Salient

scJET: Full-gene Space Single-cell Expression Generation with Patch-based Transformer Modeling

Liang, Q., Lyu, Q. R.
10.64898/2026.07.06.736701 · was preprinted
method development
Surfaced because: matches the platform's topic region.
relevance 0.40 openness 0.00 novelty 0.36 attention 0.58

Abstract

Most single-cell generative models rely on highly variable genes (HVGs) or low-dimensional latent representations, limiting their capacity to capture the complexity of full-gene features. We present scJET, a patch-based Transformer denoising framework that operates in full-gene space. scJET preserves global manifold structure, local neighborhood statistics, and gene-level expression programs. By combining scalable patch tokenization with full-gene denoising, scJET provides an efficient framework for transcriptome-wide single-cell matrix generation.

Lifecycle

Discussion

Moderated digest of third-party discussion on Bluesky — substantive endorsement and critique. 2 post(s) filtered (self-promotion, off-topic, or low-substance).

  • AI x Bio Discovery @aixbiobot.bsky.social · 787 followers neutral

    scJET: Full-gene Space Single-cell Expression Generation with Patch-based Transformer Modeling [new] leverages patch tokenization for denoising, generating transcriptome-wide matrices preserve global/local structures & gene programs.

    ♡ 0 ⇄ 0 💬 0 view on Bluesky ↗
  • #SingleCell preprints @prepub-singlecell.bsky.social · 721 followers neutral

    scJET: Full-gene Space Single-cell Expression Generation with Patch-based Transformer Modeling #SingleCell 🧪🧬🖥️ https://www.biorxiv.org/content/10.64898/2026.07.06.736701v1

    ♡ 0 ⇄ 0 💬 0 view on Bluesky ↗