Sign in

Sergey Ovchinnikov

@sokrypton.org
4.1K followers 564 following 159 posts

Scientist, Assistant Professor at MIT biology, #FirstGen

PostsRepliesMedia
Reposted by Sergey Ovchinnikov
Martin Pacesa @martinpacesa.bsky.social · 21/09/2026
ʙɪɴᴅᴄʀᴀꜰᴛ2 is out, and we're not waiting for the paper. The full code drops today, free for academic and industry use. We're releasing it early so you can start designing right now, and bring its full power to the current Adaptyv competition. github.com/PacesaLab/Bi...
4292140
Reposted by Sergey Ovchinnikov
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 19/09/2026
BFVD v3 contains 5.8M viral protein structures, 16× more than v2; 75% high quality, filling a major gap in AFDB coverage. It fully covers 72.6% of reference proteomes and spans 72.7% of ICTV species. Great work by @eunbelivable.bsky.social et al. 📄 www.biorxiv.org/content/10.6... 🌐 bfvd.foldseek.com
18431
Sergey Ovchinnikov @sokrypton.org · 18/09/2026
Ultimately, it is a major conflict of interest when a company both offers tools for research and is also doing research themselves.... We need better open models that can be run locally.
161
Sergey Ovchinnikov @sokrypton.org · 18/09/2026
In my case, it's off by default, but during my interactive sessions, it would occasionally interrupt me, asking me if it could use my session for training and I would always agree. Thinking it will improve the model for next time I need to do a similar task. Which for better or worse it did...😅
131
Sergey Ovchinnikov @sokrypton.org · 18/09/2026
I recall about ~3 months ago, claude was struggling to converting openfold weights to work inside alphafold3, I had to babysit it each step of the way. This is the session I explicity opted to share, when it asked. Now it can do it with single prompt. 🤷
170
Sergey Ovchinnikov @sokrypton.org · 18/09/2026
I do sometimes wonder how much of these improvements are actually coming from us? During my own optimizations with claude in the last year or so, eachtime claude asked if i was willing to share my session transcript, I always said yes.
1193
Sergey Ovchinnikov @sokrypton.org · 17/09/2026
static.klipy.com
The Mandalorian: This Is The Way
ALT: The Mandalorian: This Is The Way
010
Sergey Ovchinnikov @sokrypton.org · 17/09/2026
Introducing highly experimental localfold.org Building on @martinsteinegger.bsky.social af2 webgpu port, @milot.bsky.social optimizations & jax ports of af3-like models by @marielle.bsky.social, Choonghwan Lee, Julia Buhmann. WARNING: runs directly on your 💻, may drain 🪫 & eat data📱 & overheat 🔥💻
26825
Reposted by Sergey Ovchinnikov
Milot Mirdita @milot.bsky.social · 16/09/2026
ColabFold 1.6.3 is out! 2.5x faster, pip-installable, ipSAE+pDockQ2 scores. Thanks Choonghwan Lee, Marielle Russo, Gyuri Kim 🐍pip install colabfold[alphafold] CF2 Sneak Peak with AF3/Boltz/Protenix/ESMFold2… 🐍pip install "colabfold[alphafold3]@git+https://github.com/sokrypton/ColabFold@af3-preview"
29735
Sergey Ovchinnikov @sokrypton.org · 15/09/2026
Some updates: - Remote Multiplayer support fixed. - Adding support for custom PDB/AFDB inputs! (Initially implemented by @ianandersonlol.bsky.social )
1122
Sergey Ovchinnikov @sokrypton.org · 14/09/2026
Finally a more intuitaive way to learn pLDDT/pAE? 😎 sokrypton.github.io/protein_figh... (Character idea from @hannes-stark.bsky.social & Alex Waldherr)
727697
Reposted by Sergey Ovchinnikov
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 13/09/2026
Fold Spacer lets you fly through protein structures (Weekend project #2). It’s my first game: I originally set out to build a racer with structures as the tracks, but was a little too crazy. So it became this instead. You can upload your own structures. 🌐 martin-steinegger.github.io/Fold-Spacer/
215758
Sergey Ovchinnikov @sokrypton.org · 08/09/2026
We are still debugging all the other models for parity, but will soon be merged to main! 🙏
010
Sergey Ovchinnikov @sokrypton.org · 18/08/2026
some folks were complaining about side chains and not being able to draw contacts. support added!
