AI and Biological Systems Modelling: Computational Approaches to Complex Cellular and Molecular Processes

Helena V. Sørensen

AI and Biological Systems Modelling: Computational Approaches to Complex Cellular and Molecular Processes

Author(s)	Dr. Helena V. Sørensen
Country	United States
Abstract	Biological systems emerge from dynamic interactions among genes, proteins, metabolites, organelles, cells, and environmental signals. Their nonlinear behavior, multiscale organization, stochastic variation, feedback regulation, and context dependence make complete computational representation difficult. Conventional mechanistic models provide interpretable descriptions of defined biological processes, but their scalability is constrained by incomplete biological knowledge and the large number of parameters required for complex systems. Artificial intelligence offers complementary methods for extracting patterns from high-dimensional molecular, imaging, and single-cell datasets. This simulation-based study compares mechanistic modelling, conventional machine learning, deep learning, and hybrid physics-informed artificial intelligence across molecular, pathway, single-cell, cell-population, and multicellular levels. An illustrative multicriteria model assessed predictive performance, interpretability, scalability, perturbation responsiveness, data efficiency, and biological consistency. Simulated findings indicate that mechanistic approaches perform strongly for bounded molecular systems but decline as biological complexity increases. Deep learning improves performance across single-cell and cell-population tasks, although interpretability and out-of-distribution reliability remain concerns. Hybrid physics-informed artificial intelligence achieved the highest simulated performance across all levels because it combined data-driven representation learning with biological constraints. Its mean illustrative performance score was 91.4, compared with 73.6 for mechanistic modelling, 79.4 for conventional machine learning, and 85.2 for deep learning. These values are methodological simulations rather than experimental measurements. The study concludes that biologically credible artificial intelligence should integrate mechanistic knowledge, multimodal data, uncertainty estimation, causal testing, and laboratory validation. Such integration may improve protein modelling, pathway reconstruction, cellular-state prediction, perturbation analysis, and drug-response simulation while maintaining appropriate scientific caution.
Keywords	: artificial intelligence, systems biology, computational modelling, molecular processes, cellular dynamics, single-cell analysis, physics-informed learning, biological networks.
Field	Engineering
Published In	Volume 8, Issue 1, January-February 2026
Published On	2026-02-24

View / Download PDF File

About AJAMRI Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+1-872-302-3851	editor@ajamri.com

American Journal of Advanced Multidisciplinary Research and Innovation

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

AI and Biological Systems Modelling: Computational Approaches to Complex Cellular and Molecular Processes

Share this