trending

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...

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.

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.

Rasayana Virtual Lab - Ancient alchemy meets modern computational drug discovery

Rasayana runs traditional longevity remedies (Ayurveda, Traditional Chinese Medicine, dietary folk pharmacology) through modern computational drug discovery: molecular docking against six aging-related protein targets. From 39 candidates, 3 finalists survived a rigorous screen, with binding affinities in the range of approved drugs. Pre-seed stage. A non-transferable Polygon membership token lets early backers pledge toward future products for a discount, crowdfunding-style, not an investment.