Hannes Stark
@hannes-stark.bsky.social
MIT PhD Student - ML for biomolecules - https://hannes-stark.com/
Everything is integrated in one easy to use end-to-end pipeline! Just type up your design specification and try it out!
October 26, 2025 at 10:40 PM
Everything is integrated in one easy to use end-to-end pipeline! Just type up your design specification and try it out!
This results in a design specification language for various constraints – including covalent bonds, structure groups, binding sites, secondary structures and design masks – that steer the diffusion process towards specific design objectives during inference.
October 26, 2025 at 10:40 PM
This results in a design specification language for various constraints – including covalent bonds, structure groups, binding sites, secondary structures and design masks – that steer the diffusion process towards specific design objectives during inference.
With this we train a model with the standard AF3 / Boltz-2 scalable architecture that has proven state-of-the-art for folding. Injecting conditioning inputs allows us to control the designed binder in various ways
October 26, 2025 at 10:40 PM
With this we train a model with the standard AF3 / Boltz-2 scalable architecture that has proven state-of-the-art for folding. Injecting conditioning inputs allows us to control the designed binder in various ways
Due to a purely geometry-based encoding of designed residues this unified boils down to supervising with the same diffusion loss for structure prediction and design.
October 26, 2025 at 10:40 PM
Due to a purely geometry-based encoding of designed residues this unified boils down to supervising with the same diffusion loss for structure prediction and design.
BoltzGen’s success stems from its unification of design and structure prediction. A purely geometry-based representation of designed residues enables scalable training on both tasks. As a result, unlike any previous design model, BoltzGen matches the performance of SOTA folding
October 26, 2025 at 10:40 PM
BoltzGen’s success stems from its unification of design and structure prediction. A purely geometry-based representation of designed residues enables scalable training on both tasks. As a result, unlike any previous design model, BoltzGen matches the performance of SOTA folding
We have more campaigns where the validation goes beyond binding: we test 6 BoltzGen designs against each of 3 diversely structured peptides. We obtain nM binders against two and uM against the third. For every target, at least on design neutralizes its antimicrobial activity.
October 26, 2025 at 10:40 PM
We have more campaigns where the validation goes beyond binding: we test 6 BoltzGen designs against each of 3 diversely structured peptides. We obtain nM binders against two and uM against the third. For every target, at least on design neutralizes its antimicrobial activity.
For peptides, we e.g., succeed for designing linear and disulfide-bonded peptides against crucial metabolic pathway targets and disordered proteins. When testing 5 designs, we have one success, posing the first evidence of de-novo peptides binding disordered proteins.
October 26, 2025 at 10:40 PM
For peptides, we e.g., succeed for designing linear and disulfide-bonded peptides against crucial metabolic pathway targets and disordered proteins. When testing 5 designs, we have one success, posing the first evidence of de-novo peptides binding disordered proteins.
We go after targets that require generalization. E.g. we tested 15 nanobodies against each of 9 targets selected for their dissimilarity to any protein with an existing bound structure. For 6 of 9 targets we obtain nM binders. The same 67% success rate holds for miniproteins 🤗
October 26, 2025 at 10:40 PM
We go after targets that require generalization. E.g. we tested 15 nanobodies against each of 9 targets selected for their dissimilarity to any protein with an existing bound structure. For 6 of 9 targets we obtain nM binders. The same 67% success rate holds for miniproteins 🤗
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!
October 26, 2025 at 10:40 PM
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!
Reading group session on Monday: "Lookup multivariate Kolmogorov-Arnold Networks" arxiv.org/abs/2509.07103 with Sergey Pozdnyakov
On zoom at 9am PT / 12pm ET / 6pm CE(S)T: portal.valencelabs.com/starklyspeak...
On zoom at 9am PT / 12pm ET / 6pm CE(S)T: portal.valencelabs.com/starklyspeak...
October 19, 2025 at 6:34 PM
Reading group session on Monday: "Lookup multivariate Kolmogorov-Arnold Networks" arxiv.org/abs/2509.07103 with Sergey Pozdnyakov
On zoom at 9am PT / 12pm ET / 6pm CE(S)T: portal.valencelabs.com/starklyspeak...
On zoom at 9am PT / 12pm ET / 6pm CE(S)T: portal.valencelabs.com/starklyspeak...
Tomorrow on Zoom we talk with Tobias Kreimann about his "Transformers Discover Molecular Structure Without Graph Priors" arxiv.org/abs/2510.02259
Experiments on the new OMol25 dataset!
On zoom 9am PT / noon ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Experiments on the new OMol25 dataset!
On zoom 9am PT / noon ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
October 12, 2025 at 6:12 PM
Tomorrow on Zoom we talk with Tobias Kreimann about his "Transformers Discover Molecular Structure Without Graph Priors" arxiv.org/abs/2510.02259
Experiments on the new OMol25 dataset!
On zoom 9am PT / noon ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Experiments on the new OMol25 dataset!
