Correction: we stress-tested our own docking, and one of our headline claims didn't hold up
At launch we said our docking results were "in the range of approved drugs", and we pointed out a curious pattern: all three candidates had the same best-scoring target. Before moving to the lab we decided to stress-test that with control experiments.
What we did: we docked 23 unrelated molecules (steroids, triterpenoids, polyphenols, sugars, polyamines) and 7 known inhibitors into the same six pockets with identical settings, repeated the candidates with 4 random seeds, re-scored with a second scoring function, and redocked a known inhibitor into its own crystal structure.
What we found: (1) the "same best target" is an artifact of one large cavity: 22 of 26 test molecules scored best there. (2) The Vina score tracks molecule size (|r| about 0.7 to 0.94); after correcting for size none of our candidates stands out, and random steroids scored as well as our best "hit". (3) Known inhibitors are not distinguishable from size-matched random molecules in that box, and the best-known one failed to reproduce its experimental pose there (about 7.5-8 angstroms off), although it reproduced it to 0.96 angstroms in its own crystal structure. (4) Under a second scoring function the pattern mostly disappears.
So for us docking is a way to prioritize hypotheses, not evidence of binding. We have removed the "approved-drug range" wording from this launch page, our website and our chatbot. This does not mean the compounds don't work; it means docking cannot show that by itself. Independent lab assays are the decisive step, and we are arranging them now.
How we validate our AI docking pipeline before touching real molecules
Before we trust a docking score on any of our real candidates, we run the pipeline on molecules where we already know the right answer.
The method is called redocking validation: you take a protein structure from the PDB that was solved together with a bound ligand, strip the ligand out, then ask the pipeline to dock it back in blind. If the predicted pose lands close to where the crystal structure says it should, the pipeline is trustworthy for that target class.
From a docking score to a real lab report
A docking score is a prediction, not evidence. Once our virtual pipeline flags a candidate as promising against a given target, the next step is real wet-lab validation, and that part doesn't run on a laptop.
Over the past couple of weeks we've been emailing contract research organizations (CROs) directly: describing our candidates (without naming them yet), asking about assay availability, pricing, turnaround time, and sample requirements. Several have already replied with real, itemized quotes covering different assay types: enzyme activity assays, cell-based reporter assays, kinase panels.
Why we aren't naming our candidates yet
Fair question people keep asking: if you really have candidates, why not just say what they are?
Short answer: composition and use claims around a specific molecule are patentable, but only until you disclose them publicly. The moment a compound-target pairing is out in a forum post, any patent filing on that specific claim becomes much weaker or is foreclosed entirely in most jurisdictions. For a pre-seed project with no funding yet, that filing hasn't happened.
The actual targets we test against, and what would count as real proof
Following up on the "why we aren't naming our candidates" thread: the mechanisms themselves aren't the secret, and hiding them wouldn't prove anything anyway. So here they are, properly written up.
We wrote up the six protein roles our docking pipeline tests candidates against, each with the specific biomarker that would actually count as evidence of benefit, not just a docking score:
https://rasayana.andrii-it.de/bl...
Testing centuries-old alchemical remedies with modern computational drug discovery
Hi Product Hunt I'm Andrii, the solo founder behind Rasayana Virtual Lab.
The starting point: traditional longevity systems (Ayurveda, Traditional Chinese Medicine, folk pharmacology) describe hundreds of plant-derived compounds used for centuries to support vitality almost none of which have been screened against the biological mechanisms we now know drive aging.
