Presented by: Ben Lengerich, Postdoc and Alana Fellow, MIT Comp Sci and AI Lab & the Broad Institute

In biomedical data analysis, an emerging trend focuses on contextualizing observations within biological and real-world processes. This approach facilitates high-resolution, context-specific insights by integrating information across datasets, moving beyond analyzing datasets in isolation. However, modern AI systems trained by massive self-supervision across Internet-scale datasets often lack adaptability and are not directly applicable to problems of statistical inference. This presentation will examine “contextualized learning”, a meta-learning paradigm which seeks to learn relationships between dataset context and statistical parameters. Using contextualized network inference as an illustrative example, I will show how this approach yields context-specific networks, offering insights such as personalized gene expression analysis for cancer subtyping. The talk will also discuss trends towards “contextualized understanding”, bridging statistical and foundation models to standardize interpretability. The primary aim is to illustrate how contextualized learning and understanding contribute to creating learning systems that are both adaptive and persistent, facilitating cross-context information sharing and detailed analysis.