On zoom 9am PT / noon ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Tomorrow we have a reading group session with @nscorley and @SimMat20 about "Accelerating Biomolecular Modeling with AtomWorks and RF3" www.biorxiv.org/content/10.1...
We will also discuss how to close the gap between AF3 and its open source replications!
portal.valencelabs.com/starklyspeak...
We will also discuss how to close the gap between AF3 and its open source replications!
portal.valencelabs.com/starklyspeak...
October 5, 2025 at 8:21 PM
Tomorrow we have a reading group session with @nscorley and @SimMat20 about "Accelerating Biomolecular Modeling with AtomWorks and RF3" www.biorxiv.org/content/10.1...
We will also discuss how to close the gap between AF3 and its open source replications!
portal.valencelabs.com/starklyspeak...
We will also discuss how to close the gap between AF3 and its open source replications!
portal.valencelabs.com/starklyspeak...
Tomorrow we discuss diffusion models for sampling unnormalized densities "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching"
arxiv.org/abs/2504.11713
Join us on zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
arxiv.org/abs/2504.11713
Join us on zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
August 3, 2025 at 11:49 PM
Tomorrow we discuss diffusion models for sampling unnormalized densities "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching"
arxiv.org/abs/2504.11713
Join us on zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
arxiv.org/abs/2504.11713
Join us on zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
In 1h we discuss "Predicting cellular responses to perturbation across diverse contexts with State" in the reading group with the author Abhinav Adduri! www.biorxiv.org/content/10.1...
Join us on zoom at 9am PT / 12pm ET: portal.valencelabs.com/starklyspeak...
Join us on zoom at 9am PT / 12pm ET: portal.valencelabs.com/starklyspeak...
July 21, 2025 at 3:02 PM
In 1h we discuss "Predicting cellular responses to perturbation across diverse contexts with State" in the reading group with the author Abhinav Adduri! www.biorxiv.org/content/10.1...
Join us on zoom at 9am PT / 12pm ET: portal.valencelabs.com/starklyspeak...
Join us on zoom at 9am PT / 12pm ET: portal.valencelabs.com/starklyspeak...
Starkly Speaking tomorrow: @bwood_m will present "UMA: A Family of Universal Models for Atoms" ai.meta.com/research/pub...
Join us on Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Join us on Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
June 29, 2025 at 7:52 PM
Starkly Speaking tomorrow: @bwood_m will present "UMA: A Family of Universal Models for Atoms" ai.meta.com/research/pub...
Join us on Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Join us on Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Monday Starkly Speaking: we understand a core diffusion model ingredient better - classifier free guidance.
Via "Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms" arxiv.org/abs/2502.07849
On Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Via "Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms" arxiv.org/abs/2502.07849
On Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
June 21, 2025 at 11:42 PM
Monday Starkly Speaking: we understand a core diffusion model ingredient better - classifier free guidance.
Via "Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms" arxiv.org/abs/2502.07849
On Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Via "Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms" arxiv.org/abs/2502.07849
On Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
On Tue 12pm ET on Zoom: Saro Passaro, Gabriele Corso, Jeremy Wohlwend will present Boltz-2!
bit.ly/boltz2-pdf
Structure models and careful affinity data handling result in an affinity predictor approaching FEP accuracy at 1000x the speed.
Zoom link: portal.valencelabs.com/starklyspeak...
bit.ly/boltz2-pdf
Structure models and careful affinity data handling result in an affinity predictor approaching FEP accuracy at 1000x the speed.
Zoom link: portal.valencelabs.com/starklyspeak...
June 14, 2025 at 5:14 PM
On Tue 12pm ET on Zoom: Saro Passaro, Gabriele Corso, Jeremy Wohlwend will present Boltz-2!
bit.ly/boltz2-pdf
Structure models and careful affinity data handling result in an affinity predictor approaching FEP accuracy at 1000x the speed.
Zoom link: portal.valencelabs.com/starklyspeak...
bit.ly/boltz2-pdf
Structure models and careful affinity data handling result in an affinity predictor approaching FEP accuracy at 1000x the speed.
Zoom link: portal.valencelabs.com/starklyspeak...
Tomorrow in our reading group we will discuss "Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional" arxiv.org/abs/2504.18506
On zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
On zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
June 8, 2025 at 7:43 PM
Tomorrow in our reading group we will discuss "Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional" arxiv.org/abs/2504.18506
On zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
On zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Reading group tomorrow: Identifying perturbation targets through causal differential networks arxiv.org/abs/2410.03380
With @menghua_wu!
Join us on Zoom at 9am PT 12pm ET 6pm CEST: portal.valencelabs.com/starklyspeak...
With @menghua_wu!
Join us on Zoom at 9am PT 12pm ET 6pm CEST: portal.valencelabs.com/starklyspeak...
June 1, 2025 at 8:58 PM
Reading group tomorrow: Identifying perturbation targets through causal differential networks arxiv.org/abs/2410.03380
With @menghua_wu!