040
Sergey Ovchinnikov @sokrypton.org · 17/08/2026
Adding better support for RNA/DNA and Ligands (just set "Load Ligands", at fetch)
160
Sergey Ovchinnikov @sokrypton.org · 15/08/2026
But can you animate the drawing part? 😛 added a "draw" button.
1122
Sergey Ovchinnikov @sokrypton.org · 15/08/2026
Removing inner outline for loops. Beginning to look like watercolor? 😎 (thanks to @martinpacesa.bsky.social for complaining about the loops).
260
Sergey Ovchinnikov @sokrypton.org · 15/08/2026
Adding support for cyclic L/D peptide mixes.
191
Sergey Ovchinnikov @sokrypton.org · 15/08/2026
Thanks! I'll see if I can reduce the file size, it's already excluding stuff from behind, but sometimes that's nearly impossible... unless you open a very dense molecule... I added support to save as png.
120
Sergey Ovchinnikov @sokrypton.org · 15/08/2026
Try for your protein at py2dmol.solab.org (Style → Cartoon)
35213
Sergey Ovchinnikov @sokrypton.org · 15/08/2026
getting close to recreating Jane Richardson's style 😎
412315
Reposted by Sergey Ovchinnikov
Yo Akiyama @yoakiyama.bsky.social · 21/07/2026
Excited to share our now published paper @cp-cell.bsky.social highlighting advances in modeling the evolution of protein-protein interactions with MSA Pairformer. Big thanks to Zhidian Zhang, Olivia Tang, @eunbelivable.bsky.social @milot.bsky.social @martinsteinegger.bsky.social and @sokrypton.org!
cell.com
Expanding the scope of protein language modeling to protein-protein interactions with MSA Pairformer
Protein language models have excelled at modeling individual proteins, but extending these capabilities to protein complexes remains a major challenge. MSA Pairformer, a parameter-efficient protein la...
26027
Sergey Ovchinnikov @sokrypton.org · 16/07/2026
A few updates: - multiplayer support expanded to 4 players - marketplace (buy/sell/trade) - outline to show units going behind buildings - mobile friendly (classic mode available via desktop) - battering rams can hold units - various optimizations and speedups
050
Sergey Ovchinnikov @sokrypton.org · 10/07/2026
I exaggered a bit, this was a 2-week project, with hourly human supervision. Though lots of core code was written via single prompt to reproduce aoe2, it took many hours of prompting to get details right and fix all the bugs. So I think game developers are safe (or about to get a boost from AI!)
110
Sergey Ovchinnikov @sokrypton.org · 10/07/2026
biosecurity concerns
010
Sergey Ovchinnikov @sokrypton.org · 09/07/2026
One thing that helped with was implementing a simulated gameplay. Have Claude run 100s of games, get feedback and update ai.js. It is still doing some silly things... but getting better. Perhaps a future direction would be to let multiple LLM compete with eachother by building better ai.js?🤠 (3/4)
251
Sergey Ovchinnikov @sokrypton.org · 09/07/2026
Any feedback/requests are welcome! If you see something strange, save the game json and share over github for debugging! github.com/sokrypton/aoe Other features: - Experimental Multiplayer support via PeerJS - Mobile/tablet support (2/4)
github.com
GitHub - sokrypton/aoe: Age of Epochs II
Age of Epochs II. Contribute to sokrypton/aoe development by creating an account on GitHub.
