Image2Gene: A Minimalist and Weakly-Supervised Framework for Morphology-Aligned Gene Expression Prediction From Histology Images

Gene expression prediction from histological images offers a promising approach for spatial transcriptome analysis without expensive sequencing. We present Image2Gene, a simple yet effective weakly supervised contrastive learning framework that predicts gene expression profiles directly from tissue morphology using only an image encoder and multiple fully connected layers. Rather than relying on complex modules or gene expression-based embedding spaces, our approach does not rely on complex modules or gene expression-based embedding spaces. Instead, it encodes spatial coordinates via a learnable embedding and uses an image encoder to extract histological image features. We then propose a novel contrastive loss function that minimizes the difference between the cosine self-similarity of image embeddings and the Pearson autocorrelation of corresponding gene expression profiles to learn a structured image representation that reflects gene expression variations. Unlike previous methods for cross-heterogeneous modality matching, our approach aligns samples solely in image space, enabling more robust and biologically meaningful similarity learning. Finally, we perform gene expression inference via k-Nearest Neighbor interpolation in the learned image embedding space. Despite its simple architecture, extensive experiments on HER+ and cSCC spatial transcriptome datasets demonstrate that Image2Gene achieves highly competitive performance, highlighting its potential as a scalable, annotation-free alternative for inferring transcriptome patterns directly from histological sections.