Computational Biology Web Portal
Note: Articles considered especially worth reading are highlighted using this color .
How to build the virtual cell with artificial intelligence: Priorities and opportunities
Bunne et al. (2024): How to build the virtual cell with artificial intelligence: Priorities and opportunities
This paper is basically about the virtues of AI-powered virtuals cells (AIVCs), which the authors define as follows:
Our view of an AIVC is a learned simulator of cells and cellular systems under varying conditions and changing contexts, such as differentiation states, perturbations, disease states, stochastic fluctuations, and environmental conditions.
The authors argue that traditional computational cell models face challenges which can be overcome by models employing artificial intelligence:
Challenges include: (1) Multi-scale modeling: cells operate on multiple scales across both time and space, from atomic to molecular to cellular and histological, with functional properties emerging through nonlinear transformation from one scale to another. (2) Diverse processes with massive numbers of interacting components: cellular function encompasses numerous interacting processes, such as gene regulation, metabolic pathways, and signal transduction. Each process involves a multitude of biomolecular species, in diverse and dynamic configurations and states. (3) Nonlinear dynamics: most cellular processes are highly nonlinear, such that small changes in inputs can lead to complex changes in outputs. Thus, despite progress in modeling specific cellular processes, these factors collectively pose a substantial roadblock to the construction of a virtual cell.
Contact: cdvolko (at) gmail (dot) com
Imprint: This website is owned by Claus Volko, Vienna, Austria. No liability is taken for the contents of any of the linked websites. http://www.cdvolko.net/