Radoslav Krivak's Avatar

Radoslav Krivak

@rdkbio.bsky.social

🧬 Structural Bioinformatics | πŸ’Š AI/ML for Drug Discovery | Geometric DL πŸ”¬ @iocbprague.bsky.social, prev. PhD @cusbg.bsky.social @mff.unikarlova.cuni.cz

2,657 Followers  |  3,326 Following  |  142 Posts  |  Joined: 15.11.2024  |  2.077

Latest posts by rdkbio.bsky.social on Bluesky

Post image

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

22.07.2025 13:40 β€” πŸ‘ 15    πŸ” 8    πŸ’¬ 0    πŸ“Œ 2
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.

β€œI’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. β€œAnd 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.”

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. β€œI’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. β€œAnd 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...

16.07.2025 01:28 β€” πŸ‘ 5317    πŸ” 846    πŸ’¬ 284    πŸ“Œ 466

link?

14.07.2025 13:05 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

πŸ˜‚

14.07.2025 13:03 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

πŸŽ‰ 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 CK1Ξ±".

πŸ”— Pre-print: www.biorxiv.org/content/10.1...

01.07.2025 13:51 β€” πŸ‘ 4    πŸ” 1    πŸ’¬ 1    πŸ“Œ 1
Post image

We have written up a tutorial on how to run BindCraft, how to prepare your input PDB, how to select hotspots, and various other tips and tricks to get the most out of binder design!

github.com/martinpacesa...

30.06.2025 19:45 β€” πŸ‘ 135    πŸ” 54    πŸ’¬ 3    πŸ“Œ 0

VΕ‘em, kteΕ™Γ­ hΓ‘jΓ­ či podporujΓ­ ilegΓ‘lnΓ­ ΓΊtoky Izraele a USA na ÍrΓ‘n s tΓ­m, ΕΎe jde o ΓΊtok na nenΓ‘vidΔ›nΓ½ reΕΎim, jehoΕΎ pΓ‘d mΓ­stnΓ­ uvΓ­tajΓ­: PΕ™edstavte si, ΕΎe je rok 1988 a USA na obyvatele ČSSR shazujΓ­ bomby, aby jim pomohli od komunistΕ―. To by bylo radosti v ulicΓ­ch.

23.06.2025 13:54 β€” πŸ‘ 26    πŸ” 5    πŸ’¬ 3    πŸ“Œ 0

πŸš€ GPU-accelerated docking to P2Rank-predicted pockets

27.06.2025 07:25 β€” πŸ‘ 4    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0
Post image

This is cool. An archaeal species with no metabolic genes. Just replicative genes (ribosomes, messenger and transfer RNAs). 238kb genome.

www.biorxiv.org/content/10.1...

26.06.2025 22:06 β€” πŸ‘ 43    πŸ” 13    πŸ’¬ 3    πŸ“Œ 5

πŸš€ GPU-accelerated docking to P2Rank-predicted pockets

27.06.2025 07:25 β€” πŸ‘ 4    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0
Preview
Scientific institutions have a long history of anticipatory obedience Societies should learn from this and speak up to support inclusion

Scientific institutions have a long history of anticipatory obedience
www.chemistryworld.com/opinion/scie...

25.06.2025 08:57 β€” πŸ‘ 4    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0
Screenshot of PrankWeb.

Screenshot of PrankWeb.

πŸš€ Our paper on the updated PrankWeb, a web app for protein binding site prediction using P2Rank, is out in
@narjournal.bsky.social. Now with docking integration!

πŸ‘¨β€πŸ’» Try it: prankweb.cz
πŸ“„ Paper: doi.org/10.1093/nar/...
πŸ’» GitHub: github.com/cusbg/prankweb

Developed at @cusbg.bsky.social

10.06.2025 15:09 β€” πŸ‘ 24    πŸ” 7    πŸ’¬ 2    πŸ“Œ 2
Post image Post image

Fantastic to work with so many talented people! today at departmental conference of cell biology department of @sciencecharles.bsky.social . Many thanks to our guests from Israel for joining us and sharing their results and time with us

19.06.2025 09:06 β€” πŸ‘ 11    πŸ” 5    πŸ’¬ 3    πŸ“Œ 0

h/t @cpf-xyz.bsky.social

19.06.2025 09:49 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Claude Code

19.06.2025 09:48 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

Not only the Prague planetarium have the most modern LED projection in the world. They also do have these awesome mirrors on toilets! How cool is that?! 😍

18.06.2025 20:59 β€” πŸ‘ 10    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

β€œWhat is common knowledge in your field, but shocks outsiders?”

