Automated analysis of the high-dimensional, multimodal data (FACS, cytometry in general, single-cell) is an active research direction in the areas of immuno-oncology and immunotherapy. Recently, increasingly more sophisticated approaches, most of the data mining/machine learning variety, have been proposed for the primary and secondary analysis of such data, exemplified by the automated gating, clustering, visualization and, subsequently and optionally, cellular population dynamic modeling. Identification of the clinically useful predictive markers (and, perhaps even more importantly, marker combinations) is another important secondary data analysis task.
In general, there is a growing need for the systems biology data analysis pipelines aimed specifically at the high-dimensional multimodal data (including cytometry) in the immuno-oncology domain. For example, recent works in the field reduce the predictive markers' deduction to either semi-manual or pairwise combinatorics. Although these analyses are elegant and certainly valid, their completeness and generalizability are suboptimal. Notably, such analyses are deficient in automatically assessing higher-order marker interactions. This is where the network-based approaches and other higher-level analysis methods should come in.
The scope of this Research Topic covers the development and application of the systems biology analysis methods, tools and software in the context of immune-oncology and immunotherapy research. These could range from the machine learning-based approaches to the explicitly network-centered methods to the “traditional” multivariate statistical techniques to the dynamic modeling.
Topic editor Francesco Marincola is the Chief Scientific Officer at Refuge Biotechnologies. All other topic editors declare no competing interests with regards to the Research Topic subject.
Automated analysis of the high-dimensional, multimodal data (FACS, cytometry in general, single-cell) is an active research direction in the areas of immuno-oncology and immunotherapy. Recently, increasingly more sophisticated approaches, most of the data mining/machine learning variety, have been proposed for the primary and secondary analysis of such data, exemplified by the automated gating, clustering, visualization and, subsequently and optionally, cellular population dynamic modeling. Identification of the clinically useful predictive markers (and, perhaps even more importantly, marker combinations) is another important secondary data analysis task.
In general, there is a growing need for the systems biology data analysis pipelines aimed specifically at the high-dimensional multimodal data (including cytometry) in the immuno-oncology domain. For example, recent works in the field reduce the predictive markers' deduction to either semi-manual or pairwise combinatorics. Although these analyses are elegant and certainly valid, their completeness and generalizability are suboptimal. Notably, such analyses are deficient in automatically assessing higher-order marker interactions. This is where the network-based approaches and other higher-level analysis methods should come in.
The scope of this Research Topic covers the development and application of the systems biology analysis methods, tools and software in the context of immune-oncology and immunotherapy research. These could range from the machine learning-based approaches to the explicitly network-centered methods to the “traditional” multivariate statistical techniques to the dynamic modeling.
Topic editor Francesco Marincola is the Chief Scientific Officer at Refuge Biotechnologies. All other topic editors declare no competing interests with regards to the Research Topic subject.
