Metraipolis › archive › dc_c59fd85b32ec

$D^{2}R^{2}$: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction — arXiv:2608.15288

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15288
License (as archived)
CC0-1.0
Archived
2026-10-18T17:13:32.969Z
SHA-256 of the archived text
06720519bdba5ba49bb0493a3aabec62c313f311ab593c34c1c9109238accb22
Stable URL of this page
https://metraipolis.com/documento/dc_c59fd85b32ec

How to cite

$D^{2}R^{2}$: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction — arXiv:2608.15288 — arXiv (en), https://arxiv.org/abs/2608.15288 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c59fd85b32ec (Metraipolis archive dc_c59fd85b32ec, sha256 06720519bdba5ba49bb0493a3aabec62c313f311ab593c34c1c9109238accb22)
BibTeX
@misc{dcc59fd85b32ec,
  title = {$D^2R^2$: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction — arXiv:2608.15288},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15288},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c59fd85b32ec; sha256 06720519bdba5ba49bb0493a3aabec62c313f311ab593c34c1c9109238accb22},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15288. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Predicting single-cell transcriptomic responses to genetic perturbations is central to functional genomics and virtual-cell modeling. Existing approaches, however, typically predict an entire expression profile as a whole, leaving the order in which individual gene responses are generated unmodeled. To address this problem, we introduce \textbf{$D^{2}R^{2}$} (\textbf{D}iscrete \textbf{D}iffusion with \textbf{R}egulation \textbf{R}einforcement), which reformulates perturbation prediction as regulation-guided gene-wise progressive generation. A Masked Discrete Diffusion Model represents expression as ordinal tokens and reconstructs a fully masked profile step by step, allowing generated gene responses to condition those that remain masked. A Regulatory Policy Module initializes the generation policy from a gene regulatory network inferred from control cells and adapts it to the perturbation and current partially generated state. Then, group-relative policy optimization refines only the ordering policy using final perturbation-effect agreement as reward. Across Norman19 and VCC-H1, $D^{2}R^{2}$ achieves the best performance on all five metrics on Norman19 and remains competitive on H1. Controlled ablations holding the generator and generation budget fixed show that biological-prior ordering improves over random ordering and is more reliable than uncertainty-based heuristics, whereas reversing the biological-prior ordering degrades every metric. Biological analyses further show that the refined policy prioritizes regulatory genes early while promoting perturbation-specific transcription factors and responsive genes. These results establish gene generation order as an effective, controllable, and biologically interpretable dimension of single-cell perturbation prediction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15288 — 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 2026-10-18T16:29:13.784Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).