51²è¹Ý

Title: AI-Powered Systems Biology: From Timescale Modeling to Parameter Estimation & Optimization Driven Precision Therapeutics

Abstract: Biological systems are governed by highly interconnected processes operating across multiple temporal and molecular scales, making the understanding of complex diseases and the design of effective therapies extremely challenging. AI-powered systems biology offers a powerful framework for addressing this complexity by integrating multi-timescale mathematical modeling, parameter estimation, and optimization for precision therapeutics. Mechanistic pathway-based models capture interactions among signaling, gene regulation, metabolism, and proteomic dynamics, providing an interpretable systems-level view of how molecular perturbations propagate and lead to pathological states.

A central challenge in such modeling lies in the estimation of biologically meaningful parameters from sparse, noisy, and incomplete experimental data. Computational strategies that combine biological knowledge with inference and optimization methods improve parameter recovery, enhance model robustness, and reduce dependence on expensive time-course measurements. These approaches enable the construction of reliable dynamic models for complex biochemical systems operating across slow, fast, and ultrafast timescales.

The integration of machine learning with mechanistic models further extends this framework from disease understanding to therapeutic design. Such methods support biomarker discovery, identification of disease-driving perturbations, and prediction of intervention strategies capable of restoring healthier system behavior. The framework also extends to mass spectrometry–based proteomics, where protein and phosphosite turnover analysis reveals disease-relevant molecular mechanisms. Applications include RNA-independent protein accumulation in Alzheimer’s disease, phosphosite-specific effects on abnormal protein persistence, and turnover-based prediction of protein–protein interactions across tissues. Together, these advances demonstrate how AI-powered systems biology can bridge mechanistic modeling, omics analysis, and computational optimization to enable predictive, interpretable, and precision-driven therapeutics. 

About the Speaker: Dr. Abhijit Dasgupta is an assistant professor in the Department of Computer Science and Engineering at SRM University-AP, Andhra Pradesh. His research lies at the intersection of artificial intelligence, systems biology, bioinformatics, and computational medicine, with a focus on biochemical pathway modeling, parameter estimation, proteomics, and precision therapeutics. He completed his Ph.D. in Engineering through the Indian Statistical Institute, Kolkata, and Jadavpur University, where his work developed control-theoretic and AI-driven models for complex biological systems. His subsequent postdoctoral research at Systems Biology Ireland, University College Dublin, and St. Jude Children’s Research Hospital, USA, expanded this work into large-scale proteomics and multi-omics data integration. He has published widely in leading peer-reviewed journals and continues to work on bridging mechanistic modeling, machine learning, and translational biomedical research.