EVA: Towards a universal model of the immune system

TL;DR

EVA is a comprehensive cross-species, multimodal foundation model of immunology that improves understanding and prediction of immune responses across various biomedical tasks, aiding drug development and clinical research.

Contribution

EVA introduces a novel multimodal, cross-species immune model that harmonizes diverse biological data and demonstrates scalable improvements across multiple biomedical tasks.

Findings

EVA achieves state-of-the-art performance on 39 immune-related tasks.

Scaling model size improves pretraining and downstream task performance.

Mechanistic interpretability reveals meaningful biological features.

Abstract

The effective application of foundation models to translational research in immune-mediated diseases requires multimodal patient-level representations that can capture complex phenotypes emerging from multicellular interactions. Yet most current biological foundation models focus only on single-cell resolution and are evaluated on technical metrics often disconnected from actual drug development tasks and challenges. Here, we introduce EVA, the first cross-species, multimodal foundation model of immunology and inflammation, a therapeutic area where shared pathogenic mechanisms create unique opportunities for transfer learning. EVA harmonizes transcriptomics data across species, platforms, and resolutions, and integrates histology data to produce rich, unified patient representations. We establish clear scaling laws, demonstrating that increasing model size and compute translates to improvements in both pretraining and downstream tasks performance. We introduce a comprehensive evaluation suite of 39 tasks spanning the drug development pipeline: zero-shot target efficacy and gene function prediction for discovery, cross-species or cross-diseases molecular perturbations for preclinical development, and patient stratification with treatment response prediction or disease activity prediction for clinical trials applications. We benchmark EVA against several state-of-the-art biological foundation models and baselines on these tasks, and demonstrate state-of-the-art results on each task category. Using mechanistic interpretability, we further identify biological meaningful features, revealing intertwined representations across species and technologies. We release an open version of EVA for transcriptomics to accelerate research on immune-mediated diseases.