140
Sergey Ovchinnikov @sokrypton.org · 09/07/2026
🍹Long weekend Project: Since Claude Fable is banned for Science, I thought it might be fun to see if it can be used for something less scientific. 😎 Introducing Age of Epochs! ⚔️ An attempted reproduction of Age of Empires II in Javascript. ageofepochs.com (1/4)
2212
Sergey Ovchinnikov @sokrypton.org · 15/06/2026
Finally, the code for anyone wanting to run alphafold3 locally with openfold3 weights (including convert script) can be found here: github.com/sokrypton/al...
github.com
GitHub - sokrypton/alphafold3: AlphaFold 3 inference pipeline.
AlphaFold 3 inference pipeline. Contribute to sokrypton/alphafold3 development by creating an account on GitHub.
0110
Sergey Ovchinnikov @sokrypton.org · 15/06/2026
To get OpenFold3 (pytorch weights) working in AlphaFold3 (jax code base) was not super easy. Required an entire weekend and $40 of Claude Code credit. See breakdown of what had to change in AF3 code base to get OF3 weights to work: github.com/sokrypton/al... Commit: github.com/sokrypton/al... (2/3)
140
Sergey Ovchinnikov @sokrypton.org · 15/06/2026
New Experimental Google Colab Notebook now integrates AlphaFold3 with OpenFold3 and py2Dmol: colab.research.google.com/github/sokry... (1/3)
15515
Reposted by Sergey Ovchinnikov
Yehlin Cho @yehlincho.bsky.social · 21/05/2026
🚀 Excited to share our new work: Absolute Stability Predictor! 📊: forms.gle/4ZnXZSnTBvay... Built the MGnify Stability Dataset (1.8M+ measurements) and developed stability prediction models, together with @grocklin.bsky.social @KotaroTsuboyama, @sokrypton.org and teams.
1296
Reposted by Sergey Ovchinnikov
Simon Kozlov @sim0nsays.bsky.social · 01/05/2026
Yours truly is a proper scientist now! TL;DR: we used AI to redesign parts of essential cell machinery with only 19 canonical amino acids instead of 20. Why? Great thread by @harriswang.bsky.social provides more context and details. Let me talk a bit about the AI design part of this. 1/
1184
Reposted by Sergey Ovchinnikov
Harris Wang @harriswang.bsky.social · 01/05/2026
1/ Excited to share our new paper in Science @science.org: “Toward life with a 19-amino acid alphabet through generative artificial intelligence design.” A great collab w/ Sergey's group @sokrypton.org at MIT @columbiasysbio.bsky.social science.org/doi/10.1126/... 🦠🧬🛠️🖥️💥
science.org
Toward life with a 19–amino acid alphabet through generative artificial intelligence design
Because all known living organisms are made from at least 20 canonical amino acids, the feasibility of life using a more simplified alphabet remains unclear. In this work, we leveraged computational d...
711728
Reposted by Sergey Ovchinnikov
jproney @jproney.bsky.social · 13/03/2026
I'm excited to announce some major updates to our ProteinEBM paper with Chenxi Ou @sokrypton.org!
14111
Reposted by Sergey Ovchinnikov
Nick Polizzi @nickpolizzi.bsky.social · 11/03/2026
Our paper with @sokrypton.org using AlphaFold2 to predict small-molecule binding sites in proteins is now out in Nature Methods! 🧵 rdcu.be/e7SnX www.nature.com/articles/s41...
rdcu.be
AF2BIND: predicting small-molecule binding sites using the pair representation of AlphaFold2
Nature Methods - AF2BIND is a logistic regression model trained on AlphaFold2 pair features to predict small-molecule binding-site residues in proteins, without multiple sequence alignments,...
16921
Reposted by Sergey Ovchinnikov
Max Fürst @maxfus.bsky.social · 16/12/2025
New preprint🚨 Imagine (re)designing a protein via inverse folding. AF2 predicts the designed sequence to a structure with pLDDT 94 & you get 1.8 Å RMSD to the input. Perfect design? What if I told u that the structure has 4 solvent-exposed Trp and 3 Pro where a Gly should be? Why to be wary🧵👇
46524
Reposted by Sergey Ovchinnikov
jproney @jproney.bsky.social · 12/12/2025
As a bonus, here's a video of ProteinEBM folding up the fast-folder NTL9, rendered in stunning 2D by py2Dmol from @sokrypton.org! We hope models like ProteinEBM can serve as a step toward solving the "real" protein folding problem.
