Having often dealt with binder-limited projects, we sought a more accessible source for nanobodies than yeast display or llama. Here we introduce Germinal, computationally designing antibody-like binders with such a hit rate that only tens need to be screened for each target.

Not only can we now build AI-generated bacteriophages... we can design de novo antibodies to bind them! With Germinal, a new pipeline for de novo antibody design, we move closer to a world where antibodies can be designed against virtually any protein, on demand. Check it out:

Entering my PhD, de novo antibody design was a grand challenge I thought would not be solved without huge increases in affinity data and Ab-Ag structure. Only 2 years later, we provide the first open-source recipe to get antibody binders, almost magically, out of a computer (1/3)

Santiago Mille John Wang Claudia Driscoll Haoyu Dai Xiaowei Zhang Please try out the code (and bear with us as we continue to improve it 😅) ! (3/3) Code: github.com/SantiagoMille/… Preprint: biorxiv.org/cgi/content/sh…

Designing, making, and testing antibodies the “old-fashioned way” kicked my ass back in the day. I think the next step here would be a similar pipeline for the manufacturing and testing. A lot of potential. 4-22% seems “low” until you experience what it entails.

Still boggles my mind that we can leave frameworks as-is and only edit CDRs and still reliably get nM binders. Complete opposite of what I would have expected given how hard it is to graft CDRs from one FW to another (such as humanizing mouse mAbs). First RFantibody and now this

Combine multimer structure prediction and an antibody language model to design de novo antibodies with nanomolar binding affinity. Santiago Mille John Wang Talal Widatalla Claudia Driscoll Haoyu Dai Xiaowei Zhang Xiaojing Gao Brian Hie

Love to see it!

What if we could autocomplete DNA based on function? Today in nature, we share semantic design—a strategy for function-guided design with genomic language models that leverages genomic context to create de novo genes with desired functions.🧵 nature.com/articles/s4158…

Sad I couldn’t make it, but go check out the recording (in case you missed it live) with the great Claudia Driscoll & Talal Widatalla

Santiago Mille and John Wang are presenting Germinal at 4PM ET today!

Go vote for Germinal designs! Both VHH and scFvs were designed. Click the STAR at the top-right. Here are some entries using our method: proteinbase.com/collections/ni… proteinbase.com/collections/ni… proteinbase.com/collections/ni… proteinbase.com/collections/ni… proteinbase.com/collections/ni…

may the prettiest binders win ⭐️ proteinbase.com/collections/ni… ⭐️ proteinbase.com/collections/ni… ⭐️ proteinbase.com/collections/ni… ⭐️ proteinbase.com/collections/ni… ⭐️ proteinbase.com/collections/ni…

🤔🤔🤔