BiOmics: A Foundational Agent for Grounded and Autonomous Multi-omics Interpretation

Abstract While AI has automated bioinformatic workflows, biological interpretation remains fragmented and often disconnected from mechanistic insights. Existing AI is bifurcated between statistical “black-box” models that lack logical grounding and simple agents restricted to shallow knowledge retrieval. To bridge this divide, we introduce BiOmics, a foundational agent that synthesizes multi-omics data with adaptive knowledge for biological interpretation. BiOmics introduces a novel dual-track architecture comprising a harmonized explicit reasoning space for grounded logic and a unified latent embedding space for high-dimensional association mapping. This architecture enables a transformative “Retrieving-Reasoning-Predicting” paradigm for purposeful, cross-scale inference traversing the biological hierarchy, from molecular variants to disease phenotypes. Empirical evaluations demonstrate that BiOmics surpasses state-of-the-art AI agents and specialized algorithms, markedly augmenting the granularity and depth of biological insights. Specifically, BiOmics exhibits unique superiority in uncovering indirect pathogenic variants, achieving reference-free cell annotation, and prioritizing drug repurposing candidates tailored to specific datasets. BiOmics further enriches the interpretive landscape of biological entities, leveraging its reasoning-grounded knowledge graph to uncover deep functional contexts. Ultimately, BiOmics provides a versatile engineering foundation to transition AI for Science from descriptive “data fitting” to autonomous, knowledge-driven interpretation.