We’re excited to release a major update to the Boltz repo: v0.3.0. This release contains several important new features, including our confidence model and memory-efficient inference. Give it a try! github.com/jwohlwend/bo...
GitHub - jwohlwend/boltz: Official repository for the Boltz-1 biomolecular interaction model
Official repository for the Boltz-1 biomolecular interaction model - jwohlwend/boltz
github.com
November 28, 2024 at 4:50 PM
We’re excited to release a major update to the Boltz repo: v0.3.0. This release contains several important new features, including our confidence model and memory-efficient inference. Give it a try! github.com/jwohlwend/bo...
We’re so excited about the community’s use of Boltz-1 already! @jeremywohlwend.bsky.social has just released a new update to the Boltz-1 repo, which now automatically generates MSAs for users in seconds using the amazing Colabfold MMseqs server. Test it out here: github.com/jwohlwend/bo...
GitHub - jwohlwend/boltz: Official repository for the Boltz-1 biomolecular interaction model
Official repository for the Boltz-1 biomolecular interaction model - jwohlwend/boltz
github.com
November 21, 2024 at 8:43 PM
We’re so excited about the community’s use of Boltz-1 already! @jeremywohlwend.bsky.social has just released a new update to the Boltz-1 repo, which now automatically generates MSAs for users in seconds using the amazing Colabfold MMseqs server. Test it out here: github.com/jwohlwend/bo...
Boltz-1: Open source (MIT license) protein + PPI + PLI structure prediction method performs on par with AlphaFold3 by Gabriel Corso, Barzilay et al. & Genesis Therapeutics
Blog-post jclinic.mit.edu/boltz-1/
Technical report: t.co/px0spnTA0S
Model and code: github.com/jwohlwend/boltz
Blog-post jclinic.mit.edu/boltz-1/
Technical report: t.co/px0spnTA0S
Model and code: github.com/jwohlwend/boltz
Introducing Boltz-1: Democratizing Biomolecular Interaction Modeling – MIT Jameel Clinic
jclinic.mit.edu
November 18, 2024 at 1:37 AM
Boltz-1: Open source (MIT license) protein + PPI + PLI structure prediction method performs on par with AlphaFold3 by Gabriel Corso, Barzilay et al. & Genesis Therapeutics
Blog-post jclinic.mit.edu/boltz-1/
Technical report: t.co/px0spnTA0S
Model and code: github.com/jwohlwend/boltz
Blog-post jclinic.mit.edu/boltz-1/
Technical report: t.co/px0spnTA0S
Model and code: github.com/jwohlwend/boltz
To read more about Boltz-1 check out:
- Our short blog-post jclinic.mit.edu/boltz-1/
- Our technical report: gcorso.github.io/assets/boltz...
- Our code, model and instructions: github.com/jwohlwend/bo...
I'll share a separate thread with more details about the process and interesting findings!
- Our short blog-post jclinic.mit.edu/boltz-1/
- Our technical report: gcorso.github.io/assets/boltz...
- Our code, model and instructions: github.com/jwohlwend/bo...
I'll share a separate thread with more details about the process and interesting findings!
Introducing Boltz-1: Democratizing Biomolecular Interaction Modeling – MIT Jameel Clinic
jclinic.mit.edu
November 17, 2024 at 4:21 PM
To read more about Boltz-1 check out:
- Our short blog-post jclinic.mit.edu/boltz-1/
- Our technical report: gcorso.github.io/assets/boltz...
- Our code, model and instructions: github.com/jwohlwend/bo...
I'll share a separate thread with more details about the process and interesting findings!
- Our short blog-post jclinic.mit.edu/boltz-1/
- Our technical report: gcorso.github.io/assets/boltz...
- Our code, model and instructions: github.com/jwohlwend/bo...
I'll share a separate thread with more details about the process and interesting findings!
So pretty! (Chai-1 vs. Boltz-1)
November 29, 2024 at 6:15 AM
So pretty! (Chai-1 vs. Boltz-1)
Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!
November 17, 2024 at 4:20 PM
Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!
Boltz-1, hit the Git peeps! 🧶🧬https://github.com/jwohlwend/boltz
November 17, 2024 at 9:50 PM
Boltz-1, hit the Git peeps! 🧶🧬https://github.com/jwohlwend/boltz
Starting from tomorrow I will be in Vancouver for NeurIPS! Come talk to me about research, Boltz-1, Boltz-2... !
December 9, 2024 at 11:46 AM
Starting from tomorrow I will be in Vancouver for NeurIPS! Come talk to me about research, Boltz-1, Boltz-2... !
