The future development of personalized medicine depends on a vast exchange of data from different sources, as well as harmonized integrative analysis of large-scale clinical health and sample data. Computational-modelling approaches play a key role in the analysis of the underlying molecular processes and pathways that characterize human biology, but they also lead to a more profound understanding of the mechanisms and factors that drive diseases; hence, they allow personalized treatment strategies that are guided by central clinical questions. However, despite the growing popularity of computational-modelling approaches in different stakeholder communities, there are still many hurdles to overcome for their clinical routine implementation in the future. Especially the integration of heterogeneous data from multiple sources and types are challenging tasks that require clear guidelines that also have to comply with high ethical and legal standards. Here, we discuss the most relevant computational models for personalized medicine in detail that can be considered as best-practice guidelines for application in clinical care. We define specific challenges and provide applicable guidelines and recommendations for study design, data acquisition, and operation as well as for model validation and clinical translation and other research areas.

BACKGROUND: Facing the diversity of omics data and the difficulty of selecting one result over all those produced by several methods, consensus strategies have the potential to reconcile multiple inputs and to produce robust results.
RESULTS: Here, we introduce ClustOmics, a generic consensus clustering tool that we use in the context of cancer subtyping. ClustOmics relies on a non-relational graph database, which allows for the simultaneous integration of both multiple omics data and results from various clustering methods. This new tool conciliates input clusterings, regardless of their origin, their number, their size or their shape. ClustOmics implements an intuitive and flexible strategy, based upon the idea of evidence accumulation clustering. ClustOmics computes co-occurrences of pairs of samples in input clusters and uses this score as a similarity measure to reorganize data into consensus clusters.
CONCLUSIONS: We applied ClustOmics to multi-omics disease subtyping on real TCGA cancer data from ten different cancer types. We showed that ClustOmics is robust to heterogeneous qualities of input partitions, smoothing and reconciling preliminary predictions into high-quality consensus clusters, both from a computational and a biological point of view. The comparison to a state-of-the-art consensus-based integration tool, COCA, further corroborated this statement. However, the main interest of ClustOmics is not to compete with other tools, but rather to make profit from their various predictions when no gold-standard metric is available to assess their significance.
BACKGROUND: The ClustOmics source code, released under MIT license, and the results obtained on TCGA cancer data are available on GitHub: https://github.com/galadrielbriere/ClustOmics .

Advancements in deep learning techniques carry the potential to make significant contributions to healthcare, particularly in fields that utilize medical imaging for diagnosis, prognosis, and treatment decisions. The current state-of-the-art deep learning models for radiology applications consider only pixel-value information without data informing clinical context. Yet in practice, pertinent and accurate non-imaging data based on the clinical history and laboratory data enable physicians to interpret imaging findings in the appropriate clinical context, leading to a higher diagnostic accuracy, informative clinical decision making, and improved patient outcomes. To achieve a similar goal using deep learning, medical imaging pixel-based models must also achieve the capability to process contextual data from electronic health records (EHR) in addition to pixel data. In this paper, we describe different data fusion techniques that can be applied to combine medical imaging with EHR, and systematically review medical data fusion literature published between 2012 and 2020. We conducted a systematic search on PubMed and Scopus for original research articles leveraging deep learning for fusion of multimodality data. In total, we screened 985 studies and extracted data from 17 papers. By means of this systematic review, we present current knowledge, summarize important results and provide implementation guidelines to serve as a reference for researchers interested in the application of multimodal fusion in medical imaging.

Despite the ever-progressing technological advances in producing data in health and clinical research, the generation of new knowledge for medical benefits through advanced analytics still lags behind its full potential. Reasons for this obstacle are the inherent heterogeneity of data sources and the lack of broadly accepted standards. Further hurdles are associated with legal and ethical issues surrounding the use of personal/patient data across disciplines and borders. Consequently, there is a need for broadly applicable standards compliant with legal and ethical regulations that allow interpretation of heterogeneous health data through in silico methodologies to advance personalized medicine. To tackle these standardization challenges, the Horizon2020 Coordinating and Support Action EU-STANDS4PM initiated an EU-wide mapping process to evaluate strategies for data integration and data-driven in silico modelling approaches to develop standards, recommendations and guidelines for personalized medicine. A first step towards this goal is a broad stakeholder consultation process initiated by an EU-STANDS4PM workshop at the annual COMBINE meeting (COMBINE 2019 workshop report in same issue). This forum analysed the status quo of data and model standards and reflected on possibilities as well as challenges for cross-domain data integration to facilitate in silico modelling approaches for personalized medicine.