Join us on Zoom at 9am PT 12pm ET 6pm CEST: portal.valencelabs.com/starklyspeak...
With @menghua_wu!
Join us on Zoom at 9am PT 12pm ET 6pm CEST: portal.valencelabs.com/starklyspeak...
Tomorrow @TimothyDuignan joins us to discuss "Orb-v3: atomistic simulation at scale" arxiv.org/abs/2504.06231 and surrounding models to get our understanding of that field up to date!
On Zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
On Zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
May 25, 2025 at 6:12 PM
Tomorrow @TimothyDuignan joins us to discuss "Orb-v3: atomistic simulation at scale" arxiv.org/abs/2504.06231 and surrounding models to get our understanding of that field up to date!
On Zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
On Zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Tomorrow the authors @YuanqiD and Jiajun He will present their paper "FEAT: Free energy Estimators with Adaptive Transport" arxiv.org/abs/2504.11516
Estimating FED is a strong tool for comparing drug's binding affinities
Join us on zoom at 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Estimating FED is a strong tool for comparing drug's binding affinities
Join us on zoom at 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
May 18, 2025 at 6:40 PM
Tomorrow the authors @YuanqiD and Jiajun He will present their paper "FEAT: Free energy Estimators with Adaptive Transport" arxiv.org/abs/2504.11516
Estimating FED is a strong tool for comparing drug's binding affinities
Join us on zoom at 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Estimating FED is a strong tool for comparing drug's binding affinities
Join us on zoom at 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Reading group tomorrow: @json_yim and @woodyahern present "Atom level enzyme active site scaffolding using RFdiffusion2" www.biorxiv.org/content/10.1...
Join on Zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Join on Zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
May 11, 2025 at 5:11 PM
Reading group tomorrow: @json_yim and @woodyahern present "Atom level enzyme active site scaffolding using RFdiffusion2" www.biorxiv.org/content/10.1...
Join on Zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
Join on Zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
In the reading group sessions tomorrow Ezra Erives, I and whoever joins, will discuss "A General Framework for Inference-time Scaling and Steering of Diffusion Models" arxiv.org/abs/2501.06848
On zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
On zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
April 20, 2025 at 4:47 PM
In the reading group sessions tomorrow Ezra Erives, I and whoever joins, will discuss "A General Framework for Inference-time Scaling and Steering of Diffusion Models" arxiv.org/abs/2501.06848
On zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
On zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
Reading group session tomorrow, March 24th, is at 3pm PT / 6pm ET / midnight CEST about:
"One-step Diffusion Models with f-Divergence Distribution Matching" arxiv.org/abs/2502.15681
Presented by @xuyilun2
Zoom link: portal.valencelabs.com/logg
"One-step Diffusion Models with f-Divergence Distribution Matching" arxiv.org/abs/2502.15681
Presented by @xuyilun2
Zoom link: portal.valencelabs.com/logg
March 23, 2025 at 9:47 PM
Reading group session tomorrow, March 24th, is at 3pm PT / 6pm ET / midnight CEST about:
"One-step Diffusion Models with f-Divergence Distribution Matching" arxiv.org/abs/2502.15681
Presented by @xuyilun2
Zoom link: portal.valencelabs.com/logg
"One-step Diffusion Models with f-Divergence Distribution Matching" arxiv.org/abs/2502.15681
Presented by @xuyilun2
Zoom link: portal.valencelabs.com/logg
Code: github.com/NVlabs/protc...
Humans:
Moi*, Bowen Jing*, Tomas Geffner, @jyim.bsky.social , Tommi Jaakkola, Arash Vahdat, @karstenkreis.bsky.social
Many of us will be at #ICLR2025 with this stuff, happy to chat!
Also happy to improve the NVIDIA logo a bit with this beauty made by Bowen🙃
6/6
Humans:
Moi*, Bowen Jing*, Tomas Geffner, @jyim.bsky.social , Tommi Jaakkola, Arash Vahdat, @karstenkreis.bsky.social
Many of us will be at #ICLR2025 with this stuff, happy to chat!
Also happy to improve the NVIDIA logo a bit with this beauty made by Bowen🙃
6/6
March 10, 2025 at 7:51 PM
Code: github.com/NVlabs/protc...
Humans:
Moi*, Bowen Jing*, Tomas Geffner, @jyim.bsky.social , Tommi Jaakkola, Arash Vahdat, @karstenkreis.bsky.social
Many of us will be at #ICLR2025 with this stuff, happy to chat!
Also happy to improve the NVIDIA logo a bit with this beauty made by Bowen🙃
6/6
Humans:
Moi*, Bowen Jing*, Tomas Geffner, @jyim.bsky.social , Tommi Jaakkola, Arash Vahdat, @karstenkreis.bsky.social
Many of us will be at #ICLR2025 with this stuff, happy to chat!
Also happy to improve the NVIDIA logo a bit with this beauty made by Bowen🙃
6/6