Physics Informed Neural Networks for Baculovirus-Insect Cell System

Vishnu Swaroopji Masampally,Surbhi Sharma,Lopamudra Giri,Kishalay Mitra

2023 NINTH INDIAN CONTROL CONFERENCE, ICC（2023）

引用 0|浏览2

暂无评分

摘要

The Baculovirus expression vector system (BEVS) is one of the widely utilized platforms for the development of recombinant proteins, virus-like particles (VLPs), and vaccines. A mathematical model tuned with data generated from such systems is critical for its optimization and control. In this work, a mathematical model driven by physics depicting such a cell behavior has been proposed and validated with experiments conducted and subsequently used to study the physics informed neural networks (PINNs). Since the governing equations are found as a set of stiff ordinary differential equations (ODEs), Stiff-PINN, a variant of PINN that is utilized to solve stiff ODEs, is implemented here. Assuming a quasi-steady state for the oxygen concentration, the equation responsible for stiffness, the results are found to be more accurate compared to regular PINN. Such Stiff-PINN models, once developed, can act as a replacement of regular PINN models having trouble to handle stiff equations of BEVS.

查看译文

关键词

Neural Network,Physical Information,Department Of Biotechnology,Baculovirus-insect Cell System,Stiffness,Mathematical Model,Oxygen Concentration,Ordinary Differential Equations,As Table,Virus-like Particles,Quasi-steady State,Evolution Of Particles,Recombinant Virus-like Particles,Mean Square Error,Complex Systems,Infected Cells,Deep Neural Network,Output Layer,Hidden Layer,Mechanistic Model,Carbon Dioxide Concentration,Input Layer,Deep Neural Network Model,Collocation Method,Adam Optimization Algorithm,Algebraic Equations,Physics-based Models,Partial Differential Equations,Traditional Neural Network,Data-driven Models

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要