
A few years ago, designing an antibody on the computer was extremely difficult. Today, there are several open-source tools which allow anyone to design antibodies from home. Out today: A step-by-step guide to antibody design. By @btnaughton.
Ariax Bio
38 posts

@AriaxBio
World-class AI-powered protein design tools like BindCraft and BoltzGen, no-code UI, and instant GPUs—30% cheaper than AWS. Just pay for compute.

A few years ago, designing an antibody on the computer was extremely difficult. Today, there are several open-source tools which allow anyone to design antibodies from home. Out today: A step-by-step guide to antibody design. By @btnaughton.







BindCraft is generating high-affinity peptides from structure alone 🧬 MDM2: 47% hit rate (7/15 tested) with nM affinity. For WDR5, structural predictions were so precise they enabled "one-shot" stapling for a 6× potency boost (Kd 39nM). No phage display. No alanine scanning. GenAI is accelerating rational chemical design with less wet-lab screening.



1/13 🧵 Today, Bindcraft was published in @Nature , one of the most famous AIs in biology for designing protein–protein interactions (PPI). In my opinion. Bindcraft represents one of the most important advances in the post–AlphaFold2 era.

1/2 🧵 We're learning how to use BindCraft at the Center for Genomic Sciences in Mexico 🇲🇽 BindCraft achieves an experimental success rate of 10–100%, compared to the 0.2% for traditional approaches 🔥 When people talk about drug design, they're actually referring to this.





Preparing PDB files for protein design usually means wrestling with PyMOL or ChimeraX. We're making it easier. Watch us use our new Prep Inputs feature to go from PDB fetch → structure trimming → hotspot selection → launching a design job in a leisurely 75 seconds.


The ability to design antibodies against any protein of interest has major implications for medicine, biotech, and basic science. Today, we introduce Germinal, a pipeline for epitope-targeted de novo antibody design achieving 4–22% success rates with efficient experimental validation.


Great blogpost by Nick Boyd and Sam Guns from Escalante Bio (posted on the other site!) blog.escalante.bio/minibinder-des… They introduce mosaic for binder design, and show some impressive results, with 7/10 and 8/10 binders working for two targets! github.com/escalante-bio/…