GenAR: Next-Scale Autoregressive Generation for Spatial Gene Expression Prediction

Jiarui Ouyang, Yihui Wang, Yihang Gao, Yingxue Xu, Shu Yang, Hao Chen

Keywords: Spatial Transcriptomics, Gene Expression Prediction, Next-Scale Prediction

Abstract: Spatial Transcriptomics (ST) offers spatially resolved gene expression but remains costly. Predicting expression directly from widely available Hematoxylin and Eosin (H&E) stained images presents a cost-effective alternative. However, most computational approaches (i) predict each gene independently, overlooking co-expression structure, and (ii) cast the task as continuous regression despite expression being discrete counts. This mismatch can yield biologically implausible outputs and complicate downstream analyses. We introduce GenAR, a multi-scale autoregressive framework that refines predictions from coarse to fine. GenAR (a) clusters genes into hierarchical groups to expose cross-gene dependencies, (b) models expression as discrete token generation over a fixed vocabulary of integer count tokens to directly predict raw counts, and (c) conditions decoding on fused histological and spatial embeddings. From an information-theoretic view, the discrete formulation operates directly on the physical count scale, and the coarse-to-fine factorization aligns with a principled conditional decomposition. Extensive experimental results on four ST datasets across different tissue types demonstrate that GenAR achieves state-of-the-art performance, offering potential implications for precision medicine and cost-effective molecular profiling. Code will be publicly available.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 6059