New Title Alert: Boltz-1- an open-source model which predicts the 3D structure of proteins, rna, dna and small molecules; it handles modified residues, covalent ligands & glycans.
Learn more here: https://buff.ly/3ZAPowA
#SBGridSoftware #SBGrid
Learn more here: https://buff.ly/3ZAPowA
#SBGridSoftware #SBGrid
GitHub - jwohlwend/boltz: Official repository for the Boltz-1 biomolecular interaction model
Official repository for the Boltz-1 biomolecular interaction model - jwohlwend/boltz
buff.ly
December 16, 2024 at 5:00 PM
New Title Alert: Boltz-1- an open-source model which predicts the 3D structure of proteins, rna, dna and small molecules; it handles modified residues, covalent ligands & glycans.
Learn more here: https://buff.ly/3ZAPowA
#SBGridSoftware #SBGrid
Learn more here: https://buff.ly/3ZAPowA
#SBGridSoftware #SBGrid
Now available: open source UI with @Gradio for Boltz-1 by
@gcorso.bsky.social
@jeremywohlwend.bsky.social
Check it out on HuggingFace spaces. h/t
@huggingface.bsky.social
for community L4 GPU: huggingface.co/spaces/simon...
@gcorso.bsky.social
@jeremywohlwend.bsky.social
Check it out on HuggingFace spaces. h/t
@huggingface.bsky.social
for community L4 GPU: huggingface.co/spaces/simon...
Boltz 1 - a Hugging Face Space by simonduerr
Boltz-1
huggingface.co
November 21, 2024 at 8:02 PM
Now available: open source UI with @Gradio for Boltz-1 by
@gcorso.bsky.social
@jeremywohlwend.bsky.social
Check it out on HuggingFace spaces. h/t
@huggingface.bsky.social
for community L4 GPU: huggingface.co/spaces/simon...
@gcorso.bsky.social
@jeremywohlwend.bsky.social
Check it out on HuggingFace spaces. h/t
@huggingface.bsky.social
for community L4 GPU: huggingface.co/spaces/simon...
Bonus: you can now watch on YouTube the recording of the seminar we gave on Boltz-1 with @mmbronstein.bsky.social and VantAI! www.youtube.com/watch?v=mN5p...
Boltz-1: Democratizing Biomolecular Interaction Modeling | Jeremy Wohlwend, Gabriele Corso
YouTube video by VantAI
www.youtube.com
December 21, 2024 at 5:08 PM
Bonus: you can now watch on YouTube the recording of the seminar we gave on Boltz-1 with @mmbronstein.bsky.social and VantAI! www.youtube.com/watch?v=mN5p...
Here is how Boltz-1 (green), DynamicBind (magenta), and GNINA (blue) dock a collection of random molecules. GNINA, using a classical sampling algorithm (MCMC) hits all concave regions while the ML samplers have distinct preferences. Boltz is the most likely to induce a fit.
November 22, 2024 at 6:27 PM
Here is how Boltz-1 (green), DynamicBind (magenta), and GNINA (blue) dock a collection of random molecules. GNINA, using a classical sampling algorithm (MCMC) hits all concave regions while the ML samplers have distinct preferences. Boltz is the most likely to induce a fit.
Boltz & Chai differ in one key respect: antibody-antigen modeling
November 30, 2024 at 9:33 PM
Boltz & Chai differ in one key respect: antibody-antigen modeling
We test Boltz-1 on various benchmarks and demonstrate it matches the performance of Chai-1. E.g. on CASP15, Boltz-1 demonstrates strong protein-ligand and protein-protein performance achieving an LDDT-PLI of 65% (40% for Chai-1), and a proportion of DockQ>0.23 of 83% (76% for Chai-1)
November 17, 2024 at 4:21 PM
We test Boltz-1 on various benchmarks and demonstrate it matches the performance of Chai-1. E.g. on CASP15, Boltz-1 demonstrates strong protein-ligand and protein-protein performance achieving an LDDT-PLI of 65% (40% for Chai-1), and a proportion of DockQ>0.23 of 83% (76% for Chai-1)
MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures
With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly
www.eurekalert.org/news-release...
With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly
www.eurekalert.org/news-release...
MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures
Researchers in the MIT Jameel Clinic for Machine Learning in Health developed a fully open-source biomolecular structure prediction model that achieves state-of-the-art performance, at the level of Al...
www.eurekalert.org
December 22, 2024 at 5:33 PM
MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures
With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly
www.eurekalert.org/news-release...