Most drugs have several activities in the human body, and discovery of these effects goes on for years after they are on the market.

17.06.2025 13:18 β€” πŸ‘ 163    πŸ” 31    πŸ’¬ 4    πŸ“Œ 2

Beyond that though, I have been doing this sci comm stuff for a long time, and I have NEVER before known a time when I've had to grapple with so many nonsensical claims from tech leaders. There's just a constant stream, which most of the media gobbles up. I'm frankly really tired of it. 9/9

17.06.2025 22:01 β€” πŸ‘ 75    πŸ” 27    πŸ’¬ 8    πŸ“Œ 1

Congratulations! πŸŽ‰

16.06.2025 19:25 β€” πŸ‘ 4    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0
Preview
PrankWeb 4: a modular web server for protein–ligand binding site prediction and downstream analysis Abstract. Knowledge of protein–ligand binding sites (LBSs) is crucial for advancing our understanding of biology and developing practical applications in f

Looks like it got truncated. Here's the correct one: doi.org/10.1093/nar/...

12.06.2025 15:34 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

just don't take the brown acid

12.06.2025 12:06 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
PrankWeb 4: a modular web server for protein–ligand binding site prediction and downstream analysis Abstract. Knowledge of protein–ligand binding sites (LBSs) is crucial for advancing our understanding of biology and developing practical applications in f

Looks like the link to the paper was truncated. Here's the correct one: doi.org/10.1093/nar/...

11.06.2025 07:09 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

@davhox.bsky.social
@majek.bsky.social

10.06.2025 15:10 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Screenshot of PrankWeb.

Screenshot of PrankWeb.

πŸš€ Our paper on the updated PrankWeb, a web app for protein binding site prediction using P2Rank, is out in
@narjournal.bsky.social. Now with docking integration!

πŸ‘¨β€πŸ’» Try it: prankweb.cz
πŸ“„ Paper: doi.org/10.1093/nar/...
πŸ’» GitHub: github.com/cusbg/prankweb

Developed at @cusbg.bsky.social

10.06.2025 15:09 β€” πŸ‘ 24    πŸ” 7    πŸ’¬ 2    πŸ“Œ 2

@davhox.bsky.social
@majek.bsky.social

10.06.2025 15:06 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Hardly surprising

08.06.2025 03:32 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS - Nature Biotechnology A transformer model is used to construct the DreaMS Atlasβ€”a molecular network of 201 million MS/MS spectra.

Mass spectrometry is a key method to discover and identify molecules in biological and environmental samples. Yet, >90% of mass spectra remain hard to interpret. In our recent paper, we present DreaMS β€” a foundation model to interpret mass spectra of small molecules.
www.nature.com/articles/s41...

26.05.2025 13:44 β€” πŸ‘ 25    πŸ” 10    πŸ’¬ 1    πŸ“Œ 0
Post image

βš›οΈ @pluskal-lab.org from IOCB Prague, together with his student @roman-bushuiev.bsky.social and colleagues from #CIIRC CTU, Josef Ε ivic and @anton-bushuiev.bsky.social, have developed a machine learning model called #DreaMS – which accelerates the analysis of previously unknown molecules.

28.05.2025 13:42 β€” πŸ‘ 11    πŸ” 5    πŸ’¬ 1    πŸ“Œ 0
Post image

I am #exhilarated to share that our new paper "LIGYSIS-web: a resource for the analysis of protein-ligand binding sites" is now published in @narjournal.bsky.social! After almost two years of development and more than 600 commits, LIGYSIS-web is out!

πŸ“œ : tinyurl.com/utges-LIGYSI...

19.05.2025 10:37 β€” πŸ‘ 27    πŸ” 11    πŸ’¬ 2    πŸ“Œ 0
Binformatics seminar Petr Daněček David Hoksza Marian NovotnΓ½

Join us for the next #Bioinformatics seminar hosted by
@sciencecharles.bsky.social and @mff.unikarlova.cuni.cz. Nora Martin from CRG : β€œHow does the structure of a genotype-phenotype map shape variation and evolutionary processes?”.

πŸ“… Wed, Apr 30
πŸ•• 17:20

bioinformatics.cuni.cz/seminar

28.04.2025 15:59 β€” πŸ‘ 7    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0

@rdkbio is following 20 prominent accounts