated every bp in the 10kb MYC locus. Results are even more exciting: Decoding the MYC locus reveals a druggable ultraconserved RNA element www.biorxiv.org/content/10.6...
FoldMason is out now in @science.org. It generates accurate multiple structure alignments for thousands of protein structures in seconds. Great work by Cameron L. M. Gilchrist and @milot.bsky.social.
📄 www.science.org/doi/10.1126/...
🌐 search.foldseek.com/foldmason
💾 github.com/steineggerla...
China’s innovation in translational medicine: rethinking early-stage clinical development - @caidyacro.bsky.social go.nature.com/4agbEkG
Neat paper! Boosting to the MP feed 🧬
EDEN: a family of genomic language models trained on up to 9.7 trillion nucleotides from @basecamp-research.bsky.social's BaseData can design large serine recombinases, bridge recombinases, and antimicrobial peptides.
www.biorxiv.org/content/10.6...
Happy to have played a small part in this!
Can we design mutations that bias proteins towards desired conformational states?
Today in @science.org, we introduce Conformational Biasing (CB), a simple and scalable computational method that uses contrastive scoring by inverse folding models to identify conformation-biasing mutations.
1/ Check out our newest paper where we ask: How fast can we experimentally discover binders from scratch?
And we mean scratch: a blinded study.
TLDR: 26 days. And the binders work…and led to new cancer biology.
We’re coming for you AI….
chemrxiv.org/engage/chemr...
