Sergei Krivov

Sergei Krivov is a Lecturer in Longitudinal AI at the School of Molecular and Cellular Biology, Faculty of Biological Sciences, University of Leeds. His research focuses on the development and application of theoretical and computational methods to analyze complex biological dynamics, particularly in protein folding and disease progression.

His research interests include:

• Protein folding free energy landscapes
• Optimal reaction coordinate theory
• Analysis of molecular dynamics simulations
• Machine learning for dynamic data
• Stochastic modeling of disease progression
• Optimal biomarker identification from longitudinal cohort studies

The methodological core of his work centers on the committor function and diffusion-based modeling of dynamics, aiming to extract meaningful, predictive insights from high-dimensional data. He develops frameworks that automate the discovery of optimal coordinates without relying on system-specific assumptions, enabling broad applicability across biological systems.

Sergei collaborates with groups producing state-of-the-art simulation data, such as those led by D.E. Shaw, and extends these principles to clinical longitudinal data for disease modeling. His work bridges computational biophysics and AI-driven health analytics.

He is actively involved in advancing machine learning algorithms tailored for dynamical systems, addressing current limitations in applying standard ML techniques to trajectory-based biological data.

No specific scientific awards or student advisement information is publicly listed. He maintains a research presence via Google Scholar and ORCID.

His laboratory or research team focuses on algorithmic development for dynamic data interpretation, particularly in the context of protein folding and patient trajectory modeling, though no formal lab name is specified.