1365
Reposted by Sergey Ovchinnikov
Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 10/12/2025
An energy-based model of protein conformational space can be used to predict structure from sequence, sample from the conformational landscape, rank structures, and predict mutation effects. @sokrypton.org www.biorxiv.org/content/10.6...
04914
Reposted by Sergey Ovchinnikov
jproney @jproney.bsky.social · 10/12/2025
I'm super excited to announce the first preprint of my PhD, together with Chenxi Ou and @sokrypton.org! ML has revolutionized protein modeling, but crucial challenges remain. For example, we can't reliably predict complicated protein structures without MSAs, which limits what we can design.
2326
Reposted by Sergey Ovchinnikov
Joe Greener @jgreener64.bsky.social · 25/11/2025
An interesting study from @aidenkzj.bsky.social, @abulnaga.bsky.social and @sokrypton.org that builds on our Progres model to find pairs of proteins with circular permutations: www.biorxiv.org/content/10.1...
biorxiv.org
CIRPIN: Learning Circular Permutation-Invariant Representations to Uncover Putative Protein Homologs
Protein structure-based homology detection has been revolutionized by deep learning methods that can rapidly search massive databases. However, current structural search tools often miss proteins rela...
171
Reposted by Sergey Ovchinnikov
Ernst Schmid @ernstschmid.bsky.social · 12/11/2025
Thrilled to share that the final piece of my PhD work is now on bioRxiv! biorxiv.org/content/10.1... With support from @nvidia and the @NSF, we used AlphaFold to screen 1.6M+ protein pairs, revealing thousands of potential novel PPIs. All data can be viewed at predictomes.org/hp
biorxiv.org
Proteome-wide in silico screening for human protein-protein interactions
Protein-protein interactions (PPIs) drive virtually all biological processes, yet most PPIs have not been identified and even more remain structurally unresolved. We developed a two-step computational...
716667
Sergey Ovchinnikov @sokrypton.org · 19/11/2025
Adding support for interactive MSA viewing, including coloring by entropy! Auto download from AFDB (for both uniprot and pdb entries). (4/4)
0101
Sergey Ovchinnikov @sokrypton.org · 19/11/2025
Save vectorized SVG for infinitely ♾ zoomable figures. (including support for contacts). See example: biorxiv.org/content/10.1... Zhidian Zhang @yoakiyama.bsky.social @yehlincho.bsky.social @jajoosam.bsky.social (3/4)
161
Sergey Ovchinnikov @sokrypton.org · 19/11/2025
Adding record button to save animation. (2/4)
120
Sergey Ovchinnikov @sokrypton.org · 19/11/2025
A few py2Dmol updates 🧬 py2dmol.solab.org Integration with AlphaFoldDB (will auto fetch results). Drag and drop results from AF3-server or ColabFold for interactive experience! (1/4)
110331
Sergey Ovchinnikov @sokrypton.org · 29/10/2025
Is 3D dragging you down? Wish you could instead use the 2D ColabFold representation for all your work? 🤓 Introducing: py2Dmol 🧬 (feedback, suggestions, requests are welcome)
1294
Sergey Ovchinnikov @sokrypton.org · 28/10/2025
Working on the protein-hunter-chai google colab notebook. 😈 @yehlincho.bsky.social
0335
Sergey Ovchinnikov @sokrypton.org · 27/10/2025
Will it bind? A little worried about all the "TTTTTTT" 🧐 But looks cool 😎
1171
Reposted by Sergey Ovchinnikov
Yehlin Cho @yehlincho.bsky.social · 13/10/2025
Thrilled to announce our new preprint, “Protein Hunter: Exploiting Structure Hallucination within Diffusion for Protein Design,” in collaboration with @Griffin, @GBhardwaj8 and @sokrypton.org 🧬Code and notebooks will be released by the end of this week. 🎧Golden- Kpop Demon Hunters
35316