Editorial: Artificial Intelligence (AI) Optimized Systems Modeling for the Deeper Understanding of Human Cancers

Abstract

Cancer research in the field of Computational Systems Biology attempts to address questions that will advance current knowledge in the mechanisms of cancer progression or treatment resistance. By analyzing multi-omics data and developing a predictive mathematical and/or computational model of an unknown biological system, we can systematically understand 1) themechanisms that tie altered gene expression and downstream molecular mechanisms to functional cancer phenotypes (Colaprico et al., 2020; Menyhárt and Győrffy, 2021); 2) and/or the mechanisms that tie tumor morphology to functional cancer phenotypes (Koutsogiannouli et al., 2013; Suhail et al., 2019); 3) and/or the mechanisms that tie treatment sequence and combination to evolving functional cancer phenotypes (Yalcin et al., 2020). Currently, systems biology still faces some challenges, includingmodel calibration, model validation and generalization, computational efficiency, and the feasibility of clinical transition (Ching et al., 2018). Recent developments in artificial intelligence technologies, e.g., deep learning (DL), allow us tomodel the hierarchical structure of real biological systems, efficiently converting gene-level data to pathway-level information with an ultimate impact on cell phenotype (Gazestani and Lewis, 2019). Furthermore, such computational models could require fewer training samples, are more generalizable across diverse biological contexts, and can make predictions that are more consistent with the current understanding on the inner-workings of biological systems (Brodland, 2015). This special issue entitled “Artificial Intelligence (AI) Optimized Systems Modeling for the Deeper Understanding of Human Cancers” in Frontiers in Bioengineering and Biotechnology, and Frontiers in Genetics aims to provide an international forum for: