Yiquan Wang is an undergraduate in Mathematics and Applied Mathematics at Xinjiang University, and a joint-training scholar in the Tsien Excellence in Engineering Program at Tsinghua University & X-Institute. Driven to decode complex living systems, his research centers on AI for Science. Transitioning from mathematical modeling to computational biology, he pursues two complementary research directions. First, data-driven representation learning, applying deep learning to protein structure and function prediction, molecular dynamics, and multi-omics. Second, the first-principles of biological complexity, utilizing mathematical physics—such as condensed matter physics, topology, and manifold learning—to derive analytical ground truths independent of AI approximations. His overarching goal is to synergize these approaches, combining physics-based inductive biases with deep learning's expressive power to tackle formidable open challenges. These include Intrinsically Disordered Protein dynamics, Liquid-Liquid Phase Separation, 3D genome folding, rational design for undruggable targets, and Virtual Cell construction. Ultimately, he aims to combat complex human diseases and fundamentally understand life itself. His work has been published in the Journal of Chemical Information and Modeling, Physica D: Nonlinear Phenomena, and Information Sciences. He has also presented his research at main conferences including IEEE BIBM and IEEE SMC, as well as workshops at ICLR, ICML, and AAAI.