In recent years, large scale, high throughput, omics experiments as well as advanced clinical measurements have resulted in substantial amounts of data of diverse types related to metabolic diseases. Metabolic diseases are complex in nature and affected by multiple factors, for example genetic, molecular, behavioral, lifestyle choices etc. Typically these factors are associated with datasets that necessitate the development of novel multi modal analysis approaches that will allow for the in depth understanding of such disease manifestations. Recent advances of such approaches, usually based on Artificial Intelligence, have been demonstrated to not only cater better disease characterization but also the identification of novel therapeutic targets.
This Systems Endocrinology Special Issue focuses on highlighting the current state of multi omic, multimodal analysis approaches. We anticipate that these approaches will be applied across structured (EHR data, omics data etc), semi structured (clinical letters, notes etc) as well as unstructured (images, videos etc) data types.
We would welcome all studies describing efforts employing a variety of state of the art computational approaches including, but not limited to, AI, statistical and classical bioinformatics for integrating, analyzing and interpreting metabolic disease related data, across scales and levels of granularity from the molecular all the way to the patient population level.
● Insights into metabolic disorders driven by multi-omics analysis. Novel methods for multi omics analysis.
● Use of single cell genomics together with other omics to understand metabolic diseases
● Omics based biomarker or diagnostic methods for metabolic diseases.
● Genotype to phenotype association studies (GWAS, PheWAS), proteins(pGWAS), metabolites(mGWAS) or gene expressions (eQTL) analysis etc.
● Systems medicine or network medicine methods using multi modal data sets.
● Pattern detection and hypothesis generation approaches for patient stratification using multi modal data sets.
● Approaches utilizing multiple data dimensions or modalities for example text, signals, images etc.
● Data Mining, Deep Learning, and Artificial Intelligence novel methods or workflows for multi omics data sets.
● Novel statistical methods and /or analysis studies from multi omics or multi modal data sets.
In recent years, large scale, high throughput, omics experiments as well as advanced clinical measurements have resulted in substantial amounts of data of diverse types related to metabolic diseases. Metabolic diseases are complex in nature and affected by multiple factors, for example genetic, molecular, behavioral, lifestyle choices etc. Typically these factors are associated with datasets that necessitate the development of novel multi modal analysis approaches that will allow for the in depth understanding of such disease manifestations. Recent advances of such approaches, usually based on Artificial Intelligence, have been demonstrated to not only cater better disease characterization but also the identification of novel therapeutic targets.
This Systems Endocrinology Special Issue focuses on highlighting the current state of multi omic, multimodal analysis approaches. We anticipate that these approaches will be applied across structured (EHR data, omics data etc), semi structured (clinical letters, notes etc) as well as unstructured (images, videos etc) data types.
We would welcome all studies describing efforts employing a variety of state of the art computational approaches including, but not limited to, AI, statistical and classical bioinformatics for integrating, analyzing and interpreting metabolic disease related data, across scales and levels of granularity from the molecular all the way to the patient population level.
● Insights into metabolic disorders driven by multi-omics analysis. Novel methods for multi omics analysis.
● Use of single cell genomics together with other omics to understand metabolic diseases
● Omics based biomarker or diagnostic methods for metabolic diseases.
● Genotype to phenotype association studies (GWAS, PheWAS), proteins(pGWAS), metabolites(mGWAS) or gene expressions (eQTL) analysis etc.
● Systems medicine or network medicine methods using multi modal data sets.
● Pattern detection and hypothesis generation approaches for patient stratification using multi modal data sets.
● Approaches utilizing multiple data dimensions or modalities for example text, signals, images etc.
● Data Mining, Deep Learning, and Artificial Intelligence novel methods or workflows for multi omics data sets.
● Novel statistical methods and /or analysis studies from multi omics or multi modal data sets.