Mechanism-aware and multimodal AI: beyond model-agnostic interpretation
Annalisa Occhipinti, Suraj Verma, Le Minh Thao Doan, Claudio Angione
Abstract
Artificial intelligence (AI) is widely used for exploiting multimodal biomedical data, with increasingly accurate predictions and model-agnostic 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.
Topics & Concepts
BiologyMechanism (biology)Interpretation (philosophy)Cognitive scienceEpistemologyComputational biologyEvolutionary biologyComputer sciencePsychologyPhilosophyProgramming languageSemantic Web and OntologiesAI-based Problem Solving and PlanningExplainable Artificial Intelligence (XAI)