Dynamical data science and AI for Biology and Medicine – Luonan Chen

Abstract

I will present a talk on “Dynamical data science and AI” for quantifying dynamical biological processes, disease progressions and various phenotypes, including dynamic network biomarkers (DNB) for early-warning signals of critical transitions, spatial-temporal information (STI) transformation for short-term time-series prediction, knockoff conditional mutual information (KOCMI) for quantifying interventional causality, partial cross-mapping (PCM) for causal inference among variables, and further AI applications to medicine. These methods are all data-driven or model-free approaches but based on the theoretical frameworks of nonlinear dynamics. We show the principles and advantages of dynamical data-science approaches for phenotype quantification as explicable, quantifiable, and generalizable. In particular, different from statistical data-science, dynamical data-science approaches exploit the essential features of dynamical systems in terms of data, e.g. strong fluctuations near a bifurcation point, low-dimensionality of a center manifold or an attractor, and phase-space reconstruction from a single variable by delay embedding theorem, and thus are able to provide different or additional information to the traditional approaches, i.e. statistics-based data science approaches. The dynamical data-science approaches for the quantifications of various phenotypes will further play an important role in the systematical research of various fields in biology and AI.