Big Data, and in particular Electronic Health Records, provide the medical community with a great opportunity to analyze multiple pathological conditions at an unprecedented depth for many complex diseases, including diabetes. How can we infer on diabetes from large heterogeneous datasets? A possible solution is provided by invoking next‐generation computational methods and data analytics tools within systems medicine approaches. By deciphering the multi‐faceted complexity of biological systems, the potential of emerging diagnostic tools and therapeutic functions can be ultimately revealed. In diabetes, a multidimensional approach to data analysis is needed to better understand the disease conditions, trajectories and the associated comorbidities. Elucidation of multidimensionality comes from the analysis of factors such as disease phenotypes, marker types, and biological motifs while seeking to make use of multiple levels of information including genetics, omics, clinical data, and environmental and lifestyle factors. Examining the synergy between multiple dimensions represents a challenge. In such regard, the role of Big Data fuels the rise of Precision Medicine by allowing an increasing number of descriptions to be captured from individuals. Thus, data curations and analyses should be designed to deliver highly accurate predicted risk profiles and treatment recommendations. It is important to establish linkages between systems and precision medicine in order to translate their principles into clinical practice. Equivalently, to realize their full potential, the involved multiple dimensions must be able to process information ensuring inter‐exchange, reducing ambiguities and redundancies, and ultimately improving health care solutions by introducing clinical decision support systems focused on reclassified phenotypes (or digital biomarkers) and community‐driven patient stratifications.

Treating disease according to precision health requires the individualization of therapeutic solutions as a cardinal step that is part of a process that typically depends on multiple factors. The starting point is the collection and assembly of data over time to assess the patient’s health status and monitor response to therapy. Radiomics is a very important component of this process. Its main goal is implementing a protocol to quantify the image informative contents by first mining and then extracting the most representative features. Further analysis aims to detect potential disease phenotypes through signs and marks of heterogeneity. As multimodal images hinge on various data sources, and these can be integrated with treatment plans and follow-up information, radiomics is naturally centered on dynamically monitoring disease progression and/or the health trajectory of patients. However, radiomics creates critical needs too. A concise list includes: (a) successful harmonization of intra/inter-modality radiomic measurements to facilitate the association with other data domains (genetic, clinical, lifestyle aspects, etc.); (b) ability of data science to revise model strategies and analytics tools to tackle multiple data types and structures (electronic medical records, personal histories, hospitalization data, genomic from various specimens, imaging, etc.) and to offer data-agnostic solutions for patient outcomes prediction; (c) and model validation with independent datasets to ensure generalization of results, clinical value of new risk stratifications, and support to clinical decisions for highly individualized patient management.

This study highlights the relevance of network-guided controllability analysis as a precision oncology tool. Target controllability through networks is potentially relevant to cancer research for the identification of therapeutic targets. With reference to a recent study on multiple phenotypes from 22 Osteosarcoma cell lines characterized both in vitro and in vivo, we found that a variety of critical proteins in OS regulation circuits were in part phenotype-specific and in part shared. To generalize our inference approach and match cancer phenotypic heterogeneity, we employed multitype networks and identified targets in correspondence with protein sub-complexes. Therefore, we established the relevance for diagnostic and therapeutic purposes of inspecting interactive targets, namely those enriched by significant connectivity patterns in protein sub-complexes. Emerging targets appeared with reference to the OS microenvironment, and relatively to SLRP members and D-type cyclins, among other collagen, laminin and keratin proteins. These described were evidences shared across all phenotypes; instead, specific evidences were provided by critical proteins included IGFBP7 and PDGFRA in the invasive phenotype, and FGFR3 and THBS1 in the colony forming phenotype.

Recent pan-cancer studies have shown the importance of coupling DNA methylation patterns with transcriptome profiles to reveal tumor subgroups with clinically relevant distinct characteristics. While the coupling patterns remain in most cases matter for further study and/or interpretation, it is emerging that all associations between epigenetic changes and specific cancer histotypes can facilitate the development of novel epidrugs. In particular, together with chemotherapy and chemoprevention of cancer, these epidrugs will target specific enzymes involved in the complex regulation of gene expression. This perspective surveys recent cancer epigenetic findings on target drugs and therapeutic strategies, and focuses on the epigenetic modifications that can reverse a stable differentiated state of adult cell towards neoplastic phenotypes. The relevance of such developments may thus pave the way for patient’s customized personalized therapies.

Biomedical research is increasingly emphasizing the emerging role of multi-source big data. An example comes from electronically available records of patients from a mix of genotypic, phenotypic, multi-omic and clinical conditions. These data are, in part, already publicly available, and thus call for integration firs, and modelling afterwards. Consequently, a new paradigm of data-intensive biomedicine is naturally leading to novel inference tools, dealing in particular with complex diseases and comorbidities. The latter arise when multiple diseases occur in the same patient, and the complexity of treating such cases is especially high as it involves uncertainty in diagnosis and treatment. We first review some characteristics of such multifaceted complexity, emphasizing the implications for the computational analysis of data interrelationships which in comorbidity studies necessarily span much more than correlative associations. We then describe topics that require closer attention in perspective, in view of a better understanding of the role of multi-evidenced comorbidity data. We finally suggest the rationale for using networks and their tree configurations to explore causality, thus approaching a novel synergistic and translational inference design.