EVA: Towards a universal model of the immune system

2026-02-10

AI Summary

This work addresses the limitations of existing biological foundation models, which are largely confined to single-cell resolution and struggle to capture the complex cross-species, multicellular interactions characteristic of immune-mediated diseases, while also lacking evaluation frameworks aligned with drug discovery objectives. To overcome these challenges, we propose EVA—the first cross-species, multimodal foundation model for immunology and inflammation—that integrates transcriptomic and histopathological data to construct unified patient-level representations. Leveraging a multimodal fusion architecture, large-scale pretraining, transfer learning, and interpretability analyses, EVA achieves unprecedented unified modeling of the immune system across species, platforms, and resolutions. It demonstrates state-of-the-art performance across 39 tasks spanning the entire drug development pipeline, including target efficacy prediction, cross-species perturbation response, patient stratification, and treatment response forecasting. The transcriptome-based version of EVA is publicly released to accelerate research in immune-related diseases.

Technology Category

Machine Learning: Multimodal LearningComputer Vision: Multi-modal VisionHumans and AI: Other Foundations of Human Computation & AI

Application Category

Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphsSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAGUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• foundation model
• immune-mediated diseases
• multimodal representation
• cross-species
• drug development

Innovation

• foundation model
• multimodal integration
• cross-species immunology
• drug development benchmark
• scaling laws