Mechanism-aware and multimodal AI: beyond model-agnostic interpretation

Artificial intelligence (AI) is widely used for exploiting multimodal biomedical data, with increasingly accurate predictions and modelagnostic interpretations, which are however also agnostic to biological mechanisms. Combining metabolic modelling, 'omics, and imaging data via multimodal AI can generate predictions that can be interpreted mechanistically and transparently, therefore with significantly higher therapeutic potential.