BACKGROUND: In unsupervised learning and clustering, data integration from different sources and types is a difficult question discussed in several research areas. For instance in omics analysis, dozen of clustering methods have been developed in the past decade. When a single source of data is at play, hierarchical clustering (HC) is extremely popular, as a tree structure is highly interpretable and arguably more informative than just a partition of the data. However, applying blindly HC to multiple sources of data raises computational and interpretation issues.
RESULTS: We propose mergeTrees, a method that aggregates a set of trees with the same leaves to create a consensus tree. In our consensus tree, a cluster at height h contains the individuals that are in the same cluster for all the trees at height h. The method is exact and proven to be [Formula: see text], n being the individuals and q being the number of trees to aggregate. Our implementation is extremely effective on simulations, allowing us to process many large trees at a time. We also rely on mergeTrees to perform the cluster analysis of two real -omics data sets, introducing a spectral variant as an efficient and robust by-product.
CONCLUSIONS: Our tree aggregation method can be used in conjunction with hierarchical clustering to perform efficient cluster analysis. This approach was found to be robust to the absence of clustering information in some of the data sets as well as an increased variability within true clusters. The method is implemented in R/C++ and available as an R package named mergeTrees, which makes it easy to integrate in existing or new pipelines in several research areas.

Next-generation sequencing has allowed identification of millions of somatic mutations in human cancer cells. A key challenge in interpreting cancer genomes is to distinguish drivers of cancer development among available genetic mutations. To address this issue, we present the first web-based application, consensus cancer driver gene caller (C3), to identify the consensus driver genes using six different complementary strategies, i.e., frequency-based, machine learning-based, functional bias-based, clustering-based, statistics model-based, and network-based strategies. This application allows users to specify customized operations when calling driver genes, and provides solid statistical evaluations and interpretable visualizations on the integration results. C3 is implemented in Python and is freely available for public use at http://drivergene.rwebox.com/c3.

Mathematical modeling and numerical simulation are crucial to support design decisions in synthetic biology. Accurate estimation of parameter values is key, as direct experimental measurements are difficult and time-consuming. Insufficient data, incompatible measurements, and specialized models that lack universal parameters make this task challenging. Here, we have created a database (PAMDB) that integrates data from 135 publications that contain 118 circuits and 165 genetic parts of the bacterium Escherichia coli. We used a succinct, universal model formulation to describe the part behavior in each circuit. We introduce a constrained consensus inference method that was used to infer the value of the model parameters and evaluated its performance through cross-validation in a benchmark of 23 circuits. We discuss these results and summarize the challenges in data integration and parameter inference. This work provides a resource and a methodology that can be used as a point of reference for synthetic circuit modeling.

It is widely accepted and acknowledged that data harmonization is crucial: in its absence, the co-analysis of major tranches of high quality extant data is liable to inefficiency or error. However, despite its widespread practice, no formalized/systematic guidelines exist to ensure high quality retrospective data harmonization.
To better understand real-world harmonization practices and facilitate development of formal guidelines, three interrelated initiatives were undertaken between 2006 and 2015. They included a phone survey with 34 major international research initiatives, a series of workshops with experts, and case studies applying the proposed guidelines.
A wide range of projects use retrospective harmonization to support their research activities but even when appropriate approaches are used, the terminologies, procedures, technologies and methods adopted vary markedly. The generic guidelines outlined in this article delineate the essentials required and describe an interdependent step-by-step approach to harmonization: 0) define the research question, objectives and protocol; 1) assemble pre-existing knowledge and select studies; 2) define targeted variables and evaluate harmonization potential; 3) process data; 4) estimate quality of the harmonized dataset(s) generated; and 5) disseminate and preserve final harmonization products.
This manuscript provides guidelines aiming to encourage rigorous and effective approaches to harmonization which are comprehensively and transparently documented and straightforward to interpret and implement. This can be seen as a key step towards implementing guiding principles analogous to those that are well recognised as being essential in securing the foundational underpinning of systematic reviews and the meta-analysis of clinical trials.