But unfortunately:

“Thank you for your interest in the AI-coscientist Trust Test Program. Due to our current capacity, we have now closed the application form. We will scale our capacity over time to accommodate more applicants in the future.
“

Ironically this reads like GPT 3.5

Oh I haven’t tried or heard of Co-Scientist but it’s the kind of thing I’m looking to test

Sure, as long as you accept some failure rate. Maybe 80% success for 25mer peptides from a good manufacturer (e.g. JPT, SciTide, &c). For DNA it probably varies by technology, not sure what % of sequences are high purity manufactured as eg mbDNA. Not as sure about RNA but haven’t an RUO failure yet

What else kinda fits this paradigm?

Bacteriophage screening?

N-of-1 ASOs?

What else?

Personalized neoantigen targeting TCR therapies (less common) go further by actually having a distinction between target and therapeutic but the TCR is not yet computationally designed (instead isolated from the patient) and manufacturing is rough (GMP cell therapy hell)

Neoantigen vaccines come closest to embodying this paradigm but kinda cheat by making the targets and therapeutics the same thing.

Also, they don’t really work yet (which makes lack of meaningful safety screening less of a problem)

Oh these are good!

Sure! I always forget pubpeer exists but it’s a good idea