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
Five years ago, we released FLIP. The core question was: can ML models for protein fitness prediction generalize in the ways that actually matter for protein engineering, i.e. low data, extrapolation to more mutations, out-of-distribution sequences?
New pre-print from the lab on scaling transferable implicit transfer operators to protein dynamics. Collaboration with @olewinther.bsky.social lead by @panosantoniadis.bsky.social.
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)
While most AI models are trained on text and images, the Polymathic AI collaboration has something different in mind: AI trained on #physics: https://www.simonsfoundation.org/2025/12/09/these-new-ai-models-are-trained-on-physics-not-words-and-theyre-driving-discovery/ #science
New Preprint!! We show that binding entropy can be quantitatively predicted from crystallographic ensemble models, accounting for both protein conformational entropy and solvent entropy! 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...
Important perspective from Greenland.
UK Research and Innovation, plus its research councils, quietly quit X.
Via @robinbisson.bsky.social @sophieatrpn.bsky.social
www.researchprofessionalnews.com/rr-news-uk-r...
I found the secret Pret at Heathrow Terminal 5
Time for a ROK Espresso GC
I've had the pleasure of working on this in collaboration with my very sharp colleagues at Absci.
We look forward to feedback on all aspects of our design pipeline and preprint! [9/n, n=9]
This solves the false-negative problem completely! And you can use fancy asymmetric versions of ipTM @rolanddunbrack.bsky.social.
Interestingly we find that, of the 5 AFM-v2.3 models, model 2 is almost always the best on ab-ag complexes. We can cut runtime by 5x with little performance hit! [8/n]
It turns out that masking template AAs in "AF2Rank-Unmasked" may not be the optimal choice for ab-ag complexes. This is a much trickier modality for AFM—it is systematically less capable & confident there than on many PPIs seen in protein design papers.
So, we restore the template AAs! [7/n]
The hack involves "unmasking" cross-chain template information. It's not how AFM was trained, but Mirabello et al showed that AFM can leverage the newly-unmasked information (www.nature.com/articles/s41...).
However, we find that "AF2Rank-Unmasked" suffers from similar issues as AF-IG. Why? [6/n]
AF-IG is serving the protein design community well, but it falls short on antibody-antigen complexes that are OOD to the training set—it throws away too many correct PDB structures.
Sth else? With a fun AF-Multimer hack, one can run AF2Rank on complexes (this is available on ColabDesign!) [5/n]
A popular way to score/rank designed binders with AF is "AF Initial Guess" (AF-IG), introduced by the Baker lab. Here, the designed complex is fed as an initialization to AF's trunk (this is possible because of recycling).
Both AF-IG and AF2Rank are ways to provide AF with a structural hint. [4/n]
AF2Rank worked even better when template AA tokens were replaced with gap symbols. Otherwise, AF2 thinks you are giving it "the right answer" and, in the case of protein monomers, spits the decoy structure back to you over-confidently.
Why is this potentially useful to binder discrimination? [3/n]
In 2022 (!), @jproney.bsky.social & @sokrypton.org showed (AF2Rank) that AF2's template track can be repurposed to perform SotA ranking of protein monomer decoys. You provide the decoy structure as a template (instead of the structure of another homologous protein) & look at confidence scores. [2/n]
This was fun work and a remarkable effort across the computational and wet-lab teams!
Strategies for in-silico filtering and ranking of antibody designs have been under-discussed in the literature, e.g. in most technical reports on antibody design that I've seen. Let's talk about these here! [1/n]
At Absci, we performed de novo antibody design campaigns against "zero-prior" epitopes—lacking structural data from antibody-antigen or protein-protein complexes.
Model architectures, training data curation, and scoring protocols are fully described.
Preprint: www.absci.com/wp-content/u...
GERMAN PRESIDENT STEINMEIER:
“.. the United States has broken with the values that it helped to establish ..
“.. we have now moved beyond the stage where we can lament the lack of respect for international law or the erosion of the international order; we are far beyond that, I believe.”
Recently found out about @jvkersch.bsky.social's `tmtools` github.com/jvkersch/tmt.... It works nicely! Being able to pass user-defined sequence alignments is a nice (if simple) feature that is missing from OpenStructure's own `tmtools` @torstenschwede.bsky.social.
Black swan moment for energy production and storage?
Thank you for your reply! I see, so the complete statement is something like "this is the first time that the reversible folding of a protein is computed with an all-atom foundation machine learning model trained on DFT-generated data", correct?
Could you comment on the differences with the chignolin case study in www.nature.com/articles/s41...?
Exciting! Concerning your chignolin example, you write: "Previous studies tackling this system with a ML model were limited to non-transferable protein models [...] this is the first time that the reversible folding of a protein is computed with a foundation machine learning model"
🏛️ 🔍 👀
"There are no optical corrections in the Parthenon"
