Really fun and challenging (!) discussion with @cdbahl.com on BindCraft, the state of binder design, the oustanding challenges and perhaps also some misconceptions in the field 💫
www.healthtech.com/the-chain/ma...
We just passed an exciting milestone: our one thousandth member just joined @bpdmc.org!
Thank you so much to everyone who has made this journey possible, and we're excited to welcome many more wonderful folks to our nerdy protein club!
For more info, check out bpdmc.org
Quick reminder to join us at @danafarber.bsky.social tonight for a great talk by Isaac Lutz!
Very exciting! Congrats!
Here is the talk I gave @asbmb.bsky.social for the DeLano Award in Computational Biosciences in March 2026.
www.youtube.com/watch?v=g0Gv...
No joke, we've got an exciting seminar this month from Isaac Lutz
Wednesday, April 8th 2026 at 7pm EDT in Room 6055, Longwood Center, @danafarber.bsky.social
"Creativity at Scale: Problem Formulation as the Frontier of Protein Design"
bpdmc.org
Congrats Stephanie!
Only 2 weeks left to benefit from early-bird registration rate!
The 6th Protein Engineering Canada Conference will be held on June 22-24 in Ottawa, Canada.
More information here: event.fourwaves.com/pec2026/pages
New OpenFold3 preview out! (OF3p2)
It closes the gap to AlphaFold3 for most modalities.
Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9
For a deeper dive, I gave a talk on AF2BIND recently at the MIA series at the Broad Institute. Check it out! Also check out Primer by talented student Ben Fry @benf549.bsky.social (not directly involved in this work). www.youtube.com/watch?v=Cjby...
A public database of binding-site predictions in the human proteome and a google colab notebook to use the model yourself can be found here: github.com/sokrypton/af...
AF2BIND also recovered about half of liganded Cys residues in a chemoproteomics dataset (by predicting a nearby pocket to the Cys), showing good synergy. The missed pockets point to new opportunities to better train predictors on new data involving cryptic or composite pockets. Need more data!
AF2BIND predicts binding sites within proteins without relying on sidechains and performs well on unbound structures or structures that undergo large shape changes upon binding. We even showed it can find some (but not all) cryptic pockets in proteins, despite not being trained on this task.
We deployed AF2BIND across the AF2-predicted human proteome and found thousands of potentially novel binding sites missed by other binding-site predictors. These novel sites are sometimes DNA or peptide sites that have "small-molecule character" and might be druggable.
We used bait residues to approximate small molecules here, and thought we were justified because: On average, half of any small-molecule ligand in the pdb can be approximated as a linear combination of amino-acid functional groups 🤯
We trained a logistic regression model called AF2BIND using the AF2 pair embeddings between "bait residues" and a target residue of a protein as input. The model outputs the probability of the target residue being a small-molecule binding residue.
We (Artem Gazizov, Anna Lian, Jody Mou, Casper Goverde, and Sergey Ovchinnikov) wondered if embeddings from AF2 (single-chain) could be used to predict which residues in a protein would likely binding a small molecule, using only the sequence and a template structure (no MSA). AF2 did quite well!
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...
Quick reminder to join us at @danafarber.bsky.social tonight for an awesome talk by Jody Mou!
Spring is arriving in Boston and Jody Mou linkedin.com/in/jody-mou has some fresh new data to share!
Wednesday, March 11th 2026, 7pm EDT in Room 6055, Longwood Center @danafarber.bsky.social
"Computational Design of a Rapid and Orthogonal Self-Labeling Protein Tag for Live-Cell Imaging"
bpdmc.org
I had a great time nerding out about protein design with @nickpolizzi.bsky.social, and an enormous thanks to @biotechtv.bsky.social and @massbio.bsky.social for hosting us!
www.biotechtv.com/post/chris-b...
Yep, always fun to talk about proteins, especially designing them :) Thanks for having us @biotechtv.bsky.social!
I’m looking to hire a research technician for my lab at Harvard & DFCI, who would primarily work in the wet lab expressing and characterizing designed proteins, starting this summer. A great role for a recent college grad looking for an immersive research experience before grad school.
We've got Jeff Gray (graylab.jhu.edu) coming to present this month!!
Wednesday, February 25th 2026, starting at 7pm EST in Room 181, Building 68, @MIT
"Antibody language models vs. biology; protein docking denoising diffusion models vs. physics"
bpdmc.org
New Title Alert: LASErMPNN- is an all-atom ligand-conditioned protein sequence design and sidechain packing model that accounts for the presence of small molecules, including hydrogens.
Learn more here: buff.ly/cZcOmpC
#SBGridSoftware #SBGrid #StructuralBiology
Would ideally be a 2 yr commitment. I’ll update this thread with an official link to submit an application (coming soon), but in the meantime please feel free to email me with a CV and cover letter!
The tech would focus on protein-ligand binding, getting experience with biophysical methods such as SPR, ITC, fluorescence spectroscopy, NMR, X-ray crystallography, etc. Would also get experience with computational protein-design tools (though the role is primarily focused on experiments).
I’m looking to hire a research technician for my lab at Harvard & DFCI, who would primarily work in the wet lab expressing and characterizing designed proteins, starting this summer. A great role for a recent college grad looking for an immersive research experience before grad school.
Principles of in situ protein sequencing: expansion microscopy-adapted Edman degradation and amino acid recognition www.biorxiv.org/content/10.64898/2026.01...
