Protein Therapeutics
Are mini proteins the new antibodies?
Mini proteins are highly stable, easy to manufacture, and very quick to design thanks to recent AI methods. Unlike mAbs, there is a large body of structural data to train machine learning models on to generate de novo mini protein binders. Of course, there are many apparent drawbacks to using mini proteins.
Short half-lives can be tackled by fusing to Fc domains. Although it's not clear what the advantage over antibodies are here. The most promising approach seems to be designing binders to sites that antibodies don't recognize, e.g. intracellular targets where antibodies are too large to pass the cell membrane.
Another common concern appears to be immunogenicity, I'll quote David Baker here: "The immunogenicity of designed proteins are lower than you'd expect. There have been clinical trials now of our designed cytokine mimic, and it elicited very little antibodies, and all the antiviral proteins have been in many animal system and there's no sign of any neutralizing antibody response."
In unique cases such as radiopharmaceuticals (Aktis Oncology comes to mind), mini proteins' small size is a benefit, where having filtration through the kidney is quite useful.
Learn More
David Baker's talk "The Coming of Age of De Novo Protein Design"
and the Nature News feature "AI has dreamt up a blizzard of new proteins. Do any of them actually work?" shed some light onto this question as well.
I wanted to highlight the multiple published protocols that generate experimentally validated, nanomolar binders to diverse targets available on Tamarind Bio below.
BindCraft(Pacesa et. al.): http://tamarind.bio/bindcraft
Automated pipeline using AlphaFold to generate binders with 10-100% experimental success rate for challenging targets such as cellular receptors, allergens, de novo designed proteins, and CRISPR-Cas9.
RFdiffusion Binder Design Pipeline(Bennet, Watson, Juergens et. al.): http://tamarind.bio/protein-design
Combined scoring using AlphaFold and ProteinMPNN with RFdiffusion for experimentally validated high affinity binders.