Metraipolis › archive › dc_4083f4a199be
MIRAGE: Measuring Interpolation and Redundancy in Affinity GEneralization — arXiv:2609.14491
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14491
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T02:52:35.039Z
- SHA-256 of the archived text
f434e219b4d1c3d2f54cce5fbc72351c8338acaf4d4c38fe80f2479d703162f6- Stable URL of this page
https://metraipolis.com/documento/dc_4083f4a199be
How to cite
MIRAGE: Measuring Interpolation and Redundancy in Affinity GEneralization — arXiv:2609.14491 — arXiv (en), https://arxiv.org/abs/2609.14491 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4083f4a199be (Metraipolis archive dc_4083f4a199be, sha256 f434e219b4d1c3d2f54cce5fbc72351c8338acaf4d4c38fe80f2479d703162f6)
BibTeX
@misc{dc4083f4a199be,
title = {MIRAGE: Measuring Interpolation and Redundancy in Affinity GEneralization — arXiv:2609.14491},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14491},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4083f4a199be; sha256 f434e219b4d1c3d2f54cce5fbc72351c8338acaf4d4c38fe80f2479d703162f6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14491. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep learning now underpins structure-based drug design, from complex and affinity prediction to ligand ranking and pose generation. Recent co-folding models reportedly approach free-energy-perturbation accuracy at far lower cost. Yet standard evaluation, a single held-out correlation or pooled pose-success rate, cannot separate transferable binding principles from repeated exposure to related protein families in public databases, and practical success depends on genuinely novel targets. We introduce MIRAGE (Measuring Interpolation and Redundancy in Affinity GEneralization), a plug-in benchmark treating historical public family support (through 2019) as an explicit variable, applying a family-support axis to affinity and pose prediction via matched strata, family-disjoint controls, ligand-only baselines, and temporal evaluation. Co-folder affinity accuracy rises sharply with family support, while shallow controls that cannot exploit the test family stay flat, large for co-folders and near zero for every family-disjoint or trivial control. For Nesso-1 it survives covariate, conditioning, balancing, and clustering checks; Boltz-2's endpoint is limited by coverage. It localizes to family support rather than ligand chemistry, approaching a level from family identity alone. Rankings reverse on novel families, where a family-disjoint random forest leads both co-folders, significantly vs Nesso-1. On one external low-support target, neither co-folder beats molecular weight, corroborative rather than population-level evidence. gnina shows significant support dependence in rescoring whereas smina does not; MSA-free pose engines show larger gaps than smina redocking. This redundancy-driven inflation differs from conventional leakage. We propose reporting performance across family support plus excess over a support-insensitive baseline, and release MIRAGE as an installable benchmark and dataset. Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-09-15 in q-bio.QM). Categorie arXiv: Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2609.14491 — 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 2026-10-16T02:38:58.223Z dalla pagina https://arxiv.org/catchup/q-bio.QM/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).