MINT: Molecularly Informed Training with Spatial Transcriptomics Supervision for Pathology Foundation Models

TL;DR

MINT enhances pathology foundation models by integrating spatial transcriptomics data, improving gene expression prediction and pathology task performance through a novel fine-tuning framework that combines molecular and morphological information.

Contribution

MINT introduces a new fine-tuning method that incorporates spatial transcriptomics supervision into pretrained Vision Transformers for pathology analysis.

Findings

Achieved state-of-the-art gene expression prediction (mean Pearson r = 0.440).

Improved performance on pathology tasks (accuracy = 0.803).

Demonstrated the benefit of combining molecular and morphological data.

Abstract

Pathology foundation models learn morphological representations through self-supervised pretraining on large-scale whole-slide images, yet they do not explicitly capture the underlying molecular state of the tissue. Spatial transcriptomics technologies bridge this gap by measuring gene expression in situ, offering a natural cross-modal supervisory signal. We propose MINT (Molecularly Informed Training), a fine-tuning framework that incorporates spatial transcriptomics supervision into pretrained pathology Vision Transformers. MINT appends a learnable ST token to the ViT input to encode transcriptomic information separately from the morphological CLS token, preventing catastrophic forgetting through DINO self-distillation and explicit feature anchoring to the frozen pretrained encoder. Gene expression regression at both spot-level (Visium) and patch-level (Xenium) resolutions provides complementary supervision across spatial scales. Trained on 577 publicly available HEST samples, MINT achieves the best overall performance on both HEST-Bench for gene expression prediction (mean Pearson r = 0.440) and EVA for general pathology tasks (0.803), demonstrating that spatial transcriptomics supervision complements morphology-centric self-supervised pretraining.