GeroQubit: De novo molecule design for geroscience with calibrated uncertainty

Geroqubit1 pts0 comments

ABSTRACT<br>Computational molecule generation has outpaced its own credibility. We present GeroQubit, a GPU-free de-novo design platform that organizes candidates along a target × tissue × hallmark model and reports every signal alongside its measured baseline. We treat our tissue aging-signature readout as a mechanistic structural prior that we explicitly disclose is not validated against lifespan, and we surface efficacy only through a structure-to-lifespan k-NN whose weak but real signal (leave-one-out ρ ≈ 0.145) is wrapped in empirically-calibrated conformal intervals (90% target, 90.3% measured coverage). On a held-out retrospective recovery of ∼1,940 ChEMBL binders against decoys, the score reaches ROC-AUC 0.945 with ∼20× enrichment at 1% (BEDROC 0.91) and survives a scaffold-disjoint split — yet we report that it collapses to near-random (AUC 0.62) on genuinely novel chemotypes. Molecules are assembled reaction-first, so every candidate carries a verified synthetic route and atom-level synthon provenance; ADMET is handled as a multi-objective Pareto problem. We frame the disclosed weak signals and the hard-case failures not as flaws but as the honest, decision-useful output the field’s own critics demand." />

GeroQubit: a lightweight, honesty-first de-novo design platform for geroscience-native small molecules with calibrated uncertainty | bioRxiv

Skip to main content

Search for this keyword

Advanced Search

New Results

GeroQubit: a lightweight, honesty-first de-novo design platform for geroscience-native small molecules with calibrated uncertainty

View ORCID ProfileDinesh K, H. Swetha

doi: https://doi.org/10.64898/2026.06.07.730687

Dinesh K<br>1GeroQubit — independent geroscience research<br>BSc (Chemistry)<br>Find this author on Google Scholar<br>Find this author on PubMed<br>Search for this author on this site<br>ORCID record for Dinesh K<br>For correspondence:<br>dineshdeena431{at}gmail.com

H. Swetha<br>1GeroQubit — independent geroscience research<br>MSc (Chemistry)<br>Find this author on Google Scholar<br>Find this author on PubMed<br>Search for this author on this site

Abstract<br>Full Text<br>Info/History<br>Metrics<br>Preview PDF

ABSTRACT<br>Computational molecule generation has outpaced its own credibility. We present GeroQubit, a GPU-free de-novo design platform that organizes candidates along a target × tissue × hallmark model and reports every signal alongside its measured baseline. We treat our tissue aging-signature readout as a mechanistic structural prior that we explicitly disclose is not validated against lifespan, and we surface efficacy only through a structure-to-lifespan k-NN whose weak but real signal (leave-one-out ρ ≈ 0.145) is wrapped in empirically-calibrated conformal intervals (90% target, 90.3% measured coverage). On a held-out retrospective recovery of ∼1,940 ChEMBL binders against decoys, the score reaches ROC-AUC 0.945 with ∼20× enrichment at 1% (BEDROC 0.91) and survives a scaffold-disjoint split — yet we report that it collapses to near-random (AUC 0.62) on genuinely novel chemotypes. Molecules are assembled reaction-first, so every candidate carries a verified synthetic route and atom-level synthon provenance; ADMET is handled as a multi-objective Pareto problem. We frame the disclosed weak signals and the hard-case failures not as flaws but as the honest, decision-useful output the field’s own critics demand.

Competing Interest Statement<br>The authors are co-founders of GeroQubit and have a financial interest in the platform described. This is<br>disclosed in the interest of transparency

Copyright<br>The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC 4.0 International license.

Back to top

PreviousNext

Posted June 11, 2026.

Download PDF

Email

Thank you for your interest in spreading the word about bioRxiv.<br>NOTE: Your email address is requested solely to identify you as the sender of this article.

Your Email *

Your Name *

Send To *

Enter multiple addresses on separate lines or separate them with commas.

You are going to email the following<br>GeroQubit: a lightweight, honesty-first de-novo design platform for geroscience-native small molecules with calibrated uncertainty

Message Subject<br>(Your Name) has forwarded a page to you from bioRxiv

Message Body<br>(Your Name) thought you would like to see this page from the bioRxiv website.

Your Personal Message

CAPTCHAThis question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

Share

GeroQubit: a lightweight, honesty-first de-novo design platform for geroscience-native small molecules with calibrated uncertainty

Dinesh K, H. Swetha

bioRxiv 2026.06.07.730687; doi: https://doi.org/10.64898/2026.06.07.730687

Share This Article:

Copy

Citation Tools

GeroQubit: a lightweight, honesty-first de-novo design platform for geroscience-native small molecules with calibrated uncertainty

Dinesh K, H....

geroqubit novo design geroscience calibrated platform

Related Articles