Source Nature · Published · Open the original ↗
Safety
Multimodal cell foundation models require synergistic integration beyond alignment
Richter et al. show that simply aligning different types of biological data does not fully integrate them, revealing when data repeat the same information and, conversely, when they provide complementary insights.
Integrating measurements across modalities and scales into unified quantitative frameworks of cellular function is a central goal in computational biology. Although powerful unimodal foundation models exist, the scarcity of large-scale paired data limits joint multimodal training. This constraint favours compositional foundation models, which fuse frozen unimodal experts through a learned interface. However, it remains unclear when such fusion provides task-relevant information beyond the strongest unimodal representation rather than merely aggregating redundant signal. Here we introduce Synergistic Information Score, a metric grounded in partial information decomposition that quantifies information gain arising only from cross-modal interactions. Extending theory from self-supervised learning, we show that standard alignment-based objectives with frozen encoders collapse to detect linear redundancies, which constrains their ability to capture nonlinear synergistic states. This distinction is especially important for tasks that connect tissue morphology with gene expression. […]
The opening of the report, quoted unchanged from Nature. The full text continues at the source.