Geneflow predicts large gene panels from tissue images faster
More Genes, Faster Inference: Efficient Large-Panel Spatial Transcriptomics Prediction from Histology
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Predicting detailed gene activity in tissues from microscope images is difficult and often slow, especially for many genes at once. The authors introduce GeneFlow, a simpler and faster method that uses a special type of model to directly guess gene expression levels from tissue shapes and gene patterns. GeneFlow works better than previous methods on standard tests and can predict hundreds to thousands of genes quickly, making it useful for medical and biological work. This approach might help reuse existing tissue images to discover new biology.
What this means in practice
- •For clinical data scientists: Enable faster and more comprehensive gene expression profiling from standard histology images to improve disease insight and diagnosis.
- •For biotech developers: Integrate efficient large-scale spatial gene expression prediction into tools for drug discovery and tissue analysis workflows.
Authors
Songming Zhang, Yuxiao Luo, Shifu Luo, Siran Chen, Shuquan Su, Jinyan Li
Abstract
Spatial transcriptomics (ST) prediction from histology aims to infer spatially resolved gene expression profiles directly from tissue images. This is a challenging problem that is currently often addressed with complicated model architectures, additional inputs, and complicated training procedures, while remaining limited to fixed, small gene panels. This raises a natural question: Is there an efficient method for large-panel ST prediction? Here, we present GeneFlow, a simpler yet effective framework for large-scale spatial gene expression prediction that unifies flow-matching generative modeling with structured multimodal fusion. Specifically, GeneFlow first encodes both histological morphology and cross-gene interactions in spatial spots through histology and gene tokenizers. The model directly predicts spatial gene expression, rather than an intermediate velocity field, while being trained with a velocity-based flow-matching objective. We show that, even without relying on heavy generative pipelines, GeneFlow achieves state-of-the-art performance across multiple ST benchmarks, with up to 56.8% gains in 1,000-gene prediction. Extensive experiments further show that GeneFlow produces biologically meaningful spot profiles while reducing computational cost by orders of magnitude, thereby improving efficiency and scalability, particularly in clinical settings. We believe GeneFlow provides an opportunity for leveraging widely available histology images for downstream biological discovery. Code is available at: https://github.com/ZZhangsm/GeneFlow