Metraipolis › archive › dc_26aa19770204
Aptamers as a sandbox for lab-in-the-loop agentic molecular discovery — arXiv:2610.24806
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.24806
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:07:15.245Z
- SHA-256 of the archived text
6f38555e5fbad503f6386fd8d69342bb4c62792bd5b40fd3f10864d2f45fb58a- Stable URL of this page
https://metraipolis.com/documento/dc_26aa19770204
How to cite
Aptamers as a sandbox for lab-in-the-loop agentic molecular discovery — arXiv:2610.24806 — arXiv (en), https://arxiv.org/abs/2610.24806 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26aa19770204 (Metraipolis archive dc_26aa19770204, sha256 6f38555e5fbad503f6386fd8d69342bb4c62792bd5b40fd3f10864d2f45fb58a)
BibTeX
@misc{dc26aa19770204,
title = {Aptamers as a sandbox for lab-in-the-loop agentic molecular discovery — arXiv:2610.24806},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.24806},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26aa19770204; sha256 6f38555e5fbad503f6386fd8d69342bb4c62792bd5b40fd3f10864d2f45fb58a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.24806. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Despite breakthroughs in AI-driven molecular generation, existing discovery pipelines operate largely in silico, with wet-lab feedback reserved for validation rather than iterative improvement. Whether large language model (LLM)-based reasoning agents can accelerate de novo discovery by iterating with lab data remains unproven. Here we use protein-binding aptamer design as a sandbox (1-2 week cycles, \$1-\$3 per candidate) to demonstrate a wet lab in a closed loop with AI systems. We tasked agentic pipelines with developing aptamer binders against $\alpha$-thrombin and myoglobin across three design-test-improve cycles ($\sim$1,000 candidates per round; $\sim$4,400 constructs). Statistically significant, bead-corrected on-target hit rates among new candidates rose across rounds from 0.0% in Round 1 to 26.0% in Round 2 and 42.1% in Round 3 on $\alpha$-thrombin (37.1% excluding literature motif descendants), and from 10.2% in Round 1 to 3.7% in Round 2 and 33.5% in Round 3 on myoglobin. Single-clone bead-binding titrations of eight full-length $\alpha$-thrombin candidates confirmed concordance with pooled sequencing enrichment (Pearson $r = 0.90$). In these assays, literature-derived motifs engineered by the agents to reduce off-target reactivity in the pooled screen reached apparent affinities of $K_D = 24.6$--$133$ nM, whereas de novo scaffolds showed low-micromolar binding ($K_D > 1\ \mu$M). We also report how our pipelines used myoglobin binding data to exploit the G-quadruplex binder space, diagnose cross-reactivity as on-target specificity dropped from 75.0% to 19.1%, and recover by developing strategies that restored specificity to 72.4%. We demonstrate that empirical lab data is more valuable than existing computational proxies, showing how iterative experimental feedback enables AI agents to diagnose assay artifacts and refine molecular designs across rounds. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Biomolecules (q-bio.BM) ; Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2610.24806 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-21T07:05:43.501Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).