Radoslav Krivak

Very happy @roman-bushuiev.bsky.social and I joined the amazing team led by @hannes-stark.bsky.social to work on BoltzGen, a generative model for binder design based on Boltz-2. Excited what it will enable!

We train machine learning models on millions of proteins. But when it comes to making predictions, do we need them to understand all proteins at once? Often, we need an accurate model for the specific protein we are studying or designing. We address this with ProteinTTT arxiv.org/abs/2411.02109 1/🧵

The link here doesn't seem to work...

Every limitation of AlphaFold2/structure prediction you noted also applies to co-folding tools, but even more so.

Finally, Mol* with a human face

Curious how China comes into play here. Is it mainly about market opportunities, competition, or something else?

Yes... I wish Bluesky was that, but this is where we are. Linked has this recycling thing when it shows you 4 week old posts if they are relevant which is actually good.

ferritin 3d model

ferritin 3d model open

today #3Dprint protein is ferritin (PDB: 6I36)

available here:
www.printables.com/model/141627...

I am very proud of the final outcome of this project, mainly driven by Corinna Brungs and supported by numerous labs who donated compounds for analysis.

🌿 The Botanical Garden of Charles University’s Faculty of Science turns 250! Founded in 1775, it is one of Central Europe’s oldest university gardens.

Join us for a special anniversary program 15–21 Sept 2025. 🎉

@unikarlova.cuni.cz @botanickazahradauk.bsky.social

@asarigun.bsky.social

There is a new version of Runs N' Poses preprint by @peterskrinjar.bsky.social and @ninjani.bsky.social comparing Boltz-2 to Boltz-1 and to other co-folding methods by extension (though not yet to classical docking).

@mdc-biocat.bsky.social - how did comparison of Boltz-2 to PocketVina turn out?

Machine Learning in Computational Biology 2025 YouTube video by Machine Learning in Computational Biology

YouTube link for MLCB2025 is up! Starting in 30 min. www.youtube.com/live/19I7xTh...

Day 3 opened with Kenneth Atz @Roche tackling the holy grail of #CADD: P-L binding #affinity prediction. By reframing limits of data & models, we can focus on the next solvable challenges - a sharp reminder of complexity & progress ahead.
#CECAM @cecamevents.bsky.social @iocbprague.bsky.social

This afternoon at our @cecamevents.bsky.social Workshop in Prague:
Talks by Ulf Ryde, Ran Friedman & Charles-Alexandre Mattelaer explored QM methods for binding affinity, energy decomposition & binding geometries. Great discussions on rigorous QM in drug design!
#compchem @iocbprague.bsky.social

Morning session of our #CECAM Workshop in Prague featured @gdefabritiis.bsky.social presenting a ML force field for drug discovery, Julien Michel on electrostatic embedding for ML/MM free energy calcs, and Carlos Cruz Marin on ML models for logP.
@iocbprague.bsky.social @cecamevents.bsky.social

Closing Day2 with exciting talks:
M.Lepsik on #SQM scoring on AI-generated structures,M.Hennemann on local properties at P-L interfaces & I.Gordiy on enhanced sampling with ML potentials.Inspiring end before our social dinner!
@cecamevents.bsky.social @iocbprague.bsky.social @iocbtech.bsky.social

We opened Day 2 of our #CECAM flagship workshop in Prague with the CECAM director Andrea Cavalli, highlighting steered #MD, dynamical docking & the complexity of binding energetics, and the challenges ahead. 🚀

#CECAMinPrague @iocbprague.bsky.social @cecamevents.bsky.social @iocbtech.bsky.social

Day 1 of our #CECAM Flagship Workshop in Prague started strong!
Talks by Kennie Merz, Jan Řezáč, Markus Hermann & Hamza Ibrahim sparked great discussion on #QM, #ML & #DrugDesign

Thanks to @iocbprague.bsky.social, @iocbtech.bsky.social & @cecamevents.bsky.social for support!

#compchem #SQM

Tomorrow we kick off our #CECAM Flagship Workshop on Quantum Chemistry for Drug Design (Sept 8–10, Prague). 3 days of cutting-edge talks bridging #QM #ML & #drugdesign with world-class speakers shorturl.at/5sooU

#compchem #SQM @iocbtech.bsky.social @cecamevents.bsky.social @iocbprague.bsky.social

CATH turns 30 years old 🥳
They celebrate with a Symposium on September 16th! I'll be presenting our work: "An Atlas of Energetic Evolutionary Constraints Across Protein Families"

Unbelievable selection of speakers! So if you are around London, you can register to attend:
tinyurl.com/2pnk8hj5

Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, Christian, @sokrypton.org, Bruno and many other amazing lab members and collaborators.

www.nature.com/articles/s41...

😂

The first day of our bioML symposium at @iocbprague.bsky.social went very well. It is amazing to see how fast this field is moving forward. Thanks to everyone for the fantastic talks! 🤖🧬

Ribosome transfer via tunnelling nanotubes rescues protein synthesis in pancreatic cancer cells Background: Pancreatic ductal adenocarcinoma (PDAC) is considered as one of the deadliest types of cancer. Tunnelling nanotubes (TNTs) are thin, membranous, intercellular communication structures obse...

Our significantly expanded preprint is out. In it we show that pancreatic cancer cells can transfer ribosomes via tunnelling nanotubes and rescue protein synthesis when co-cultured with cells with impaired ribosomal biogenesis.
🧪
(Includes some #bayesian #rstats inspired by @rmcelreath.bsky.social)

New Practical Cheminformatics Post
patwalters.github.io/Three-Papers...

Travis Kalanick, the founder of Uber who no longer works at the company, appeared on All-In to talk with hosts Jason Calacanis and Chamath Palihapitiya about the future of technology. When the topic turned to AI, Kalanick discussed how he uses xAI’s Grok, which went haywire last week, praising Adolf Hitler and advocating for a second Holocaust against Jews. “I’ll go down this thread with [Chat]GPT or Grok and I’ll start to get to the edge of what’s known in quantum physics and then I’m doing the equivalent of vibe coding, except it’s vibe physics,” Kalanick explained. “And we’re approaching what’s known. And I’m trying to poke and see if there’s breakthroughs to be had. And I’ve gotten pretty damn close to some interesting breakthroughs just doing that.”

My god these guys are such spectacular morons

gizmodo.com/billionaires...

link?

😂

🎉 I am thrilled to share that our latest work on is now publicly available on @biorxivpreprint.bsky.social.

The title is "Mutations within the predicted fragment-binding region of FAM83G/SACK1G abolish ints interaction with the Ser/Thr kinase CK1α".

🔗 Pre-print: www.biorxiv.org/content/10.1...