Metraipolis › archive › dc_6ccb74657258

When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation — arXiv:2609.04861

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04861
License (as archived)
CC0-1.0
Archived
2026-10-16T22:58:19.355Z
SHA-256 of the archived text
120d563ce9f7c172244e68fc98fc99dd625f9f26b1c47efc9a278be907790e73
Stable URL of this page
https://metraipolis.com/documento/dc_6ccb74657258

How to cite

When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation — arXiv:2609.04861 — arXiv (en), https://arxiv.org/abs/2609.04861 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ccb74657258 (Metraipolis archive dc_6ccb74657258, sha256 120d563ce9f7c172244e68fc98fc99dd625f9f26b1c47efc9a278be907790e73)
BibTeX
@misc{dc6ccb74657258,
  title = {When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation — arXiv:2609.04861},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04861},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ccb74657258; sha256 120d563ce9f7c172244e68fc98fc99dd625f9f26b1c47efc9a278be907790e73},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04861. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bidirectional discrete diffusion model appears naturally suited to genomic modeling because it can reconstruct missing sequence from both flanks. We developed GenDA (Genomic Density-optimized Absorbing Diffusion) under the additional hypothesis that entropy-guided span placement would concentrate reconstruction pressure on compositionally complex regions, improving both downstream variant-effect prediction and functional sequence generation. Our results only partially support this premise. After supervised fine-tuning, the 202M-parameter GenDA model reaches a pooled ClinVar SNV AUROC of 0.774, exceeding a similarly scaled autoregressive model by 0.103. However, a matched random-span variant reaches 0.777, providing no evidence that entropy guidance causes the ClinVar improvement. More unexpectedly, GenDA fails a zero-shot functional inpainting stress test: across promoters, enhancers, exon boundaries, and intron boundaries, it does not consistently outperform a control that shuffles the native gap while exactly preserving 3-mer composition. Failure is already present for 50--500-bp gaps, although enhancer degradation worsens at longer gaps. Diagnostics identify several boundary conditions: entropy measures local sequence complexity rather than functional importance; 1-mer tokenization limits physical context; training spans are capped at 300 bp; and high absolute AlphaGenome fidelity can coexist with negative control-normalized restoration. These results show that strong fine-tuned variant prediction, a plausible corruption prior, and functional generation are distinct claims that require separate validation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.04861 — 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 2026-10-16T22:31:32.195Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).