Sergey Ovchinnikov
@sokrypton.org
Scientist, Assistant Professor at MIT biology, #FirstGen
Reposted by Sergey Ovchinnikov
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...
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...
September 21, 2026 at 9:55 AM
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...
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...
Reposted by Sergey Ovchinnikov
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
📄 www.biorxiv.org/content/10.6...
🌐 bfvd.foldseek.com
September 19, 2026 at 6:48 AM
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
📄 www.biorxiv.org/content/10.6...
🌐 bfvd.foldseek.com
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 🔥💻
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 🔥💻
September 17, 2026 at 3:12 AM
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 🔥💻
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 🔥💻
Reposted by Sergey Ovchinnikov
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"
🐍pip install colabfold[alphafold]
CF2 Sneak Peak with AF3/Boltz/Protenix/ESMFold2…
🐍pip install "colabfold[alphafold3]@git+https://github.com/sokrypton/ColabFold@af3-preview"
September 16, 2026 at 5:14 PM
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"
🐍pip install colabfold[alphafold]
CF2 Sneak Peak with AF3/Boltz/Protenix/ESMFold2…
🐍pip install "colabfold[alphafold3]@git+https://github.com/sokrypton/ColabFold@af3-preview"
Finally a more intuitaive way to learn pLDDT/pAE? 😎
sokrypton.github.io/protein_figh...
(Character idea from @hannes-stark.bsky.social & Alex Waldherr)
sokrypton.github.io/protein_figh...
(Character idea from @hannes-stark.bsky.social & Alex Waldherr)
September 14, 2026 at 1:47 PM
Finally a more intuitaive way to learn pLDDT/pAE? 😎
sokrypton.github.io/protein_figh...
(Character idea from @hannes-stark.bsky.social & Alex Waldherr)
sokrypton.github.io/protein_figh...
(Character idea from @hannes-stark.bsky.social & Alex Waldherr)
Reposted by Sergey Ovchinnikov
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/
🌐 martin-steinegger.github.io/Fold-Spacer/
September 13, 2026 at 5:01 PM
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/
🌐 martin-steinegger.github.io/Fold-Spacer/
getting close to recreating Jane Richardson's style 😎
August 15, 2026 at 1:24 AM
getting close to recreating Jane Richardson's style 😎
Reposted by Sergey Ovchinnikov
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!
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...
www.cell.com
July 21, 2026 at 8:45 PM
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!
🍹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)
Introducing Age of Epochs! ⚔️ An attempted reproduction of Age of Empires II in Javascript.
ageofepochs.com
(1/4)
July 9, 2026 at 1:40 PM
🍹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)
Introducing Age of Epochs! ⚔️ An attempted reproduction of Age of Empires II in Javascript.
ageofepochs.com
(1/4)
New Experimental Google Colab Notebook now integrates AlphaFold3 with OpenFold3 and py2Dmol:
colab.research.google.com/github/sokry...
(1/3)
colab.research.google.com/github/sokry...
(1/3)
June 15, 2026 at 2:11 PM
New Experimental Google Colab Notebook now integrates AlphaFold3 with OpenFold3 and py2Dmol:
colab.research.google.com/github/sokry...
(1/3)
colab.research.google.com/github/sokry...
(1/3)
Reposted by Sergey Ovchinnikov
🚀 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.
📊: 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.
May 21, 2026 at 10:17 PM
🚀 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.
📊: 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.
Reposted by Sergey Ovchinnikov
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/
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/
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/... 🦠🧬🛠️🖥️💥
@columbiasysbio.bsky.social science.org/doi/10.1126/... 🦠🧬🛠️🖥️💥
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...
science.org
May 1, 2026 at 9:54 PM
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/
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/
Reposted by Sergey Ovchinnikov
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/... 🦠🧬🛠️🖥️💥
@columbiasysbio.bsky.social science.org/doi/10.1126/... 🦠🧬🛠️🖥️💥
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...
science.org
May 1, 2026 at 9:30 PM
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/... 🦠🧬🛠️🖥️💥
@columbiasysbio.bsky.social science.org/doi/10.1126/... 🦠🧬🛠️🖥️💥
Reposted by Sergey Ovchinnikov
I'm excited to announce some major updates to our ProteinEBM paper with Chenxi Ou @sokrypton.org!
March 13, 2026 at 9:37 PM
I'm excited to announce some major updates to our ProteinEBM paper with Chenxi Ou @sokrypton.org!
Reposted by Sergey Ovchinnikov
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/e7SnX
www.nature.com/articles/s41...
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,...
rdcu.be
March 11, 2026 at 2:17 PM
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/e7SnX
www.nature.com/articles/s41...
Reposted by Sergey Ovchinnikov
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🧵👇
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🧵👇
December 16, 2025 at 3:15 PM
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🧵👇
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🧵👇
Reposted by Sergey Ovchinnikov
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.
December 12, 2025 at 4:09 AM
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.
Reposted by Sergey Ovchinnikov
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...
@sokrypton.org
www.biorxiv.org/content/10.6...
December 10, 2025 at 11:17 PM
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...
@sokrypton.org
www.biorxiv.org/content/10.6...
Reposted by Sergey Ovchinnikov
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.
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.
December 10, 2025 at 3:03 PM
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.
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.
Reposted by Sergey Ovchinnikov
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...
www.biorxiv.org/content/10.1...
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...
www.biorxiv.org
November 25, 2025 at 2:43 PM
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...
www.biorxiv.org/content/10.1...
Reposted by Sergey Ovchinnikov
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
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...
biorxiv.org
November 12, 2025 at 9:26 PM
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
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)
py2dmol.solab.org
Integration with AlphaFoldDB (will auto fetch results). Drag and drop results from AF3-server or ColabFold for interactive experience! (1/4)
November 19, 2025 at 8:15 AM
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)
py2dmol.solab.org
Integration with AlphaFoldDB (will auto fetch results). Drag and drop results from AF3-server or ColabFold for interactive experience! (1/4)
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)
Introducing: py2Dmol 🧬
(feedback, suggestions, requests are welcome)
October 29, 2025 at 1:39 AM
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)
Introducing: py2Dmol 🧬
(feedback, suggestions, requests are welcome)
October 28, 2025 at 3:34 AM
Will it bind? A little worried about all the "TTTTTTT" 🧐 But looks cool 😎
October 27, 2025 at 12:07 AM
Will it bind? A little worried about all the "TTTTTTT" 🧐 But looks cool 😎