Modeling and Simulation of Cell Signaling Networks for Subsequent Analytics Processes Using Big Data and Machine...

Area of Science:

• Computational Biology
• Bioinformatics
• Systems Biology

Background:

• Traditional modeling and simulation of biological systems, particularly cell signaling networks, face limitations in predictive accuracy and data handling.
• The PI3K/AKT/mTOR pathway is a critical cancer-related signaling network often studied using computational methods.

Purpose of the Study:

• To investigate the integration of big data, data mining, and machine learning techniques to improve traditional modeling and simulation of biological systems.
• To enhance the capacity and predictive power of computational simulations for cell signaling pathways.

Main Methods:

• Modeling, simulation, validation, and calibration of the PI3K/AKT/mTOR signaling pathway.
• Application of big data techniques for data extraction, collection, filtering, and storage of system interactions.
• Utilizing data mining and machine learning (exploratory data analysis, feature selection, neural networks) on biological datasets.

Main Results:

• Successful modeling and simulation of the PI3K/AKT/mTOR pathway, with simulated behavior matching expected outcomes.
• Generation and analysis of large datasets detailing system component interactions over time.
• Identification of new inferences and knowledge from the biological dataset using machine learning techniques.

Conclusions:

• Integrating big data, data mining, and machine learning significantly enhances traditional approaches to biological system simulation.
• These advanced techniques increase the predictive power of computational models for cell signaling networks.
• The study demonstrates a powerful synergistic approach for advancing biological systems research.