With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly
www.eurekalert.org/news-release...
I am thrilled to release ProteinDJ: a high-performance and modular protein design pipeline. Our open-source workflow incorporates #RFdiffusion, #ProteinMPNN, #FAMPNN, #AlphaFold2 and #Boltz-2. It is a fast, free, and fun way to design proteins (1/5)
doi.org/10.1101/2025.09.24.678028 #proteindesign
doi.org/10.1101/2025.09.24.678028 #proteindesign
September 28, 2025 at 9:16 PM
I am thrilled to release ProteinDJ: a high-performance and modular protein design pipeline. Our open-source workflow incorporates #RFdiffusion, #ProteinMPNN, #FAMPNN, #AlphaFold2 and #Boltz-2. It is a fast, free, and fun way to design proteins (1/5)
doi.org/10.1101/2025.09.24.678028 #proteindesign
doi.org/10.1101/2025.09.24.678028 #proteindesign
Join us next Thursday on December 5th @ Stata Center to hear from the main authors behind Boltz-1, Jeremy Wohlwend and @gcorso.bsky.social, about best practices for Boltz-1 and a vision for the exponential progress of AI in life sciences.
🎟️ Register: jclinic.mit.edu/events/boltz...
🎟️ Register: jclinic.mit.edu/events/boltz...
November 27, 2024 at 9:08 PM
Join us next Thursday on December 5th @ Stata Center to hear from the main authors behind Boltz-1, Jeremy Wohlwend and @gcorso.bsky.social, about best practices for Boltz-1 and a vision for the exponential progress of AI in life sciences.
🎟️ Register: jclinic.mit.edu/events/boltz...
🎟️ Register: jclinic.mit.edu/events/boltz...
I guess we have Boltz-1 to thank for pushing all these other AF3 clones to adopt fully open-source licenses and models.
Protenix, the AF3 reproduction made by TikTok's parent company ByteDance, is now available for commercial use with an Apache 2.0 license
GitHub - bytedance/Protenix: A trainable PyTorch reproduction of AlphaFold 3.
A trainable PyTorch reproduction of AlphaFold 3. Contribute to bytedance/Protenix development by creating an account on GitHub.
github.com
December 13, 2024 at 4:55 PM
I guess we have Boltz-1 to thank for pushing all these other AF3 clones to adopt fully open-source licenses and models.
Also from the GitHub repo: antibody antigen docking performance comparison to Boltz-1 and AF-2.3
November 28, 2024 at 2:36 PM
Also from the GitHub repo: antibody antigen docking performance comparison to Boltz-1 and AF-2.3
I've created a new plugin for #PyMOL (called PyMOLfold) that allows you to fold protein sequences right in the GUI. Simply select your model of choice (e.g., #ESM3, Boltz-1) and paste in your amino acid sequence.
github.com/colbyford/Py...
#ai #proteinfolding #alphafold
github.com/colbyford/Py...
#ai #proteinfolding #alphafold
December 13, 2024 at 1:46 PM
I've created a new plugin for #PyMOL (called PyMOLfold) that allows you to fold protein sequences right in the GUI. Simply select your model of choice (e.g., #ESM3, Boltz-1) and paste in your amino acid sequence.
github.com/colbyford/Py...
#ai #proteinfolding #alphafold
github.com/colbyford/Py...
#ai #proteinfolding #alphafold
AF3 you are so close to getting it... (maybe better with Boltz-1 with real lipids?)
December 17, 2024 at 5:15 PM
AF3 you are so close to getting it... (maybe better with Boltz-1 with real lipids?)
So according to benchmarks, boltz, alphafold3, and chai-1 all do roughly as well at predicting protein structures in aggregate.
But I was wondering if they all tend to fail and succeed on the same individual proteins, or if some algos are better at some proteins.
Plotted from the boltz benchmark:
But I was wondering if they all tend to fail and succeed on the same individual proteins, or if some algos are better at some proteins.
Plotted from the boltz benchmark:
January 29, 2025 at 4:37 PM
So according to benchmarks, boltz, alphafold3, and chai-1 all do roughly as well at predicting protein structures in aggregate.
But I was wondering if they all tend to fail and succeed on the same individual proteins, or if some algos are better at some proteins.
Plotted from the boltz benchmark:
But I was wondering if they all tend to fail and succeed on the same individual proteins, or if some algos are better at some proteins.
Plotted from the boltz benchmark: