| KEYWORD |
AI-based Meta-Modeling of Whole-Cell Models
keywords AI, COMPUTATIONAL BIOLOGY, DEEP LEARNING, GENERATIVE AI, MODELING AND SIMULATION, SIMULATION
Reference persons ROBERTA BARDINI, STEFANO DI CARLO, ALESSANDRO SAVINO
External reference persons Riccardo Smeriglio
Research Groups DAUIN - GR-24 - reSilient coMputer archItectures and LIfE Sci - SMILIES
Description This thesis proposal aims to develop a comprehensive AI-based meta-model that unifies multiple existing whole-cell models into a single, coherent framework. Whole-cell models attempt to simulate the full genomic and molecular machinery underlying cellular functions, but current approaches are often fragmented, employ heterogeneous infrastructures, and lack consistent integration strategies. By harnessing state-of-the-art artificial intelligence and deep learning techniques, this work will create a meta-model capable of accurately reproducing the behavior of various whole-cell models, effectively capturing the functional intricacies of cells at a systems level.
The project will encompass the aggregation of existing whole-cell simulations, the application of machine learning algorithms to identify patterns and key regulatory nodes, and the development of a fast and precise predictive meta-model. Rigorous evaluation against benchmark datasets and established computational frameworks will ensure the robustness and generalizability of the resulting AI-based meta-model. The candidate will gain expertise in artificial intelligence methodologies, meta-modeling techniques, Python-based algorithm development, and fine-tuning complex neural architectures through this integrative and innovative approach, ultimately contributing to a more unified understanding of cellular dynamics.
Deadline 10/12/2025
PROPONI LA TUA CANDIDATURA