Metraipolis › archive › dc_6457ad05942e
AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses — arXiv:2609.32527
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32527
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:55:39.910Z
- SHA-256 of the archived text
ebf852f919ddee26abef6f79812b6c5caaf3494a9387f99483cbbd2bf77cf0dc- Stable URL of this page
https://metraipolis.com/documento/dc_6457ad05942e
How to cite
AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses — arXiv:2609.32527 — arXiv (en), https://arxiv.org/abs/2609.32527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6457ad05942e (Metraipolis archive dc_6457ad05942e, sha256 ebf852f919ddee26abef6f79812b6c5caaf3494a9387f99483cbbd2bf77cf0dc)
BibTeX
@misc{dc6457ad05942e,
title = {AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses — arXiv:2609.32527},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32527},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6457ad05942e; sha256 ebf852f919ddee26abef6f79812b6c5caaf3494a9387f99483cbbd2bf77cf0dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predicting cellular responses to genetic perturbations helps prioritize experiments in single-cell genomics, where exhaustive measurement is infeasible. While computational models increasingly predict these responses, three evaluation deficiencies obscure what their scores demonstrate. First, absolute metrics cannot separate target-specific predictions from a shared background response. Second, common metrics remain high under gene shuffling, so gene-level accuracy is never verified. Third, a score at one training size says nothing about coverage, which depends on representation-space proximity and response-constraining power. We propose AmbiModBench, a specificity-aware, gene-resolved and coverage-aware benchmark. It pairs every score with a training-mean reference fitted on the same split, screens each readout by gene-coordinate permutation, and links embedding distance to response variation. Across K562, RPE1 and Norman, strong absolute scores largely reflect shared background rather than target-specific learning. Widely used readouts track response magnitude distributions rather than the affected genes. Detectable gain follows representation-space coverage rather than training-set size. Nonetheless, on RPE1 the protocol yields a reproducible target-specific gain across five additional splits and three gene selections, which absolute scores alone cannot distinguish from shared background. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Genomics (q-bio.GN); Applications (stat.AP). Pagina del lavoro: https://arxiv.org/abs/2609.32527 — 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 2026-10-07T20:29:00.853Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).