2 Comments
User's avatar
Julian D'Costa's avatar

I would love to see this happen. I remember messing around with GANs trying to generate anti microbial peptides back in 2020 and being sad at how small the datasets were.

How much do you think a million peptide database would actually cost? And how long would it take?

Astera

https://astera.org/first-residency-cohort/ and Renaissance Philanthropy https://renaissancephilanthropy.substack.com/ seem like they might be useful for finding funding.

Expand full comment
Luis Pedro Coelho's avatar

There are trade-offs, but $100 per peptide is probably the lowest end (assuming already some cost-reducing learning).

My current plans would actually involve a deeper characterisation (testing against multiple bacterial strains + eukaryotic cells + some NMR data), and then the cost is $500~1,000/peptide with current methods. Still, it would be possible to double the size of the databases with a relatively modest investment

Thanks for the links. I will follow-up

Expand full comment