Biological and physiological processes occur across a range of spatial and temporal scales, and processes at one level of scale (e.g., gene expression inside single cells) can affect processes at other levels of scale (e.g., coordinated cell migration of endothelial cells during angiogenesis, the spatiotemporal evolution of inflammation, and the growth of a tumor). Deducing the cause-and-effect relationships that link biological and physiological processes across scales is a major challenge that computational modeling and analysis approaches seek to address.
Mechanistic models, such as differential equation-based models that describe changes in the density of a capillary network as a function of tissue oxygenation levels and growth factor concentrations, are particularly well suited for simulating and/or computing how intersecting biological processes give rise to changes over time. Hence, mechanistic models can generate new hypotheses that attempt to explain how biological processes cause biological outcomes. On the other hand, machine learning approaches such as network inference algorithms, clustering algorithms, and neural networks can integrate massive amounts of data to identify and visualize patterns, trends, and correlations in the data. Hence, machine learning algorithms point to what biological processes contribute to biological outcomes.
Although mechanistic modeling and machine learning approaches offer fundamentally different types of insights, they are highly compatible with one another. Emerging modeling approaches are combining them in ways that compensate for the deficiencies of each, while more comprehensively and efficiently leveraging large-scale data sets to produce new insights about what biological processes connect across spatial and temporal scales and how they intersect to drive changes in cells, tissues, and organs.
The goal of this Research Topic is to showcase novel methods and tools for integrating mechanistic modeling with machine learning, and present their deployment to address a range of biological and biomedical questions that require a multiscale analysis.
Papers submitted to this Research Topic should demonstrate and/or highlight both the benefits and the challenges of coupling mechanistic modeling with machine learning approaches. This Research Topic encourages a diversity of papers that address different biological contexts, physiological processes, and diseases.
This Research Topic will include both review papers and original research papers. Review papers should summarize the relevant existing literature and highlight overarching trends to date, as well as future directions. Original research papers should utilize and/or integrate both mechanistic modeling and machine learning approaches. Original papers that ONLY use either mechanistic modeling or machine learning approaches will not be considered.
We encourage original papers that present novel methods or computational tools, combine existing (i.e., published) models and/or approaches, or deploy existing models and/or approaches to study a new process or address a new problem. Authors should defend how their study takes into consideration the multiscale nature of biological and/or physiological processes.
Please note: We expect the authors to share models and algorithms publicly and encourage authors to validate model predictions by comparing them to experimental data, including published experimental data.
Biological and physiological processes occur across a range of spatial and temporal scales, and processes at one level of scale (e.g., gene expression inside single cells) can affect processes at other levels of scale (e.g., coordinated cell migration of endothelial cells during angiogenesis, the spatiotemporal evolution of inflammation, and the growth of a tumor). Deducing the cause-and-effect relationships that link biological and physiological processes across scales is a major challenge that computational modeling and analysis approaches seek to address.
Mechanistic models, such as differential equation-based models that describe changes in the density of a capillary network as a function of tissue oxygenation levels and growth factor concentrations, are particularly well suited for simulating and/or computing how intersecting biological processes give rise to changes over time. Hence, mechanistic models can generate new hypotheses that attempt to explain how biological processes cause biological outcomes. On the other hand, machine learning approaches such as network inference algorithms, clustering algorithms, and neural networks can integrate massive amounts of data to identify and visualize patterns, trends, and correlations in the data. Hence, machine learning algorithms point to what biological processes contribute to biological outcomes.
Although mechanistic modeling and machine learning approaches offer fundamentally different types of insights, they are highly compatible with one another. Emerging modeling approaches are combining them in ways that compensate for the deficiencies of each, while more comprehensively and efficiently leveraging large-scale data sets to produce new insights about what biological processes connect across spatial and temporal scales and how they intersect to drive changes in cells, tissues, and organs.
The goal of this Research Topic is to showcase novel methods and tools for integrating mechanistic modeling with machine learning, and present their deployment to address a range of biological and biomedical questions that require a multiscale analysis.
Papers submitted to this Research Topic should demonstrate and/or highlight both the benefits and the challenges of coupling mechanistic modeling with machine learning approaches. This Research Topic encourages a diversity of papers that address different biological contexts, physiological processes, and diseases.
This Research Topic will include both review papers and original research papers. Review papers should summarize the relevant existing literature and highlight overarching trends to date, as well as future directions. Original research papers should utilize and/or integrate both mechanistic modeling and machine learning approaches. Original papers that ONLY use either mechanistic modeling or machine learning approaches will not be considered.
We encourage original papers that present novel methods or computational tools, combine existing (i.e., published) models and/or approaches, or deploy existing models and/or approaches to study a new process or address a new problem. Authors should defend how their study takes into consideration the multiscale nature of biological and/or physiological processes.
Please note: We expect the authors to share models and algorithms publicly and encourage authors to validate model predictions by comparing them to experimental data, including published experimental data.