About this Research Topic
Over the past decade, it has become clear that no two patients are precisely the same. Thus, the traditional therapy model, treating the disease rather than the patient, has proven ineffective. Nowhere was this more evident than in the context of chronic, non-communicable diseases. Precision medicine (PM) has emerged as an attempt to provide treatment and prevention, considering individual variability in genetics, lifestyle, behavior, and environment. However, the complexity of the response of living organisms to drugs and diseases necessitates a combination of approaches that substantially upgrade the information content of data and provides formalisms for placing the data with a rational framework. These critical functions are enabled by recent advances in machine learning (ML) and systems biology (SB), respectively.
However, both require and operate on different underlying principles: ML builds on advances in computational sciences and statistical learning to develop black/gray models, whereas SB builds on mathematical and computational representations of (semi)mechanistic models. However, each approach has limitations: ML requires substantial data, while SB requires a deeper understanding of physiology and pharmacology. One promising avenue for bridging the gap is to explore the interface of ML and SB and explore the possibility of developing hybrid models that allow us to not only capitalize on the advantages of each approach separately but, more importantly, benefit from synergies between the two
In this special issue, we are soliciting contributions that discuss applications and theoretical/computational advances to further develop and explore opportunities at the interface of SB and ML. We solicit contributions highlighting specific applications across diverse disease areas and pharmaceutical interventions, discuss theoretical challenges, or propose novel approaches, frameworks, and theoretical advances. We also welcome contributions aiming at exploring the possibility of developing standards and best practices as we move towards this novel modeling approach.
The special issue will include original scientific papers, perspectives, and reviews that fit the theme. Contributions not fitting the theme will be considered general submissions to the journal.
This topic aims to expand on discussion from the 9th International Conference on the Foundations of Systems Biology in Engineering (FOSBE 2022).
However, both require and operate on different underlying principles: ML builds on advances in computational sciences and statistical learning to develop black/gray models, whereas SB builds on mathematical and computational representations of (semi)mechanistic models. However, each approach has limitations: ML requires substantial data, while SB requires a deeper understanding of physiology and pharmacology. One promising avenue for bridging the gap is to explore the interface of ML and SB and explore the possibility of developing hybrid models that allow us to not only capitalize on the advantages of each approach separately but, more importantly, benefit from synergies between the two
In this special issue, we are soliciting contributions that discuss applications and theoretical/computational advances to further develop and explore opportunities at the interface of SB and ML. We solicit contributions highlighting specific applications across diverse disease areas and pharmaceutical interventions, discuss theoretical challenges, or propose novel approaches, frameworks, and theoretical advances. We also welcome contributions aiming at exploring the possibility of developing standards and best practices as we move towards this novel modeling approach.
The special issue will include original scientific papers, perspectives, and reviews that fit the theme. Contributions not fitting the theme will be considered general submissions to the journal.
This topic aims to expand on discussion from the 9th International Conference on the Foundations of Systems Biology in Engineering (FOSBE 2022).
Keywords: chronic, non-communicable diseases, Precision medicine, machine learning, systems biology, hybrid models, modeling, pharmaceutical
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
