peptide research index · robinhood chain
The body is the runtime.
Peptide discovery is a language problem. Amino acids are tokens, a sequence is a sentence, and something already knows how to read them.
the model reads biology, writes peptides.
Robinhood Chain block — · chain 4663 · CA TBA
Type what hurts.
Plain language in. Ranked peptides out, each one citing the study it came from. No account, no server — it runs in your browser.
It launches against a stock.
$bioLLM pairs against LLY — tokenized Eli Lilly stock — on long.xyz. No stablecoin pool. The index catalogues the molecules; the pair is the company that makes them.
pair asset LLY 0x8005d266423c7ea827372c9c864491e5786600ea · verify the address in Robinhood's own registry ↗
The meme is the mechanism.
Retatrutide hauls three fat jaks because it hits three receptors. All 33 →
Real molecules. Real coordinates.
Drawn from PubChem's computed coordinates — the geometry chemistry software uses. The whole wall →
Scale
The index runs from two-residue dipeptides to insulin. Bars are heavy-atom counts, to scale.
Check it yourself
Real sources
79 PubChem records, 761 Europe PMC citations, 57 entries with registered trials, 6 experimental structures, 46 parent proteins.
Checked against itself
20 sequences are mass-verified — computed backbone mass agrees with PubChem to within 1.5 Da. Where they disagree, the site says so.
Honest about gaps
Unknown fields read not characterised. Retatrutide has no published primary structure, so its sequence is blank. That blank is why the rest is worth reading.
The model writes new ones.
It reads the corpus, then writes sequences that aren't in it. Every one gets screened against the index before it ships — the method is public.
What survives goes to the registry: timestamped, hashed, open. Publish it so nobody can own it.